First Push

README.md

@@ -8,21 +8,27 @@ tags:
 ---
 
   # **ppo** Agent playing **SnowballTarget**
-  This is a trained model of a **ppo** agent playing **SnowballTarget** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
-  
+  This is a trained model of a **ppo** agent playing **SnowballTarget**
+  using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
+
   ## Usage (with ML-Agents)
-  The Documentation: https://github.com/huggingface/ml-agents#get-started
-  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+  The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
 
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+  - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
+  browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
+  - A *longer tutorial* to understand how works ML-Agents:
+  https://huggingface.co/learn/deep-rl-course/unit5/introduction
 
   ### Resume the training
-  ```
+  ```bash
   mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
   ```
+
   ### Watch your Agent play
-  You can watch your agent **playing directly in your browser:**.
-  
-  1. Go to https://huggingface.co/spaces/unity/ML-Agents-SnowballTarget
+  You can watch your agent **playing directly in your browser**
+
+  1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
   2. Step 1: Find your model_id: Jeibros/ppo-SnowballTarget
   3. Step 2: Select your *.nn /*.onnx file
   4. Click on Watch the agent play 👀

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60e9080434454bdf7219a4287765b987f32f8c289f210082fa0cf6032ee5e677
+oid sha256:633f985e4f98e1d52c9489d09daf84bd770912de0aee7aba76dbde510f7d6e23
 size 646532

SnowballTarget/SnowballTarget-159936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed85638f7708034e423b0abf1f3b81a2db321668093f34c8f1574b543c2ff00
+size 646532

SnowballTarget/SnowballTarget-159936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18a929e10e2fad1d862de661b55855642fb220c2918b3f05449ac7356c85831e
+size 3843968

SnowballTarget/SnowballTarget-164992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6304e9a854f8528c3596962a322ff78eeb09f4a3cb14e9ad534e1898356b62d0
+size 646532

SnowballTarget/SnowballTarget-164992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acb69b88dc7bd28d8ecb635ec403c245e468e9842be3eb49b884e1f7e7cca6fe
+size 3843968

SnowballTarget/SnowballTarget-169976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7f64d7ec112340eeee5f350345f6b30853db2d7bb5117d05b72e1d309fe19d0
+size 646532

SnowballTarget/SnowballTarget-169976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34e31bb00b75d55216ec78d23b8ecb1b6c070fdb0e83c079bba62ded9597d778
+size 3843968

SnowballTarget/SnowballTarget-174952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc21dde0d963d2a98395b4b027b29c7b28c0eb4fdebc5a911f753d4ebe0f50f4
+size 646532

SnowballTarget/SnowballTarget-174952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:604c9a0ac1b0e79d131ee2d19b8b75d2005322fe2c2d477e16292e3f317a5b6f
+size 3843968

SnowballTarget/SnowballTarget-179992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a43ad048744271848239b5b3ee11f71addeb2f62d3dab777a0f1e07abbb8164d
+size 646532

SnowballTarget/SnowballTarget-179992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb6838e47bb06785e762675e91a9c6f66e6b9768a6bc4e83ffc18d5333c0c899
+size 3843968

SnowballTarget/SnowballTarget-184992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4ca4be6c6304b6609f1387a40bf61f16370af2fdb247e06a4cb6a7a6c4e94f7
+size 646532

SnowballTarget/SnowballTarget-184992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66dbb30638e0a55769e5311da7b61f2335c3ef03243499b677770b029ea105d6
+size 3843968

SnowballTarget/SnowballTarget-189968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03717e967de98a32a8db0ff5498a663e071b45cc0f15a24ff52512f7f168d97b
+size 646532

SnowballTarget/SnowballTarget-189968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74081c21203e9934e5184e97e11282506f57d25310cda2376095f3d18b4286d5
+size 3843968

SnowballTarget/SnowballTarget-194944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb69e46003375a8862cbca5f4470984263b20046720aebcbf4931d357aa91288
+size 646532

SnowballTarget/SnowballTarget-194944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9527991f5601037aa584dfab762eb226309821e75773c16b4e7b6ac048927e9
+size 3843968

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:633f985e4f98e1d52c9489d09daf84bd770912de0aee7aba76dbde510f7d6e23
+size 646532

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b7fe56cc55a1a03b3a4f7ca9babc8da823432ea667706df762c5b660fbeb2d9
+size 3843968

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:633f985e4f98e1d52c9489d09daf84bd770912de0aee7aba76dbde510f7d6e23
+size 646532

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d9db1d5668e126c4785ec5d985db9a85319e4dac70b925a3dbd39d9cf1ba83f
+size 3843968

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f1770efc60a45c2aa7d0f8fe557179032ed4a0302ced73c2594ff8414108e5c
+oid sha256:8d9db1d5668e126c4785ec5d985db9a85319e4dac70b925a3dbd39d9cf1ba83f
 size 3843968

SnowballTarget/events.out.tfevents.1686583121.7c4b9d5ff59a.1945.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2356caafceac69c4e24fe65704e740bc09376ea83da92aee1f638f2f72985e7
+size 28090

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": 500000, "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": 5, "even_checkpoints": false, "max_steps": 500000, "time_horizon": 64, "summary_freq": 50000, "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": 0.0003, "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": 5000, "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": 20.0, "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}

configuration.yaml

@@ -14,7 +14,7 @@ behaviors:
       learning_rate_schedule: linear
       beta_schedule: linear
       epsilon_schedule: linear
-    checkpoint_interval: 500000
+    checkpoint_interval: 5000
     network_settings:
       normalize: false
       hidden_units: 256
@@ -36,11 +36,11 @@ behaviors:
           goal_conditioning_type: hyper
           deterministic: false
     init_path: null
-    keep_checkpoints: 5
+    keep_checkpoints: 10
     even_checkpoints: false
-    max_steps: 500000
+    max_steps: 200000
     time_horizon: 64
-    summary_freq: 50000
+    summary_freq: 10000
     threaded: true
     self_play: null
     behavioral_cloning: null
@@ -58,7 +58,7 @@ engine_settings:
   width: 84
   height: 84
   quality_level: 5
-  time_scale: 20
+  time_scale: 20.0
   target_frame_rate: -1
   capture_frame_rate: 60
   no_graphics: true

run_logs/Player-0.log

@@ -34,7 +34,7 @@ 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  0.087 seconds
+- Completed reload, in  0.136 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 +45,7 @@ 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: 0.648341 ms
+UnloadTime: 1.011150 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 +53,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 13417 frames, [16.0 KB-32.0 KB]: 227 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 5377 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
@@ -169,19 +169,19 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 40
+  Peak main deferred allocation count 44
     [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]: 12338 frames, [8.0 MB-16.0 MB]: 1307 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 5469 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 9.6 MB
+      Peak Allocated memory 6.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 13645 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5469 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 17.9 MB
@@ -213,13 +213,13 @@ 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]: 12688 frames, [64.0 KB-128.0 KB]: 957 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5056 frames, [64.0 KB-128.0 KB]: 413 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 66.8 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 13645 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5469 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -231,13 +231,13 @@ 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]: 13645 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5469 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]: 13644 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5468 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 +249,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 13645 frames
+      Peak usage frame count: [0-1.0 KB]: 5469 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]: 13645 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 5469 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -2,213 +2,213 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 0.6540644764900208,
-            "min": 0.642225980758667,
-            "max": 2.5468595027923584,
-            "count": 10
+            "value": 0.8867369890213013,
+            "min": 0.8867369890213013,
+            "max": 2.8655693531036377,
+            "count": 20
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 32714.34375,
-            "min": 32037.443359375,
-            "max": 128646.96875,
-            "count": 10
+            "value": 8505.5810546875,
+            "min": 8505.5810546875,
+            "max": 29409.337890625,
+            "count": 20
         },
         "SnowballTarget.Step.mean": {
-            "value": 499976.0,
-            "min": 49936.0,
-            "max": 499976.0,
-            "count": 10
+            "value": 199984.0,
+            "min": 9952.0,
+            "max": 199984.0,
+            "count": 20
         },
         "SnowballTarget.Step.sum": {
-            "value": 499976.0,
-            "min": 49936.0,
-            "max": 499976.0,
-            "count": 10
+            "value": 199984.0,
+            "min": 9952.0,
+            "max": 199984.0,
+            "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 13.653072357177734,
-            "min": 2.432321548461914,
-            "max": 13.653072357177734,
-            "count": 10
+            "value": 13.046875,
+            "min": 0.492266982793808,
+            "max": 13.046875,
+            "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 13694.03125,
-            "min": 2412.863037109375,
-            "max": 13694.03125,
-            "count": 10
+            "value": 2544.140625,
+            "min": 95.49979400634766,
+            "max": 2648.087890625,
+            "count": 20
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
             "value": 199.0,
             "min": 199.0,
             "max": 199.0,
-            "count": 10
+            "count": 20
         },
         "SnowballTarget.Environment.EpisodeLength.sum": {
-            "value": 50347.0,
-            "min": 48158.0,
-            "max": 50347.0,
-            "count": 10
+            "value": 10945.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.067286214474424,
-            "min": 0.06581340910017461,
-            "max": 0.06951543596175226,
-            "count": 10
+            "value": 0.05997834385397807,
+            "min": 0.05997834385397807,
+            "max": 0.07576822043851923,
+            "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 1.547582932911752,
-            "min": 1.4952910310859768,
-            "max": 1.5685453961695224,
-            "count": 10
+            "value": 0.2399133754159123,
+            "min": 0.2399133754159123,
+            "max": 0.37884110219259615,
+            "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.1824719393713192,
-            "min": 0.17135330770428325,
-            "max": 0.2703039176882787,
-            "count": 10
+            "value": 0.20376944804892821,
+            "min": 0.12399268490901472,
+            "max": 0.2859430268114688,
+            "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 4.1968546055403415,
-            "min": 3.816594999210507,
-            "max": 6.21699010683041,
-            "count": 10
+            "value": 0.8150777921957129,
+            "min": 0.49597073963605887,
+            "max": 1.4297151340573442,
+            "count": 20
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 1.4932895022400003e-05,
-            "min": 1.4932895022400003e-05,
-            "max": 0.00028487280504239996,
-            "count": 10
+            "value": 8.082097306000005e-06,
+            "min": 8.082097306000005e-06,
+            "max": 0.000291882002706,
+            "count": 20
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 0.0003434565855152001,
-            "min": 0.0003434565855152001,
-            "max": 0.006267201710932799,
-            "count": 10
+            "value": 3.232838922400002e-05,
+            "min": 3.232838922400002e-05,
+            "max": 0.00138516003828,
+            "count": 20
         },
         "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10497759999999999,
-            "min": 0.10497759999999999,
-            "max": 0.19495760000000004,
-            "count": 10
+            "value": 0.10269400000000001,
+            "min": 0.10269400000000001,
+            "max": 0.19729400000000002,
+            "count": 20
         },
         "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 2.4144848,
-            "min": 2.4144848,
-            "max": 4.289067200000001,
-            "count": 10
+            "value": 0.41077600000000003,
+            "min": 0.41077600000000003,
+            "max": 0.96172,
+            "count": 20
         },
         "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0002583822400000001,
-            "min": 0.0002583822400000001,
-            "max": 0.0047483842399999995,
-            "count": 10
+            "value": 0.0001444306000000001,
+            "min": 0.0001444306000000001,
+            "max": 0.0048649706,
+            "count": 20
         },
         "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.0059427915200000025,
-            "min": 0.0059427915200000025,
-            "max": 0.10446445328,
-            "count": 10
+            "value": 0.0005777224000000004,
+            "min": 0.0005777224000000004,
+            "max": 0.023089828,
+            "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 26.76284584980237,
-            "min": 8.297520661157025,
-            "max": 26.857707509881422,
-            "count": 10
+            "value": 25.772727272727273,
+            "min": 4.204545454545454,
+            "max": 25.90909090909091,
+            "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 6771.0,
-            "min": 2008.0,
-            "max": 6795.0,
-            "count": 10
+            "value": 1134.0,
+            "min": 185.0,
+            "max": 1411.0,
+            "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 26.76284584980237,
-            "min": 8.297520661157025,
-            "max": 26.857707509881422,
-            "count": 10
+            "value": 25.772727272727273,
+            "min": 4.204545454545454,
+            "max": 25.90909090909091,
+            "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 6771.0,
-            "min": 2008.0,
-            "max": 6795.0,
-            "count": 10
+            "value": 1134.0,
+            "min": 185.0,
+            "max": 1411.0,
+            "count": 20
         },
         "SnowballTarget.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 10
+            "count": 20
         },
         "SnowballTarget.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 10
+            "count": 20
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1686033575",
-        "python_version": "3.10.11 (main, Apr  5 2023, 14:15:10) [GCC 9.4.0]",
+        "start_time_seconds": "1686583119",
+        "python_version": "3.10.12 (main, Jun  7 2023, 12:45:35) [GCC 9.4.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
         "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": "1686034731"
+        "end_time_seconds": "1686583698"
     },
-    "total": 1156.3851819529998,
+    "total": 578.381406132,
     "count": 1,
-    "self": 0.43912741799977084,
+    "self": 0.9531930520000742,
     "children": {
         "run_training.setup": {
-            "total": 0.03984599699992941,
+            "total": 0.07172308900004509,
             "count": 1,
-            "self": 0.03984599699992941
+            "self": 0.07172308900004509
         },
         "TrainerController.start_learning": {
-            "total": 1155.906208538,
+            "total": 577.356489991,
             "count": 1,
-            "self": 1.3832883969903378,
+            "self": 0.7381638260003456,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.6961842189998606,
+                    "total": 5.815364906000013,
                     "count": 1,
-                    "self": 3.6961842189998606
+                    "self": 5.815364906000013
                 },
                 "TrainerController.advance": {
-                    "total": 1150.65582140601,
-                    "count": 45482,
-                    "self": 0.6831515139665498,
+                    "total": 570.5417217109995,
+                    "count": 18230,
+                    "self": 0.38011827400202947,
                     "children": {
                         "env_step": {
-                            "total": 1149.9726698920435,
-                            "count": 45482,
-                            "self": 840.1267747421127,
+                            "total": 570.1616034369974,
+                            "count": 18230,
+                            "self": 415.2228667380073,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 309.0889052379598,
-                                    "count": 45482,
-                                    "self": 4.648943237982394,
+                                    "total": 154.57025875799974,
+                                    "count": 18230,
+                                    "self": 2.329320297002539,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 304.4399619999774,
-                                            "count": 45482,
-                                            "self": 304.4399619999774
+                                            "total": 152.2409384609972,
+                                            "count": 18230,
+                                            "self": 152.2409384609972
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.7569899119710044,
-                                    "count": 45482,
+                                    "total": 0.368477940990374,
+                                    "count": 18230,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1151.7000857540193,
-                                            "count": 45482,
+                                            "total": 574.9013252950081,
+                                            "count": 18230,
                                             "is_parallel": true,
-                                            "self": 532.7902005319793,
+                                            "self": 264.8934394190214,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.005341451999811397,
+                                                            "total": 0.006853279999972983,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0037065660001189826,
+                                                            "self": 0.004323302999978296,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0016348859996924148,
+                                                                    "total": 0.0025299769999946875,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0016348859996924148
+                                                                    "self": 0.0025299769999946875
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04124022700011665,
+                                                            "total": 0.03998278200003824,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005451929998798732,
+                                                            "self": 0.0006589900000335547,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00032195700009651773,
+                                                                    "total": 0.00029402000001255146,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00032195700009651773
+                                                                    "self": 0.00029402000001255146
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.03847198199991908,
+                                                                    "total": 0.0366775109999935,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.03847198199991908
+                                                                    "self": 0.0366775109999935
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0019010950002211757,
+                                                                    "total": 0.0023522609999986344,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00035728100033338706,
+                                                                    "self": 0.0004488470000296729,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0015438139998877887,
+                                                                            "total": 0.0019034139999689614,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0015438139998877887
+                                                                            "self": 0.0019034139999689614
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 618.90988522204,
-                                                    "count": 45481,
+                                                    "total": 310.0078858759867,
+                                                    "count": 18229,
                                                     "is_parallel": true,
-                                                    "self": 25.307762699031628,
+                                                    "self": 12.6898613589849,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 13.521906853021392,
-                                                            "count": 45481,
+                                                            "total": 6.402676535993692,
+                                                            "count": 18229,
                                                             "is_parallel": true,
-                                                            "self": 13.521906853021392
+                                                            "self": 6.402676535993692
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 495.52656037400993,
-                                                            "count": 45481,
+                                                            "total": 248.24702683600935,
+                                                            "count": 18229,
                                                             "is_parallel": true,
-                                                            "self": 495.52656037400993
+                                                            "self": 248.24702683600935
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 84.55365529597702,
-                                                            "count": 45481,
+                                                            "total": 42.66832114499874,
+                                                            "count": 18229,
                                                             "is_parallel": true,
-                                                            "self": 16.18123561201992,
+                                                            "self": 8.275188611003898,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 68.3724196839571,
-                                                                    "count": 454810,
+                                                                    "total": 34.393132533994844,
+                                                                    "count": 182290,
                                                                     "is_parallel": true,
-                                                                    "self": 68.3724196839571
+                                                                    "self": 34.393132533994844
                                                                 }
                                                             }
                                                         }
@@ -309,9 +309,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 4.670199996326119e-05,
+                    "total": 0.0001654920000646598,
                     "count": 1,
-                    "self": 4.670199996326119e-05,
+                    "self": 0.0001654920000646598,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -320,36 +320,36 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 1141.9305564049903,
-                                    "count": 1139402,
+                                    "total": 565.8226938610748,
+                                    "count": 546312,
                                     "is_parallel": true,
-                                    "self": 24.710460600061424,
+                                    "self": 12.58049569512616,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 623.5043044219235,
-                                            "count": 1139402,
+                                            "total": 320.60923400694793,
+                                            "count": 546312,
                                             "is_parallel": true,
-                                            "self": 623.2970631079236,
+                                            "self": 305.64768057594847,
                                             "children": {
                                                 "RLTrainer._checkpoint": {
-                                                    "total": 0.20724131399992984,
-                                                    "count": 1,
+                                                    "total": 14.961553430999459,
+                                                    "count": 40,
                                                     "is_parallel": true,
-                                                    "self": 0.20724131399992984
+                                                    "self": 14.961553430999459
                                                 }
                                             }
                                         },
                                         "_update_policy": {
-                                            "total": 493.71579138300535,
-                                            "count": 227,
+                                            "total": 232.63296415900066,
+                                            "count": 90,
                                             "is_parallel": true,
-                                            "self": 184.7323687779906,
+                                            "self": 86.53489770399852,
                                             "children": {
                                                 "TorchPPOOptimizer.update": {
-                                                    "total": 308.98342260501477,
-                                                    "count": 11574,
+                                                    "total": 146.09806645500214,
+                                                    "count": 4587,
                                                     "is_parallel": true,
-                                                    "self": 308.98342260501477
+                                                    "self": 146.09806645500214
                                                 }
                                             }
                                         }
@@ -360,14 +360,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.1708678139998483,
+                    "total": 0.2610740560000977,
                     "count": 1,
-                    "self": 0.0009915569999066065,
+                    "self": 0.003333339000050728,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.1698762569999417,
+                            "total": 0.25774071700004697,
                             "count": 1,
-                            "self": 0.1698762569999417
+                            "self": 0.25774071700004697
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,31 +2,103 @@
     "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 499976,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.onnx",
-                "reward": 27.818181818181817,
-                "creation_time": 1686034731.2697759,
+                "steps": 159936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-159936.onnx",
+                "reward": 25.636363636363637,
+                "creation_time": 1686583580.4983654,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-159936.pt"
                 ]
             },
             {
-                "steps": 500104,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.onnx",
-                "reward": 27.818181818181817,
-                "creation_time": 1686034731.4646697,
+                "steps": 164992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-164992.onnx",
+                "reward": 24.4,
+                "creation_time": 1686583596.0095642,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-164992.pt"
+                ]
+            },
+            {
+                "steps": 169976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-169976.onnx",
+                "reward": 25.545454545454547,
+                "creation_time": 1686583609.0519998,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-169976.pt"
+                ]
+            },
+            {
+                "steps": 174952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-174952.onnx",
+                "reward": 25.09090909090909,
+                "creation_time": 1686583623.4727666,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-174952.pt"
+                ]
+            },
+            {
+                "steps": 179992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-179992.onnx",
+                "reward": 26.272727272727273,
+                "creation_time": 1686583638.0229383,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-179992.pt"
+                ]
+            },
+            {
+                "steps": 184992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-184992.onnx",
+                "reward": 25.454545454545453,
+                "creation_time": 1686583653.674834,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-184992.pt"
+                ]
+            },
+            {
+                "steps": 189968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-189968.onnx",
+                "reward": 25.636363636363637,
+                "creation_time": 1686583668.41145,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-189968.pt"
+                ]
+            },
+            {
+                "steps": 194944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-194944.onnx",
+                "reward": 25.272727272727273,
+                "creation_time": 1686583682.1123881,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-194944.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 26.363636363636363,
+                "creation_time": 1686583696.930381,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 200112,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 26.363636363636363,
+                "creation_time": 1686583697.2291028,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 500104,
+            "steps": 200112,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 27.818181818181817,
-            "creation_time": 1686034731.4646697,
+            "reward": 26.363636363636363,
+            "creation_time": 1686583697.2291028,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.pt"
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
             ]
         }
     },