first attempt

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83ee0483f6fde00d85b83faaa0dcd5aa00b76af366845673b4a1693c62557d85
+oid sha256:0114b7504287238e035d0e3d0e97728c844b4281fccd4d8390bf7b38a66a26e5
 size 646532

SnowballTarget/SnowballTarget-149800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ae8230c8ef481cbe8dd45a3acca3d363e5e273426515ac57c022cf6703776e
+size 646532

SnowballTarget/SnowballTarget-149800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ead86d8fbe68fbbeca2bd21975c1e6aed77011115c076185269ee41ea739e738
+size 3843968

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe3eb0bebe3a96aa791b2e57cb0b627b2401e4ddf9b94a1a8e34a81392cd1988
+oid sha256:9a855931a9c292fa992f49e8fa7c86d184444a5c260faddb90ea7963bd6dc9be
 size 646532

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf4ba6b2210a37e004ddf49c0b7f9c9ef752eef6fc4d96b81cf2d46630441a0d
+oid sha256:f22346cf76fac75fd80eea0437877147b6fb0d3c92fa7debccb67d739d0efa3b
 size 3843968

SnowballTarget/SnowballTarget-180400.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0096ff72b20dbe868a5364435f23065812d1d51b0bc4edd97fed5af26189b6fb
+size 646532

SnowballTarget/SnowballTarget-180400.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d2150ca8dbb3f81ceece1036afad10bc10af2479c1054e77d44af1d357772f0
+size 3843968

SnowballTarget/SnowballTarget-199800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0114b7504287238e035d0e3d0e97728c844b4281fccd4d8390bf7b38a66a26e5
+size 646532

SnowballTarget/SnowballTarget-199800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72ed3e272cddcc5e08140c6c0327e0379a77eaf6178a9a9e74db3ee26db6f0db
+size 3843968

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83ee0483f6fde00d85b83faaa0dcd5aa00b76af366845673b4a1693c62557d85
+oid sha256:e921599490596056f50cdc872e7c2eec825d7bd7547aba5b1484a51b248d56c7
 size 646532

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a95d06a972598a8a4187a0b1ab1b38177613ae8d6761ff295b08f1c8a14e8889
+oid sha256:e0090e049472e213380a1fb6f00a76e5c6c9f4dc50bbd1318ec7a7c092ebe66b
 size 3843968

SnowballTarget/SnowballTarget-200200.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0114b7504287238e035d0e3d0e97728c844b4281fccd4d8390bf7b38a66a26e5
+size 646532

SnowballTarget/SnowballTarget-200200.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:532f7c097a0ed8694e9c4822be6d505d9ed870087f07d87313c4f1f37758df9a
+size 3843968

SnowballTarget/SnowballTarget-49800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fefb87f80b8d5774f4faf6b974cce35c0eb16c5fd4c7d979c722a5171e92b58
+size 646532

SnowballTarget/SnowballTarget-49800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce1c8644454fa345bbb8377d9ccfe8bca37b1227920f0836f555a9cb0e95c6a7
+size 3843968

SnowballTarget/SnowballTarget-49952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e8bc0f9be79217433f74b39b947d30f16f299feda66a87ad66867cfaff028ce
+size 646532

SnowballTarget/SnowballTarget-49952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73d63c4dce7ffa1002aba3821c2b85e330ff6b1a8de372e97492f077d754d79f
+size 3843968

SnowballTarget/SnowballTarget-99800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b78886b05b8928a18d70ac0d7ad93b4001f73b86166a093efb7596b4396dfc2b
+size 646532

SnowballTarget/SnowballTarget-99800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d5623c533decebf6d7f9b5a66fc14c88637fea8a63a0bd58d0997c68abfa7bf
+size 3843968

SnowballTarget/SnowballTarget-99896.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c9b1a3fac0ac7f13c22e81d402fda4be39d4eeae07e0db1c6f571040c8abed1
+size 646532

SnowballTarget/SnowballTarget-99896.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cbb870e3f0cff3cd28884ab3554b8ef52c031b5141b5ba87c28c024bc91ac18
+size 3843968

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b61232ddee2b11d13f90f75188677fda5f3254e949d5cb74fe5730a2e48d7b5
+oid sha256:532f7c097a0ed8694e9c4822be6d505d9ed870087f07d87313c4f1f37758df9a
 size 3843968

SnowballTarget/events.out.tfevents.1695401511.b12cb4178495.38096.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:802fb152758dc1cd5415c1b3dd6002c25cdafbc0992e2130657d328e64c0d362
+size 28719

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, "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": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.005, "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": 0.95, "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": 256, "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, "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": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -5,7 +5,7 @@ behaviors:
     hyperparameters:
       batch_size: 128
       buffer_size: 2048
-      learning_rate: 0.0003
+      learning_rate: 0.005
       beta: 0.005
       epsilon: 0.2
       lambd: 0.95
@@ -25,7 +25,7 @@ behaviors:
       deterministic: false
     reward_signals:
       extrinsic:
-        gamma: 0.99
+        gamma: 0.95
         strength: 1.0
         network_settings:
           normalize: false
@@ -39,7 +39,7 @@ behaviors:
     keep_checkpoints: 10
     even_checkpoints: false
     max_steps: 200000
-    time_horizon: 64
+    time_horizon: 256
     summary_freq: 10000
     threaded: true
     self_play: null
@@ -68,7 +68,7 @@ checkpoint_settings:
   initialize_from: null
   load_model: false
   resume: false
-  force: false
+  force: true
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
 Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
 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
-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
 Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ 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  0.079 seconds
+- Completed reload, in  0.144 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)
@@ -45,7 +42,7 @@ 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: 0.650181 ms
+UnloadTime: 0.852645 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.
@@ -53,7 +50,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 5370 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 5373 frames, [16.0 KB-32.0 KB]: 91 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
@@ -169,22 +166,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 41
+  Peak main deferred allocation count 46
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 5462 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 5465 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 7.1 MB
+      Peak Allocated memory 6.9 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 5462 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5465 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.3 MB
+      Peak Allocated memory 17.5 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -213,13 +210,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 4731 frames, [64.0 KB-128.0 KB]: 731 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5022 frames, [64.0 KB-128.0 KB]: 443 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 66.4 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 5462 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5465 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -231,13 +228,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5462 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5465 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 0.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5461 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5464 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 MB
@@ -249,13 +246,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 5462 frames
+      Peak usage frame count: [0-1.0 KB]: 5465 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]: 5462 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 5465 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -2,135 +2,135 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 0.9905679821968079,
-            "min": 0.9905679821968079,
-            "max": 2.870112419128418,
+            "value": 1.2230117321014404,
+            "min": 1.2230117321014404,
+            "max": 2.8615801334381104,
             "count": 20
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 9479.7353515625,
-            "min": 9479.7353515625,
-            "max": 29392.8203125,
+            "value": 10843.2216796875,
+            "min": 10843.2216796875,
+            "max": 31634.767578125,
+            "count": 20
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 20
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 8756.0,
+            "max": 10945.0,
             "count": 20
         },
         "SnowballTarget.Step.mean": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
+            "value": 199800.0,
+            "min": 9800.0,
+            "max": 199800.0,
             "count": 20
         },
         "SnowballTarget.Step.sum": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
+            "value": 199800.0,
+            "min": 9800.0,
+            "max": 199800.0,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 12.542269706726074,
-            "min": 0.436093270778656,
-            "max": 12.641898155212402,
+            "value": 2.6578848361968994,
+            "min": 0.1388860046863556,
+            "max": 2.6578848361968994,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2445.74267578125,
-            "min": 84.60209655761719,
-            "max": 2578.947265625,
+            "value": 132.8942413330078,
+            "min": 6.805414199829102,
+            "max": 132.8942413330078,
             "count": 20
         },
-        "SnowballTarget.Environment.EpisodeLength.mean": {
-            "value": 199.0,
-            "min": 199.0,
-            "max": 199.0,
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 26.06,
+            "min": 3.306122448979592,
+            "max": 26.06,
             "count": 20
         },
-        "SnowballTarget.Environment.EpisodeLength.sum": {
-            "value": 8756.0,
-            "min": 8756.0,
-            "max": 10945.0,
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1303.0,
+            "min": 162.0,
+            "max": 1303.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 26.06,
+            "min": 3.306122448979592,
+            "max": 26.06,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1303.0,
+            "min": 162.0,
+            "max": 1303.0,
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.06483898489372508,
-            "min": 0.06352636912976653,
-            "max": 0.07632039742772986,
+            "value": 0.06663666524086603,
+            "min": 0.062078236376857034,
+            "max": 0.07542671996177923,
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.25935593957490033,
-            "min": 0.2541054765190661,
-            "max": 0.37813210600242936,
+            "value": 0.26654666096346413,
+            "min": 0.24831294550742813,
+            "max": 0.3654332542928922,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.21808049170409932,
-            "min": 0.1486261908556152,
-            "max": 0.2853587735517352,
+            "value": 0.1303019299007514,
+            "min": 0.1107853918098936,
+            "max": 0.16196015699237,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.8723219668163973,
-            "min": 0.5945047634224608,
-            "max": 1.426793867758676,
+            "value": 0.5212077196030056,
+            "min": 0.45419704154425977,
+            "max": 0.80980078496185,
             "count": 20
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 8.082097306000005e-06,
-            "min": 8.082097306000005e-06,
-            "max": 0.000291882002706,
+            "value": 0.00013250009735000013,
+            "min": 0.00013250009735000013,
+            "max": 0.0048625000027499995,
             "count": 20
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 3.232838922400002e-05,
-            "min": 3.232838922400002e-05,
-            "max": 0.00138516003828,
+            "value": 0.0005300003894000005,
+            "min": 0.0005300003894000005,
+            "max": 0.0230750000385,
             "count": 20
         },
         "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10269400000000001,
-            "min": 0.10269400000000001,
-            "max": 0.19729400000000002,
+            "value": 0.10265,
+            "min": 0.10265,
+            "max": 0.19725000000000004,
             "count": 20
         },
         "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.41077600000000003,
-            "min": 0.41077600000000003,
-            "max": 0.96172,
+            "value": 0.4106,
+            "min": 0.4106,
+            "max": 0.9615,
             "count": 20
         },
         "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0001444306000000001,
-            "min": 0.0001444306000000001,
-            "max": 0.0048649706,
+            "value": 0.00014223500000000013,
+            "min": 0.00014223500000000013,
+            "max": 0.004862775,
             "count": 20
         },
         "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.0005777224000000004,
-            "min": 0.0005777224000000004,
-            "max": 0.023089828,
-            "count": 20
-        },
-        "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 24.25,
-            "min": 3.659090909090909,
-            "max": 25.136363636363637,
-            "count": 20
-        },
-        "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1067.0,
-            "min": 161.0,
-            "max": 1371.0,
-            "count": 20
-        },
-        "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 24.25,
-            "min": 3.659090909090909,
-            "max": 25.136363636363637,
-            "count": 20
-        },
-        "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1067.0,
-            "min": 161.0,
-            "max": 1371.0,
+            "value": 0.0005689400000000005,
+            "min": 0.0005689400000000005,
+            "max": 0.023078849999999998,
             "count": 20
         },
         "SnowballTarget.IsTraining.mean": {
@@ -148,67 +148,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1695394432",
+        "start_time_seconds": "1695401510",
         "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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1695394901"
+        "end_time_seconds": "1695401999"
     },
-    "total": 468.565025098,
+    "total": 489.3164900869997,
     "count": 1,
-    "self": 0.4315352239996173,
+    "self": 0.4249920430011116,
     "children": {
         "run_training.setup": {
-            "total": 0.04176162900012059,
+            "total": 0.0627173489992856,
             "count": 1,
-            "self": 0.04176162900012059
+            "self": 0.0627173489992856
         },
         "TrainerController.start_learning": {
-            "total": 468.09172824500024,
+            "total": 488.8287806949993,
             "count": 1,
-            "self": 0.514204477987505,
+            "self": 0.6065480870856845,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 5.107928096000023,
+                    "total": 5.072198931000457,
                     "count": 1,
-                    "self": 5.107928096000023
+                    "self": 5.072198931000457
                 },
                 "TrainerController.advance": {
-                    "total": 462.3062296520127,
-                    "count": 18204,
-                    "self": 0.259350869028367,
+                    "total": 482.9976769819132,
+                    "count": 18215,
+                    "self": 0.3135042810226878,
                     "children": {
                         "env_step": {
-                            "total": 462.0468787829843,
-                            "count": 18204,
-                            "self": 335.5412605870131,
+                            "total": 482.6841727008905,
+                            "count": 18215,
+                            "self": 329.7428118088865,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 126.23264098198888,
-                                    "count": 18204,
-                                    "self": 1.7489456039616016,
+                                    "total": 152.63644833307808,
+                                    "count": 18215,
+                                    "self": 2.010919573111096,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 124.48369537802728,
-                                            "count": 18204,
-                                            "self": 124.48369537802728
+                                            "total": 150.62552875996698,
+                                            "count": 18215,
+                                            "self": 150.62552875996698
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.2729772139823581,
-                                    "count": 18204,
+                                    "total": 0.3049125589259347,
+                                    "count": 18215,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 466.533233262963,
-                                            "count": 18204,
+                                            "total": 487.00681764308683,
+                                            "count": 18215,
                                             "is_parallel": true,
-                                            "self": 221.27764433995458,
+                                            "self": 217.11979806996897,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.005599847999974372,
+                                                            "total": 0.0031566649995511398,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.003952773999799319,
+                                                            "self": 0.0008025640017876867,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0016470740001750528,
+                                                                    "total": 0.002354100997763453,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0016470740001750528
+                                                                    "self": 0.002354100997763453
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.07310378800002582,
+                                                            "total": 0.0503288039999461,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006380299998909322,
+                                                            "self": 0.00044396799967216793,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004580760000862938,
+                                                                    "total": 0.00036525100040307734,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004580760000862938
+                                                                    "self": 0.00036525100040307734
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.0655762330000016,
+                                                                    "total": 0.04633746699983021,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0655762330000016
+                                                                    "self": 0.04633746699983021
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.006431449000046996,
+                                                                    "total": 0.0031821180000406457,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004294929995012353,
+                                                                    "self": 0.0013967680006317096,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.006001956000545761,
+                                                                            "total": 0.0017853499994089361,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.006001956000545761
+                                                                            "self": 0.0017853499994089361
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 245.25558892300842,
-                                                    "count": 18203,
+                                                    "total": 269.88701957311787,
+                                                    "count": 18214,
                                                     "is_parallel": true,
-                                                    "self": 10.398779897999475,
+                                                    "self": 11.017855447158581,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 5.246553642999743,
-                                                            "count": 18203,
+                                                            "total": 5.760899235985562,
+                                                            "count": 18214,
                                                             "is_parallel": true,
-                                                            "self": 5.246553642999743
+                                                            "self": 5.760899235985562
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 193.51584178901112,
-                                                            "count": 18203,
+                                                            "total": 213.35939599697667,
+                                                            "count": 18214,
                                                             "is_parallel": true,
-                                                            "self": 193.51584178901112
+                                                            "self": 213.35939599697667
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 36.09441359299808,
-                                                            "count": 18203,
+                                                            "total": 39.74886889299705,
+                                                            "count": 18214,
                                                             "is_parallel": true,
-                                                            "self": 6.484813412918129,
+                                                            "self": 7.288212614084841,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 29.60960018007995,
-                                                                    "count": 182030,
+                                                                    "total": 32.46065627891221,
+                                                                    "count": 182140,
                                                                     "is_parallel": true,
-                                                                    "self": 29.60960018007995
+                                                                    "self": 32.46065627891221
                                                                 }
                                                             }
                                                         }
@@ -309,9 +309,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 0.00017802000002120622,
+                    "total": 3.9815999116399325e-05,
                     "count": 1,
-                    "self": 0.00017802000002120622,
+                    "self": 3.9815999116399325e-05,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -320,36 +320,36 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 458.7752014971038,
-                                    "count": 437497,
+                                    "total": 480.6060743708822,
+                                    "count": 287816,
                                     "is_parallel": true,
-                                    "self": 9.64992278710929,
+                                    "self": 7.188309569088233,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 250.02878089399564,
-                                            "count": 437497,
+                                            "total": 171.0720139917994,
+                                            "count": 287816,
                                             "is_parallel": true,
-                                            "self": 249.2222624149956,
+                                            "self": 170.23745129379859,
                                             "children": {
                                                 "RLTrainer._checkpoint": {
-                                                    "total": 0.806518479000033,
+                                                    "total": 0.8345626980008092,
                                                     "count": 4,
                                                     "is_parallel": true,
-                                                    "self": 0.806518479000033
+                                                    "self": 0.8345626980008092
                                                 }
                                             }
                                         },
                                         "_update_policy": {
-                                            "total": 199.09649781599887,
+                                            "total": 302.34575080999457,
                                             "count": 90,
                                             "is_parallel": true,
-                                            "self": 79.48694423101233,
+                                            "self": 97.19458248201772,
                                             "children": {
                                                 "TorchPPOOptimizer.update": {
-                                                    "total": 119.60955358498654,
-                                                    "count": 4584,
+                                                    "total": 205.15116832797685,
+                                                    "count": 4590,
                                                     "is_parallel": true,
-                                                    "self": 119.60955358498654
+                                                    "self": 205.15116832797685
                                                 }
                                             }
                                         }
@@ -360,14 +360,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.16318799900000158,
+                    "total": 0.152316879000864,
                     "count": 1,
-                    "self": 0.0008954439999797614,
+                    "self": 0.0010705269996833522,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.16229255500002182,
+                            "total": 0.15124635200118064,
                             "count": 1,
-                            "self": 0.16229255500002182
+                            "self": 0.15124635200118064
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,58 +2,58 @@
     "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 13.363636363636363,
-                "creation_time": 1695394553.3457396,
+                "steps": 49800,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49800.onnx",
+                "reward": 14.142857142857142,
+                "creation_time": 1695401633.3461013,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49800.pt"
                 ]
             },
             {
-                "steps": 99960,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 20.454545454545453,
-                "creation_time": 1695394670.3220997,
+                "steps": 99800,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99800.onnx",
+                "reward": 21.0,
+                "creation_time": 1695401757.3653636,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99800.pt"
                 ]
             },
             {
-                "steps": 149984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 23.727272727272727,
-                "creation_time": 1695394785.4409354,
+                "steps": 149800,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149800.onnx",
+                "reward": 23.0,
+                "creation_time": 1695401883.1586978,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149800.pt"
                 ]
             },
             {
-                "steps": 199984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 24.272727272727273,
-                "creation_time": 1695394900.5425246,
+                "steps": 199800,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199800.onnx",
+                "reward": 26.0,
+                "creation_time": 1695401998.799362,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199800.pt"
                 ]
             },
             {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 24.272727272727273,
-                "creation_time": 1695394900.7377973,
+                "steps": 200200,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.onnx",
+                "reward": 26.09090909090909,
+                "creation_time": 1695401999.0192761,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200112,
+            "steps": 200200,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 24.272727272727273,
-            "creation_time": 1695394900.7377973,
+            "reward": 26.09090909090909,
+            "creation_time": 1695401999.0192761,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.pt"
             ]
         }
     },