First Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ba083d7b6bfec43f9f0b14efac926b82cab40e81071dd81918a542f9aa93b41
+oid sha256:cca4de0ea61c1e66e4df6178a00d2933e7dbfde879f724eb06199c5612cba771
 size 1418184

Pyramids/Pyramids-1000023.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cca4de0ea61c1e66e4df6178a00d2933e7dbfde879f724eb06199c5612cba771
+size 1418184

Pyramids/Pyramids-1000023.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:955b01dcabaa2dfc67e1681953f13e039b786aaf67c543888c05ddb3cff2727d
+size 8650990

Pyramids/Pyramids-499989.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3808f0874fc5900b0c8ed17e14ce8f1a9fe5fed5d560a4cea3ae7203b5a83f73
+size 1418184

Pyramids/Pyramids-499989.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b269a5bee41ec6d1ef26405f799a27e6b5125641aec5e04446eee7bdb41c847
+size 8650990

Pyramids/Pyramids-999959.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cca4de0ea61c1e66e4df6178a00d2933e7dbfde879f724eb06199c5612cba771
+size 1418184

Pyramids/Pyramids-999959.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba8a019ed2ea392b7c0078ff626413b393ab7665b4e405e5d25cc7c3e40b2ac8
+size 8650990

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f805f3035369e3cd092a3e5b104a0405616875d48b1ec3b46577a8347ba0473d
+oid sha256:955b01dcabaa2dfc67e1681953f13e039b786aaf67c543888c05ddb3cff2727d
 size 8650990

Pyramids/{events.out.tfevents.1679265578.0decef17658a.63925.0 → events.out.tfevents.1679268068.0decef17658a.74670.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f275b5de33c27dd52299e41272a8953619c10be0de575f6430d94c218cede37
-size 219575
+oid sha256:9be1c1d2cad632115996c6a87f0feb3793395c785284cf591059df896bda4e98
+size 200428

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 256, "buffer_size": 2048, "learning_rate": 1e-05, "beta": 0.001, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 5, "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": 256, "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, "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": true, "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": 1e-05, "beta": 0.001, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 5, "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": 64, "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, "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": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -3,7 +3,7 @@ behaviors:
   Pyramids:
     trainer_type: ppo
     hyperparameters:
-      batch_size: 256
+      batch_size: 128
       buffer_size: 2048
       learning_rate: 1.0e-05
       beta: 0.001
@@ -52,7 +52,7 @@ behaviors:
     keep_checkpoints: 5
     even_checkpoints: false
     max_steps: 1000000
-    time_horizon: 256
+    time_horizon: 64
     summary_freq: 30000
     threaded: false
     self_play: null

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 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] 55087 [Flags] 2 [Guid] 430651186 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.12 [Port] 55076 [Flags] 2 [Guid] 3214456908 [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'
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
@@ -33,7 +33,7 @@ ALSA lib pcm.c:2642:(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  0.127 seconds
+- Completed reload, in  0.089 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)
@@ -65,7 +65,7 @@ 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: 1.049285 ms
+UnloadTime: 0.822376 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.
@@ -73,7 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 4723 frames, [32.0 KB-64.0 KB]: 13003 frames, [64.0 KB-128.0 KB]: 1060 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 3945 frames, [32.0 KB-64.0 KB]: 13816 frames, [64.0 KB-128.0 KB]: 998 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
@@ -128,12 +128,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 7]
+    [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 15]
+    [ALLOC_TEMP_Background Job.Worker 7]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -146,7 +146,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 480 B
+      Peak Allocated Bytes 240 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -183,12 +183,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0.8 KB
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
+    [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_Background Job.Worker 14]
+    [ALLOC_TEMP_Background Job.Worker 9]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -204,29 +204,29 @@ PlayerConnection::CleanupMemory Statistics:
       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]: 18488 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18461 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 13219
+  Peak main deferred allocation count 12318
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 1 frames, [32.0 MB-64.0 MB]: 18786 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18759 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 47.1 MB
-      Peak Large allocation bytes 16.0 MB
+      Peak Allocated memory 31.1 MB
+      Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames, [4.0 MB-8.0 MB]: 18786 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18760 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 7.5 MB
-      Peak Large allocation bytes 0 B
+      Peak Allocated memory 22.6 MB
+      Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
   Used Block Count 1
@@ -254,13 +254,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18786 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18759 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 18787 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18760 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -272,13 +272,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18488 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18461 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 1.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 18786 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18759 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.7 MB
@@ -290,25 +290,25 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18787 frames
+      Peak usage frame count: [0-1.0 KB]: 18760 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]: 18787 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18760 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.9 KB
       Peak Large allocation bytes 0 B
 [ALLOC_PROFILER]
-  Peak usage frame count: [16.0 KB-32.0 KB]: 18787 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18760 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.0 KB
+  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":1679267528875,"processId":63945,"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}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1679270257162,"processId":74696,"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

@@ -2,171 +2,171 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 1.2146869897842407,
-            "min": 0.9896594882011414,
-            "max": 1.5723788738250732,
+            "value": 1.2178698778152466,
+            "min": 0.978621244430542,
+            "max": 1.531394362449646,
             "count": 33
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 36712.69921875,
-            "min": 29593.240234375,
-            "max": 50316.125,
+            "value": 36302.265625,
+            "min": 29609.1640625,
+            "max": 46456.37890625,
             "count": 33
         },
         "Pyramids.Step.mean": {
-            "value": 989846.0,
-            "min": 29912.0,
-            "max": 989846.0,
+            "value": 989945.0,
+            "min": 29952.0,
+            "max": 989945.0,
             "count": 33
         },
         "Pyramids.Step.sum": {
-            "value": 989846.0,
-            "min": 29912.0,
-            "max": 989846.0,
+            "value": 989945.0,
+            "min": 29952.0,
+            "max": 989945.0,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.09318581968545914,
-            "min": -0.10448312759399414,
-            "max": 0.11592250317335129,
+            "value": -0.09416185319423676,
+            "min": -0.10026509314775467,
+            "max": -0.07534562051296234,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -11.18229866027832,
-            "min": -12.537975311279297,
-            "max": 13.794777870178223,
+            "value": -45.1035270690918,
+            "min": -48.12724304199219,
+            "max": -36.01520538330078,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.009033100679516792,
-            "min": 0.008212273940443993,
-            "max": 0.16503913700580597,
+            "value": 0.006924273446202278,
+            "min": 0.006652571260929108,
+            "max": 0.33888018131256104,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 1.0839720964431763,
-            "min": 0.9854728579521179,
-            "max": 19.639657974243164,
+            "value": 3.3167269229888916,
+            "min": 3.1998867988586426,
+            "max": 160.62921142578125,
             "count": 33
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.04336800926329139,
-            "min": 0.04336800926329139,
-            "max": 0.05144197753541881,
+            "value": 0.06743227906757966,
+            "min": 0.06530650933077896,
+            "max": 0.07187657296773979,
             "count": 33
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.563784120422788,
-            "min": 0.3237078666321135,
-            "max": 0.6904101612473218,
+            "value": 1.011484186013695,
+            "min": 0.6368278165203741,
+            "max": 1.078148594516097,
             "count": 33
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.0006743224475672816,
-            "min": 0.0001644655073101199,
-            "max": 0.009170986648485046,
+            "value": 0.00026463768029013105,
+            "min": 8.607955980854361e-05,
+            "max": 0.009659164084872126,
             "count": 33
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.008766191818374661,
-            "min": 0.0017867105967438659,
-            "max": 0.06419690653939532,
+            "value": 0.0039695652043519655,
+            "min": 0.0012185832862744268,
+            "max": 0.08693247676384913,
             "count": 33
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 2.42748342723077e-07,
-            "min": 2.42748342723077e-07,
-            "max": 9.83835590217143e-06,
+            "value": 2.4928484146000004e-07,
+            "min": 2.4928484146000004e-07,
+            "max": 9.848108185600001e-06,
             "count": 33
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 3.1557284554000004e-06,
-            "min": 3.1557284554000004e-06,
-            "max": 7.406853931520003e-05,
+            "value": 3.7392726219000005e-06,
+            "min": 3.7392726219000005e-06,
+            "max": 0.000125339346608,
             "count": 33
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10242650769230771,
-            "min": 0.10242650769230771,
-            "max": 0.19838354285714285,
+            "value": 0.10249187333333333,
+            "min": 0.10249187333333333,
+            "max": 0.19848106666666665,
             "count": 33
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.3315446000000002,
-            "min": 1.1372405,
-            "max": 2.0230631,
+            "value": 1.5373781,
+            "min": 1.4774085000000003,
+            "max": 2.653392,
             "count": 33
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 3.4022426153846146e-05,
-            "min": 3.4022426153846146e-05,
-            "max": 0.0009839970742857144,
+            "value": 3.4669545999999996e-05,
+            "min": 3.4669545999999996e-05,
+            "max": 0.00098496256,
             "count": 33
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.00044229153999999994,
-            "min": 0.00044229153999999994,
-            "max": 0.00741277952,
+            "value": 0.00052004319,
+            "min": 0.00052004319,
+            "max": 0.0125485808,
             "count": 33
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.008448954671621323,
-            "min": 0.008020293898880482,
-            "max": 0.3150196075439453,
+            "value": 0.006172921974211931,
+            "min": 0.006172921974211931,
+            "max": 0.35047006607055664,
             "count": 33
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.1098364070057869,
-            "min": 0.10856666415929794,
-            "max": 2.205137252807617,
+            "value": 0.09259382635354996,
+            "min": 0.09259382635354996,
+            "max": 3.1542305946350098,
             "count": 33
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 990.8620689655172,
-            "min": 923.6129032258065,
+            "value": 997.7142857142857,
+            "min": 947.8235294117648,
             "max": 999.0,
             "count": 33
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 28735.0,
+            "value": 27936.0,
             "min": 15984.0,
-            "max": 32445.0,
+            "max": 32457.0,
             "count": 33
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": -0.9224483288567642,
-            "min": -1.0000000596046448,
-            "max": -0.6766062993556261,
+            "value": -0.9269714739971927,
+            "min": -1.0000000447034836,
+            "max": -0.7257032734492133,
             "count": 33
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": -26.75100153684616,
-            "min": -32.00000190734863,
-            "max": -21.651401579380035,
+            "value": -25.955201271921396,
+            "min": -31.995601437985897,
+            "max": -16.000000715255737,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": -0.9224483288567642,
-            "min": -1.0000000596046448,
-            "max": -0.6766062993556261,
+            "value": -0.9269714739971927,
+            "min": -1.0000000447034836,
+            "max": -0.7257032734492133,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": -26.75100153684616,
-            "min": -32.00000190734863,
-            "max": -21.651401579380035,
+            "value": -25.955201271921396,
+            "min": -31.995601437985897,
+            "max": -16.000000715255737,
             "count": 33
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.08709845945624442,
-            "min": 0.08274509015910585,
-            "max": 5.101729082024616,
+            "value": 0.06642726676156079,
+            "min": 0.06642726676156079,
+            "max": 7.77874572458677,
             "count": 33
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 2.525855324231088,
-            "min": 2.3996076146140695,
-            "max": 117.33976888656616,
+            "value": 1.8599634693237022,
+            "min": 1.8599634693237022,
+            "max": 124.45993159338832,
             "count": 33
         },
         "Pyramids.IsTraining.mean": {
@@ -184,7 +184,7 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1679265574",
+        "start_time_seconds": "1679268065",
         "python_version": "3.9.16 (main, Dec  7 2022, 01:11:51) \n[GCC 9.4.0]",
         "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 --force",
         "mlagents_version": "0.31.0.dev0",
@@ -192,59 +192,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1679267528"
+        "end_time_seconds": "1679270257"
     },
-    "total": 1954.4793025219988,
+    "total": 2191.6629659499995,
     "count": 1,
-    "self": 0.6379936590001307,
+    "self": 0.5846875659990474,
     "children": {
         "run_training.setup": {
-            "total": 0.12045019099969068,
+            "total": 0.10720040500018513,
             "count": 1,
-            "self": 0.12045019099969068
+            "self": 0.10720040500018513
         },
         "TrainerController.start_learning": {
-            "total": 1953.720858671999,
+            "total": 2190.9710779790003,
             "count": 1,
-            "self": 1.2079912686804164,
+            "self": 1.3612827802971879,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 7.375598333999733,
+                    "total": 5.8314437640001415,
                     "count": 1,
-                    "self": 7.375598333999733
+                    "self": 5.8314437640001415
                 },
                 "TrainerController.advance": {
-                    "total": 1945.0344424873201,
-                    "count": 63165,
-                    "self": 1.3063586383377697,
+                    "total": 2183.676896880701,
+                    "count": 62979,
+                    "self": 1.3647283913815045,
                     "children": {
                         "env_step": {
-                            "total": 1218.0692026518082,
-                            "count": 63165,
-                            "self": 1109.1271717838135,
+                            "total": 1210.1977025874476,
+                            "count": 62979,
+                            "self": 1103.0912961345093,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 108.1541118158857,
-                                    "count": 63165,
-                                    "self": 4.544392002902896,
+                                    "total": 106.31721929490595,
+                                    "count": 62979,
+                                    "self": 4.633913444762584,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 103.6097198129828,
-                                            "count": 62623,
-                                            "self": 103.6097198129828
+                                            "total": 101.68330585014337,
+                                            "count": 62533,
+                                            "self": 101.68330585014337
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.7879190521089185,
-                                    "count": 63165,
+                                    "total": 0.7891871580322913,
+                                    "count": 62979,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1949.9453769584088,
-                                            "count": 63165,
+                                            "total": 2186.867053809863,
+                                            "count": 62979,
                                             "is_parallel": true,
-                                            "self": 949.3234969744371,
+                                            "self": 1190.9609772805125,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.002765096000075573,
+                                                            "total": 0.001743867000186583,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0008359540006495081,
+                                                            "self": 0.0005617989954771474,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.001929141999426065,
+                                                                    "total": 0.0011820680047094356,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.001929141999426065
+                                                                    "self": 0.0011820680047094356
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04595310099830385,
+                                                            "total": 0.04660846600017976,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.000520799998412258,
+                                                            "self": 0.000542361998668639,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00045820000013918616,
+                                                                    "total": 0.00045826900168322027,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00045820000013918616
+                                                                    "self": 0.00045826900168322027
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04335681399970781,
+                                                                    "total": 0.04401887800122495,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04335681399970781
+                                                                    "self": 0.04401887800122495
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0016172870000445982,
+                                                                    "total": 0.0015889569986029528,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00042478900286369026,
+                                                                    "self": 0.000355634001607541,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001192497997180908,
+                                                                            "total": 0.0012333229969954118,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001192497997180908
+                                                                            "self": 0.0012333229969954118
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1000.6218799839717,
-                                                    "count": 63164,
+                                                    "total": 995.9060765293507,
+                                                    "count": 62978,
                                                     "is_parallel": true,
-                                                    "self": 30.076404745150285,
+                                                    "self": 30.054837589927047,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 21.94980984517315,
-                                                            "count": 63164,
+                                                            "total": 21.997584377746534,
+                                                            "count": 62978,
                                                             "is_parallel": true,
-                                                            "self": 21.94980984517315
+                                                            "self": 21.997584377746534
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 860.0084207044274,
-                                                            "count": 63164,
+                                                            "total": 855.7250264272552,
+                                                            "count": 62978,
                                                             "is_parallel": true,
-                                                            "self": 860.0084207044274
+                                                            "self": 855.7250264272552
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 88.58724468922082,
-                                                            "count": 63164,
+                                                            "total": 88.12862813442189,
+                                                            "count": 62978,
                                                             "is_parallel": true,
-                                                            "self": 18.637918927441206,
+                                                            "self": 18.660616718716483,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 69.94932576177962,
-                                                                    "count": 505312,
+                                                                    "total": 69.4680114157054,
+                                                                    "count": 503824,
                                                                     "is_parallel": true,
-                                                                    "self": 69.94932576177962
+                                                                    "self": 69.4680114157054
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 725.6588811971742,
-                            "count": 63165,
-                            "self": 2.3752801694045047,
+                            "total": 972.1144659018719,
+                            "count": 62979,
+                            "self": 2.1299416257825214,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 98.98341768376122,
-                                    "count": 63165,
-                                    "self": 98.77641942575974,
+                                    "total": 139.69850369111737,
+                                    "count": 62979,
+                                    "self": 139.49490435512052,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.20699825800147664,
+                                            "total": 0.20359933599684155,
                                             "count": 2,
-                                            "self": 0.20699825800147664
+                                            "self": 0.20359933599684155
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 624.3001833440085,
-                                    "count": 356,
-                                    "self": 462.13107691998084,
+                                    "total": 830.286020584972,
+                                    "count": 459,
+                                    "self": 525.5271057420978,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 162.16910642402763,
-                                            "count": 18470,
-                                            "self": 162.16910642402763
+                                            "total": 304.7589148428742,
+                                            "count": 38100,
+                                            "self": 304.7589148428742
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.010000212583691e-07,
+                    "total": 9.650029824115336e-07,
                     "count": 1,
-                    "self": 9.010000212583691e-07
+                    "self": 9.650029824115336e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.10282568099864875,
+                    "total": 0.10145358899899293,
                     "count": 1,
-                    "self": 0.0017251659992325585,
+                    "self": 0.0016745319990150165,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.10110051499941619,
+                            "total": 0.09977905699997791,
                             "count": 1,
-                            "self": 0.10110051499941619
+                            "self": 0.09977905699997791
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,40 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499938,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499938.onnx",
-                "reward": -0.9994000494480133,
-                "creation_time": 1679266539.4776866,
+                "steps": 499989,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499989.onnx",
+                "reward": null,
+                "creation_time": 1679269153.792673,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499938.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499989.pt"
                 ]
             },
             {
-                "steps": 999798,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999798.onnx",
+                "steps": 999959,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999959.onnx",
                 "reward": null,
-                "creation_time": 1679267528.162051,
+                "creation_time": 1679270256.5306325,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999798.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-999959.pt"
                 ]
             },
             {
-                "steps": 1000054,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000054.onnx",
+                "steps": 1000023,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000023.onnx",
                 "reward": null,
-                "creation_time": 1679267528.2810836,
+                "creation_time": 1679270256.6381073,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000054.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1000023.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000054,
+            "steps": 1000023,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
             "reward": null,
-            "creation_time": 1679267528.2810836,
+            "creation_time": 1679270256.6381073,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000054.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1000023.pt"
             ]
         }
     },