First Push

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1700a38244be88a5d9be6afc9498afbb0b14d680bd3a66b86d343d24f7a17bbb
+size 1420238

Pyramids/Pyramids-1000041.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1700a38244be88a5d9be6afc9498afbb0b14d680bd3a66b86d343d24f7a17bbb
+size 1420238

Pyramids/Pyramids-1000041.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5554b5f6973cc08bba12d23a16f8b409c0e8158b17b8e9003abe4d5094484696
+size 8656252

Pyramids/Pyramids-499921.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e783e3621c9d4052a228d9d167f59d68cfa34667e9f289abb28bbede12ed5d44
+size 1420238

Pyramids/Pyramids-499921.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b41136dcbf9009b50e10db540358ef0cce4d5c03fd176a66fdd00b1cbaeb3acd
+size 8656173

Pyramids/Pyramids-999913.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1700a38244be88a5d9be6afc9498afbb0b14d680bd3a66b86d343d24f7a17bbb
+size 1420238

Pyramids/Pyramids-999913.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:136e63e636d8f5d4e4189298c5e217c1cdb680a75199637bef5ea8d1f5eba869
+size 8656173

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6038c17514f9dc78730b970222563917eb10c00a403ae5f841f25a46fe0ede7
+size 8655778

Pyramids/events.out.tfevents.1700217976.49d0b286b7ef.8919.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67d8b3b1599a63239e59f7d119ff43a3d19ea73b2aae7e42fa472e2fd01f33a0
+size 333027

README.md

@@ -1,14 +1,14 @@
 ---
 library_name: ml-agents
 tags:
-- SnowballTarget
+- Pyramids
 - deep-reinforcement-learning
 - reinforcement-learning
-- ML-Agents-SnowballTarget
+- ML-Agents-Pyramids
 ---
 
-  # **ppo** Agent playing **SnowballTarget**
-  This is a trained model of a **ppo** agent playing **SnowballTarget**
+  # **ppo** Agent playing **Pyramids**
+  This is a trained model of a **ppo** agent playing **Pyramids**
   using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
 
   ## Usage (with ML-Agents)

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -1,12 +1,12 @@
 default_settings: null
 behaviors:
-  SnowballTarget:
+  Pyramids:
     trainer_type: ppo
     hyperparameters:
       batch_size: 128
       buffer_size: 2048
       learning_rate: 0.0003
-      beta: 0.005
+      beta: 0.01
       epsilon: 0.2
       lambd: 0.95
       num_epoch: 3
@@ -14,10 +14,10 @@ behaviors:
       learning_rate_schedule: linear
       beta_schedule: linear
       epsilon_schedule: linear
-    checkpoint_interval: 50000
+    checkpoint_interval: 500000
     network_settings:
       normalize: false
-      hidden_units: 256
+      hidden_units: 512
       num_layers: 2
       vis_encode_type: simple
       memory: null
@@ -35,17 +35,30 @@ behaviors:
           memory: null
           goal_conditioning_type: hyper
           deterministic: false
+      rnd:
+        gamma: 0.99
+        strength: 0.01
+        network_settings:
+          normalize: false
+          hidden_units: 64
+          num_layers: 3
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+        learning_rate: 0.0001
+        encoding_size: null
     init_path: null
-    keep_checkpoints: 10
+    keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 200000
-    time_horizon: 64
-    summary_freq: 10000
-    threaded: true
+    max_steps: 1000000
+    time_horizon: 128
+    summary_freq: 30000
+    threaded: false
     self_play: null
     behavioral_cloning: null
 env_settings:
-  env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
+  env_path: ./training-envs-executables/linux/Pyramids/Pyramids
   env_args: null
   base_port: 5005
   num_envs: 1
@@ -65,7 +78,7 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget1
+  run_id: Pyramids Training
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -1,12 +1,14 @@
-Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
-Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
+Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
+Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+Found 1 interfaces on host : 0) 172.28.0.12
+Multi-casting "[IP] 172.28.0.12 [Port] 55272 [Flags] 2 [Guid] 3327517883 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
+PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
+PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
 Unable to load player prefs
-Initialize engine version: 2021.3.14f1 (eee1884e7226)
-[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
+Initialize engine version: 2021.3.5f1 (40eb3a945986)
+[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
 GfxDevice: creating device client; threaded=0; jobified=0
 NullGfxDevice:
@@ -34,10 +36,31 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.085 seconds
+- Completed reload, in  0.146 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Legacy Shaders/Diffuse shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'ML-Agents/GridPattern' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader ML-Agents/GridPattern shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'ML-Agents/GridPattern' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
@@ -45,85 +68,90 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.692805 ms
+UnloadTime: 1.065021 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
-Memory Statistics:
+PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 5368 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 9081 frames, [32.0 KB-64.0 KB]: 7409 frames, [64.0 KB-128.0 KB]: 2280 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
       Overflow Count 0
-    [ALLOC_TEMP_Loading.AsyncRead]
-      Initial Block Size 64.0 KB
-      Current Block Size 64.0 KB
-      Peak Allocated Bytes 198 B
-      Overflow Count 0
-    [ALLOC_TEMP_Loading.PreloadManager]
-      Initial Block Size 256.0 KB
-      Current Block Size 304.0 KB
-      Peak Allocated Bytes 228.9 KB
-      Overflow Count 4
     [ALLOC_TEMP_Background Job.Worker 8]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
+    [ALLOC_TEMP_Background Job.Worker 10]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 0]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
-      Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 10]
+    [ALLOC_TEMP_Background Job.Worker 6]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 14]
+    [ALLOC_TEMP_AUDIO_FMOD mixer thread]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 6]
+    [ALLOC_TEMP_Background Job.Worker 11]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 12]
+    [ALLOC_TEMP_Background Job.Worker 3]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_EnlightenWorker]
+    [ALLOC_TEMP_BatchDeleteObjects]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_AUDIO_FMOD stream thread]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 1]
+    [ALLOC_TEMP_Background Job.Worker 7]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 2]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 7]
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 320.0 KB
+      Peak Allocated Bytes 251.5 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Profiler.Dispatcher]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 240 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -143,49 +171,65 @@ Memory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 11]
+    [ALLOC_TEMP_Background Job.Worker 0]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 3]
+    [ALLOC_TEMP_Background Job.Worker 4]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 0]
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 4]
+    [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_BatchDeleteObjects]
+    [ALLOC_TEMP_EnlightenWorker]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 128 B
+      Overflow Count 0
+[ALLOC_MEMORYPROFILER]
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18472 frames
+  Requested Block Size 1.0 MB
+  Peak Block count 2
+  Peak Allocated memory 1.6 MB
+  Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 40
+  Peak main deferred allocation count 12451
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.0 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 5460 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 1 frames, [32.0 MB-64.0 MB]: 18770 frames
       Requested Block Size 16.0 MB
-      Peak Block count 1
-      Peak Allocated memory 6.6 MB
-      Peak Large allocation bytes 0 B
+      Peak Block count 3
+      Peak Allocated memory 45.9 MB
+      Peak Large allocation bytes 16.0 MB
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 5460 frames
+      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames, [4.0 MB-8.0 MB]: 18770 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.7 MB
-      Peak Large allocation bytes 16.0 MB
+      Peak Allocated memory 7.7 MB
+      Peak Large allocation bytes 0 B
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
   Used Block Count 1
@@ -211,52 +255,63 @@ Memory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.0 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 4786 frames, [64.0 KB-128.0 KB]: 674 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18770 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 66.8 KB
+      Peak Allocated memory 67.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 5460 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18771 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 39.6 KB
+      Peak Allocated memory 67.7 KB
       Peak Large allocation bytes 0 B
 [ALLOC_CACHEOBJECTS] Dual Thread Allocator
-  Peak main deferred allocation count 0
+  Peak main deferred allocation count 1
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.0 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5460 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18472 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
-      Peak Allocated memory 0.6 MB
+      Peak Allocated memory 1.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5459 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18770 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
-      Peak Block count 1
-      Peak Allocated memory 2.2 MB
+      Peak Block count 2
+      Peak Allocated memory 4.7 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.0 MB
+      Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 5460 frames
+      Peak usage frame count: [0-1.0 KB]: 18771 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 5460 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18771 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
-      Peak Allocated memory 1.7 KB
+      Peak Allocated memory 1.9 KB
       Peak Large allocation bytes 0 B
+[ALLOC_PROFILER]
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18771 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 29.2 KB
+  Peak Large allocation bytes 0 B
+    [ALLOC_PROFILER_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 396 B
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1700220260474,"processId":8942,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -1,214 +1,250 @@
 {
     "name": "root",
     "gauges": {
-        "SnowballTarget.Policy.Entropy.mean": {
-            "value": 0.9257236123085022,
-            "min": 0.9257236123085022,
-            "max": 2.85087251663208,
-            "count": 20
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.2128964066505432,
+            "min": 0.21030749380588531,
+            "max": 1.5014017820358276,
+            "count": 33
         },
-        "SnowballTarget.Policy.Entropy.sum": {
-            "value": 8848.9921875,
-            "min": 8848.9921875,
-            "max": 29227.14453125,
-            "count": 20
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 6417.54931640625,
+            "min": 6352.96875,
+            "max": 45546.5234375,
+            "count": 33
         },
-        "SnowballTarget.Step.mean": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+        "Pyramids.Step.mean": {
+            "value": 989942.0,
+            "min": 29939.0,
+            "max": 989942.0,
+            "count": 33
         },
-        "SnowballTarget.Step.sum": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+        "Pyramids.Step.sum": {
+            "value": 989942.0,
+            "min": 29939.0,
+            "max": 989942.0,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 13.057461738586426,
-            "min": 0.38897618651390076,
-            "max": 13.057461738586426,
-            "count": 20
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.31374651193618774,
+            "min": -0.08951158821582794,
+            "max": 0.31374651193618774,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2546.205078125,
-            "min": 75.46138000488281,
-            "max": 2640.293701171875,
-            "count": 20
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 81.5740966796875,
+            "min": -21.66180419921875,
+            "max": 81.5740966796875,
+            "count": 33
         },
-        "SnowballTarget.Environment.EpisodeLength.mean": {
-            "value": 199.0,
-            "min": 199.0,
-            "max": 199.0,
-            "count": 20
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": -0.004393260460346937,
+            "min": -0.012115906924009323,
+            "max": 0.23532558977603912,
+            "count": 33
         },
-        "SnowballTarget.Environment.EpisodeLength.sum": {
-            "value": 8756.0,
-            "min": 8756.0,
-            "max": 10945.0,
-            "count": 20
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": -1.1422476768493652,
+            "min": -3.1380198001861572,
+            "max": 56.47814178466797,
+            "count": 33
         },
-        "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.06732053183876298,
-            "min": 0.06322166504265339,
-            "max": 0.0742530175035353,
-            "count": 20
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06752732259199201,
+            "min": 0.06522106252393847,
+            "max": 0.07279608260828112,
+            "count": 33
         },
-        "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.2692821273550519,
-            "min": 0.2605167574655235,
-            "max": 0.35981430531155284,
-            "count": 20
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.9453825162878882,
+            "min": 0.5798006398301124,
+            "max": 1.0843246984683599,
+            "count": 33
         },
-        "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.22601626988719492,
-            "min": 0.13982274073778705,
-            "max": 0.29387098704190817,
-            "count": 20
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.012615614256425206,
+            "min": 0.0011345364677769788,
+            "max": 0.012615614256425206,
+            "count": 33
         },
-        "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.9040650795487797,
-            "min": 0.5592909629511482,
-            "max": 1.3585495837763246,
-            "count": 20
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.17661859958995288,
+            "min": 0.015883510548877704,
+            "max": 0.17661859958995288,
+            "count": 33
         },
-        "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 8.082097306000005e-06,
-            "min": 8.082097306000005e-06,
-            "max": 0.000291882002706,
-            "count": 20
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 7.41896895561429e-06,
+            "min": 7.41896895561429e-06,
+            "max": 0.0002948414642195125,
+            "count": 33
         },
-        "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 3.232838922400002e-05,
-            "min": 3.232838922400002e-05,
-            "max": 0.00138516003828,
-            "count": 20
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 0.00010386556537860007,
+            "min": 0.00010386556537860007,
+            "max": 0.003634944488351899,
+            "count": 33
         },
-        "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10269400000000001,
-            "min": 0.10269400000000001,
-            "max": 0.19729400000000002,
-            "count": 20
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10247295714285716,
+            "min": 0.10247295714285716,
+            "max": 0.1982804875,
+            "count": 33
         },
-        "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.41077600000000003,
-            "min": 0.41077600000000003,
-            "max": 0.96172,
-            "count": 20
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4346214000000002,
+            "min": 1.4346214000000002,
+            "max": 2.6116481,
+            "count": 33
         },
-        "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0001444306000000001,
-            "min": 0.0001444306000000001,
-            "max": 0.0048649706,
-            "count": 20
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.0002570484185714287,
+            "min": 0.0002570484185714287,
+            "max": 0.009828220701250001,
+            "count": 33
         },
-        "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.0005777224000000004,
-            "min": 0.0005777224000000004,
-            "max": 0.023089828,
-            "count": 20
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.0035986778600000024,
+            "min": 0.0035986778600000024,
+            "max": 0.12118364519000002,
+            "count": 33
         },
-        "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 25.818181818181817,
-            "min": 3.840909090909091,
-            "max": 26.0,
-            "count": 20
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.008793679997324944,
+            "min": 0.008624312467873096,
+            "max": 0.30082982778549194,
+            "count": 33
         },
-        "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1136.0,
-            "min": 169.0,
-            "max": 1411.0,
-            "count": 20
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.12311152368783951,
+            "min": 0.12224704027175903,
+            "max": 2.4066386222839355,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 25.818181818181817,
-            "min": 3.840909090909091,
-            "max": 26.0,
-            "count": 20
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 510.0175438596491,
+            "min": 510.0175438596491,
+            "max": 999.0,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1136.0,
-            "min": 169.0,
-            "max": 1411.0,
-            "count": 20
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 29071.0,
+            "min": 16482.0,
+            "max": 33890.0,
+            "count": 33
         },
-        "SnowballTarget.IsTraining.mean": {
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.1038982205485042,
+            "min": -0.9999750521965325,
+            "max": 1.1683428294158407,
+            "count": 33
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 62.922198571264744,
+            "min": -31.99920167028904,
+            "max": 65.42719844728708,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.1038982205485042,
+            "min": -0.9999750521965325,
+            "max": 1.1683428294158407,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 62.922198571264744,
+            "min": -31.99920167028904,
+            "max": 65.42719844728708,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.04689537300784427,
+            "min": 0.04689537300784427,
+            "max": 6.564111180165234,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 2.6730362614471233,
+            "min": 2.656817455776036,
+            "max": 111.58989006280899,
+            "count": 33
+        },
+        "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 33
         },
-        "SnowballTarget.IsTraining.sum": {
+        "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 33
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1700216438",
+        "start_time_seconds": "1700217974",
         "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.1.0+cu118",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1700216940"
+        "end_time_seconds": "1700220260"
     },
-    "total": 502.22486539500005,
+    "total": 2285.5228324429995,
     "count": 1,
-    "self": 0.42500524199999745,
+    "self": 0.43572933299901706,
     "children": {
         "run_training.setup": {
-            "total": 0.044669948999967346,
+            "total": 0.04166331700025694,
             "count": 1,
-            "self": 0.044669948999967346
+            "self": 0.04166331700025694
         },
         "TrainerController.start_learning": {
-            "total": 501.7551902040001,
+            "total": 2285.0454397930002,
             "count": 1,
-            "self": 0.6259564039945644,
+            "self": 1.5995892299156367,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 8.176201995999918,
+                    "total": 4.784148884999922,
                     "count": 1,
-                    "self": 8.176201995999918
+                    "self": 4.784148884999922
                 },
                 "TrainerController.advance": {
-                    "total": 492.8657697680055,
-                    "count": 18200,
-                    "self": 0.3013136200193003,
+                    "total": 2278.586472650084,
+                    "count": 63598,
+                    "self": 1.7262340438956016,
                     "children": {
                         "env_step": {
-                            "total": 492.5644561479862,
-                            "count": 18200,
-                            "self": 340.4087428389854,
+                            "total": 1625.3484271650227,
+                            "count": 63598,
+                            "self": 1480.2039698739654,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 151.84856054499312,
-                                    "count": 18200,
-                                    "self": 1.5237474409943843,
+                                    "total": 144.18083631203308,
+                                    "count": 63598,
+                                    "self": 4.871128785942801,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 150.32481310399874,
-                                            "count": 18200,
-                                            "self": 150.32481310399874
+                                            "total": 139.30970752609028,
+                                            "count": 62570,
+                                            "self": 139.30970752609028
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.30715276400769653,
-                                    "count": 18200,
+                                    "total": 0.9636209790241992,
+                                    "count": 63598,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 500.231713596996,
-                                            "count": 18200,
+                                            "total": 2279.820372581928,
+                                            "count": 63598,
                                             "is_parallel": true,
-                                            "self": 242.62562280699456,
+                                            "self": 930.9025903088218,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.005502616999933707,
+                                                            "total": 0.002430161999654956,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.003849871999818788,
+                                                            "self": 0.0006677939982182579,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.001652745000114919,
-                                                                    "count": 10,
+                                                                    "total": 0.0017623680014366983,
+                                                                    "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.001652745000114919
+                                                                    "self": 0.0017623680014366983
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.06710519199998544,
+                                                            "total": 0.05362268099997891,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006720140000879837,
+                                                            "self": 0.0005593279997810896,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004172659999994721,
+                                                                    "total": 0.0005006799997318012,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004172659999994721
+                                                                    "self": 0.0005006799997318012
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.06410648499991112,
+                                                                    "total": 0.04883407600027567,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.06410648499991112
+                                                                    "self": 0.04883407600027567
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.001909426999986863,
+                                                                    "total": 0.003728597000190348,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003494110001156514,
+                                                                    "self": 0.0003880680005750037,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0015600159998712115,
-                                                                            "count": 10,
+                                                                            "total": 0.0033405289996153442,
+                                                                            "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0015600159998712115
+                                                                            "self": 0.0033405289996153442
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 257.6060907900014,
-                                                    "count": 18199,
+                                                    "total": 1348.9177822731062,
+                                                    "count": 63597,
                                                     "is_parallel": true,
-                                                    "self": 11.028681755007483,
+                                                    "self": 35.88211202110733,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 5.764600804994188,
-                                                            "count": 18199,
+                                                            "total": 26.179195308036924,
+                                                            "count": 63597,
                                                             "is_parallel": true,
-                                                            "self": 5.764600804994188
+                                                            "self": 26.179195308036924
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 204.0870958390043,
-                                                            "count": 18199,
+                                                            "total": 1181.33779482701,
+                                                            "count": 63597,
                                                             "is_parallel": true,
-                                                            "self": 204.0870958390043
+                                                            "self": 1181.33779482701
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 36.725712390995454,
-                                                            "count": 18199,
+                                                            "total": 105.51868011695205,
+                                                            "count": 63597,
                                                             "is_parallel": true,
-                                                            "self": 7.147675778994085,
+                                                            "self": 22.222502548862394,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 29.57803661200137,
-                                                                    "count": 181990,
+                                                                    "total": 83.29617756808966,
+                                                                    "count": 508776,
                                                                     "is_parallel": true,
-                                                                    "self": 29.57803661200137
+                                                                    "self": 83.29617756808966
                                                                 }
                                                             }
                                                         }
@@ -305,53 +341,33 @@
                                     }
                                 }
                             }
-                        }
-                    }
-                },
-                "trainer_threads": {
-                    "total": 0.00012291200005165592,
-                    "count": 1,
-                    "self": 0.00012291200005165592,
-                    "children": {
-                        "thread_root": {
-                            "total": 0.0,
-                            "count": 0,
-                            "is_parallel": true,
-                            "self": 0.0,
+                        },
+                        "trainer_advance": {
+                            "total": 651.5118114411657,
+                            "count": 63598,
+                            "self": 3.1603776352335444,
                             "children": {
-                                "trainer_advance": {
-                                    "total": 488.59221939203417,
-                                    "count": 518912,
-                                    "is_parallel": true,
-                                    "self": 11.22611798205412,
+                                "process_trajectory": {
+                                    "total": 129.76795496093155,
+                                    "count": 63598,
+                                    "self": 129.5387627909322,
                                     "children": {
-                                        "process_trajectory": {
-                                            "total": 278.8572700369805,
-                                            "count": 518912,
-                                            "is_parallel": true,
-                                            "self": 277.5229314349805,
-                                            "children": {
-                                                "RLTrainer._checkpoint": {
-                                                    "total": 1.3343386020000025,
-                                                    "count": 4,
-                                                    "is_parallel": true,
-                                                    "self": 1.3343386020000025
-                                                }
-                                            }
-                                        },
-                                        "_update_policy": {
-                                            "total": 198.50883137299957,
-                                            "count": 90,
-                                            "is_parallel": true,
-                                            "self": 63.03522133899946,
-                                            "children": {
-                                                "TorchPPOOptimizer.update": {
-                                                    "total": 135.4736100340001,
-                                                    "count": 4587,
-                                                    "is_parallel": true,
-                                                    "self": 135.4736100340001
-                                                }
-                                            }
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.22919216999935088,
+                                            "count": 2,
+                                            "self": 0.22919216999935088
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 518.5834788450006,
+                                    "count": 457,
+                                    "self": 308.4481009559704,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 210.13537788903022,
+                                            "count": 22767,
+                                            "self": 210.13537788903022
                                         }
                                     }
                                 }
@@ -359,15 +375,20 @@
                         }
                     }
                 },
+                "trainer_threads": {
+                    "total": 9.960003808373585e-07,
+                    "count": 1,
+                    "self": 9.960003808373585e-07
+                },
                 "TrainerController._save_models": {
-                    "total": 0.0871391240000321,
+                    "total": 0.07522803200026829,
                     "count": 1,
-                    "self": 0.0008231500000874803,
+                    "self": 0.0012851960009356844,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.08631597399994462,
+                            "total": 0.0739428359993326,
                             "count": 1,
-                            "self": 0.08631597399994462
+                            "self": 0.0739428359993326
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,59 +1,41 @@
 {
-    "SnowballTarget": {
+    "Pyramids": {
         "checkpoints": [
             {
-                "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 12.363636363636363,
-                "creation_time": 1700216574.3941166,
+                "steps": 499921,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499921.onnx",
+                "reward": -0.999800056219101,
+                "creation_time": 1700219071.7869961,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499921.pt"
                 ]
             },
             {
-                "steps": 99960,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 21.0,
-                "creation_time": 1700216696.1662965,
+                "steps": 999913,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999913.onnx",
+                "reward": -0.9992000460624695,
+                "creation_time": 1700220259.9968917,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-999913.pt"
                 ]
             },
             {
-                "steps": 149984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 25.90909090909091,
-                "creation_time": 1700216819.1469169,
+                "steps": 1000041,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000041.onnx",
+                "reward": -0.9992000460624695,
+                "creation_time": 1700220260.0824633,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
-                ]
-            },
-            {
-                "steps": 199984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 25.454545454545453,
-                "creation_time": 1700216940.093626,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
-                ]
-            },
-            {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 25.454545454545453,
-                "creation_time": 1700216940.2137508,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1000041.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200112,
-            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 25.454545454545453,
-            "creation_time": 1700216940.2137508,
+            "steps": 1000041,
+            "file_path": "results/Pyramids Training/Pyramids.onnx",
+            "reward": -0.9992000460624695,
+            "creation_time": 1700220260.0824633,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1000041.pt"
             ]
         }
     },