more trained model

README.md

@@ -14,13 +14,19 @@ tags:
   ## Usage (with ML-Agents)
   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 the Agent play
-  Watch Berrie the bear **hitting targets in browser**
+  ### Watch your Agent play
+  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: elliemci/ppo-Snowball-Target

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:937b3ba4dbd003d1f63e19fee42ce918fd8686f3d8fef2b15c94ed619ba595ba
+oid sha256:97833265fcef23894afefe436cc68d42a9b427750dbb03182867350efa91bff1
 size 650646

SnowballTarget/SnowballTarget-1000120.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0581d2f95c33537a09a0987f4b4c399e527e8a507ee4d163c090940c1a8126c
+size 650646

SnowballTarget/SnowballTarget-1000120.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3ac01408d14992d0adb968a1393d6628aa9c297408d15429f8ef347c1285017
+size 3849318

SnowballTarget/SnowballTarget-1499968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:585aaa07f47572a2b9391ce9f5fc979050adaaa38f7601e18b83fdeb68585a8d
+size 650646

SnowballTarget/SnowballTarget-1499968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c2dd277fe91d3012590fa09a4b1d98fd63503381506732ac1952b11fd52d45a
+size 3849318

SnowballTarget/SnowballTarget-1999944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6288b1cafe63d52c67b5083c29e7b1c6825bb51973a784bf3e3972fd13b69109
+size 650646

SnowballTarget/SnowballTarget-1999944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61dd4e2bdff7d4b39c00ceec2db723ad0a8416b5c542b1fd1052d864c23f6bf4
+size 3849318

SnowballTarget/SnowballTarget-2000328.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6288b1cafe63d52c67b5083c29e7b1c6825bb51973a784bf3e3972fd13b69109
+size 650646

SnowballTarget/SnowballTarget-2000328.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c431d5c36f1614952f1461a01612c7a8a357432f04ca3ed068bbb0159cd41b29
+size 3849318

SnowballTarget/SnowballTarget-2499984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c97f8eddb06ee6629d5173fc83401ca4de41ca4fd4fa5d6e676362155ecba9f
+size 650646

SnowballTarget/SnowballTarget-2499984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abd501815618b1b2a2206007586253f7e5dbb6350916367002dcaaaac33ed73c
+size 3849318

SnowballTarget/SnowballTarget-2999960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bba2e877c70dbf19312b8d0770d1a5d966f204a7f5d65d315c73acc41024423
+size 650646

SnowballTarget/SnowballTarget-2999960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18f31ea8a889591f100591c3b8bcc15568ebe2a09dfb9d8ac1d8ae844824eb32
+size 3849318

SnowballTarget/SnowballTarget-3499936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14593738f5a939a890e153ab140cb48c9df66adfecc7ba7eeeb862c6c425b76f
+size 650646

SnowballTarget/SnowballTarget-3499936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8ac3918045f106d4d3aba03ac45c2e1fabfdb4ca294d82890457c00cf8ac2ca
+size 3849318

SnowballTarget/SnowballTarget-3999976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2330c9a4424e009bb4c71e0ad4d39ae1c5e324f5afd201ab89c125fc3ebee990
+size 650646

SnowballTarget/SnowballTarget-3999976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd6e247251d237811af01ccd1a2f72ba1458db5e1d1f841127adef729ce9b8d7
+size 3849318

SnowballTarget/SnowballTarget-4059440.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97833265fcef23894afefe436cc68d42a9b427750dbb03182867350efa91bff1
+size 650646

SnowballTarget/SnowballTarget-4059440.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5baaa80832edec14166b0b96afaf931368a1b7a5a334b5f31428e86402a914b5
+size 3849318

SnowballTarget/SnowballTarget-999992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0581d2f95c33537a09a0987f4b4c399e527e8a507ee4d163c090940c1a8126c
+size 650646

SnowballTarget/SnowballTarget-999992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48bf66536b361d9e63cc1308a697724d9514599e58bfd1c9ab52eff57234f7c1
+size 3849179

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3232f8f0c485c96cafe742213b1a0db75b0992816adc135710741294fd63f548
-size 3848757
+oid sha256:f4246e5f52c1eef1d5e9e1b89f7db02c0dc1154cf6355f20ef6d301a441e51ff
+size 3848290

SnowballTarget/events.out.tfevents.1759619468.222bc6b1bac0.23309.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f4c0b0f645a078188719d0e3cc48ed6321e5c7187a7946c85c92e63582c8d8e
+size 1114

SnowballTarget/events.out.tfevents.1759635131.74437285bc07.11580.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4e80b078b25af891f7bcf4334fb91900a14b016ebe981bcc639418a452679d1
+size 66586

SnowballTarget/events.out.tfevents.1759637937.74437285bc07.23232.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:274bf463d4eae99d659473a7028ce00b325e09515a63b83222ec8dc44de19877
+size 82439

SnowballTarget/events.out.tfevents.1759641721.74437285bc07.38555.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ea922f1d88689c8cc96b0ccbd67974904d98b772bd93acd273c8a9f9719d8ae
+size 177897

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.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "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": "cpu"}, "debug": false}
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.001, "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": 10, "even_checkpoints": false, "max_steps": 5000000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20.0, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": true, "force": false, "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: 0.001
       beta: 0.005
       epsilon: 0.2
       lambd: 0.95
@@ -14,7 +14,7 @@ behaviors:
       learning_rate_schedule: linear
       beta_schedule: linear
       epsilon_schedule: linear
-    checkpoint_interval: 50000
+    checkpoint_interval: 500000
     network_settings:
       normalize: false
       hidden_units: 256
@@ -38,7 +38,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 10
     even_checkpoints: false
-    max_steps: 200000
+    max_steps: 5000000
     time_horizon: 64
     summary_freq: 10000
     threaded: true
@@ -59,7 +59,7 @@ 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
@@ -69,11 +69,11 @@ checkpoint_settings:
   run_id: SnowballTarget1
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: false
   results_dir: results
 torch_settings:
-  device: cpu
+  device: null
 debug: false

run_logs/Player-0.log

@@ -2,9 +2,6 @@ Mono path[0] = '/content/drive/MyDrive/ColabNotebooks/DeepRL/unity_ml_agents/ml-
 Mono config path = '/content/drive/MyDrive/ColabNotebooks/DeepRL/unity_ml_agents/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/drive/MyDrive/ColabNotebooks/DeepRL/unity_ml_agents/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  6.577 seconds
+- Completed reload, in  2.167 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: 1.350994 ms
+UnloadTime: 1.275486 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]: 5371 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 45 frames, [8.0 KB-16.0 KB]: 55196 frames, [16.0 KB-32.0 KB]: 936 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 40
+  Peak main deferred allocation count 39
     [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]: 5463 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 9975 frames, [8.0 MB-16.0 MB]: 29242 frames, [16.0 MB-32.0 MB]: 16961 frames
       Requested Block Size 16.0 MB
-      Peak Block count 1
-      Peak Allocated memory 6.9 MB
+      Peak Block count 2
+      Peak Allocated memory 25.3 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 5463 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 56178 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.2 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]: 5122 frames, [64.0 KB-128.0 KB]: 341 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 54953 frames, [64.0 KB-128.0 KB]: 1225 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]: 5463 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 56178 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]: 5463 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 56178 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]: 5462 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 56177 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]: 5463 frames
+      Peak usage frame count: [0-1.0 KB]: 56178 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]: 5463 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 56178 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": 0.8864038586616516,
-            "min": 0.8864038586616516,
-            "max": 2.871638536453247,
-            "count": 20
+            "value": 0.5378670692443848,
+            "min": 0.25169727206230164,
+            "max": 0.8338563442230225,
+            "count": 205
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 8482.884765625,
-            "min": 8482.884765625,
-            "max": 29440.0390625,
-            "count": 20
+            "value": 5455.0478515625,
+            "min": 2408.742919921875,
+            "max": 8392.9716796875,
+            "count": 205
         },
         "SnowballTarget.Step.mean": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+            "value": 4049936.0,
+            "min": 2009960.0,
+            "max": 4049936.0,
+            "count": 205
         },
         "SnowballTarget.Step.sum": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+            "value": 4049936.0,
+            "min": 2009960.0,
+            "max": 4049936.0,
+            "count": 205
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 13.26480770111084,
-            "min": 0.42416539788246155,
-            "max": 13.26480770111084,
-            "count": 20
+            "value": 14.551513671875,
+            "min": 9.390125274658203,
+            "max": 14.746602058410645,
+            "count": 205
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2586.637451171875,
-            "min": 82.2880859375,
-            "max": 2689.9091796875,
-            "count": 20
+            "value": 2822.99365234375,
+            "min": 1924.9755859375,
+            "max": 3022.7861328125,
+            "count": 205
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
             "value": 199.0,
             "min": 199.0,
             "max": 199.0,
-            "count": 20
+            "count": 205
         },
         "SnowballTarget.Environment.EpisodeLength.sum": {
             "value": 8756.0,
             "min": 8756.0,
             "max": 10945.0,
-            "count": 20
+            "count": 205
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.07335391956211441,
-            "min": 0.06281399575504931,
-            "max": 0.07335391956211441,
-            "count": 20
+            "value": 0.06759569437018204,
+            "min": 0.06010027918062977,
+            "max": 0.08732905397454149,
+            "count": 205
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.29341567824845766,
-            "min": 0.2582186224620576,
-            "max": 0.35503686174257276,
-            "count": 20
+            "value": 0.27038277748072814,
+            "min": 0.24040111672251907,
+            "max": 0.3776409532326986,
+            "count": 205
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.18263008303063755,
-            "min": 0.10906449994688634,
-            "max": 0.2709916849784991,
-            "count": 20
+            "value": 0.1507860389264191,
+            "min": 0.1247357524858386,
+            "max": 0.7414896927627863,
+            "count": 205
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.7305203321225502,
-            "min": 0.43625799978754537,
-            "max": 1.3486190797651516,
-            "count": 20
+            "value": 0.6031441557056764,
+            "min": 0.4989430099433544,
+            "max": 3.7074484638139316,
+            "count": 205
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 8.082097306000005e-06,
-            "min": 8.082097306000005e-06,
-            "max": 0.000291882002706,
-            "count": 20
+            "value": 0.00019097208090280006,
+            "min": 0.00019097208090280006,
+            "max": 0.0005988520401148,
+            "count": 205
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 3.232838922400002e-05,
-            "min": 3.232838922400002e-05,
-            "max": 0.00138516003828,
-            "count": 20
+            "value": 0.0007638883236112002,
+            "min": 0.0007638883236112002,
+            "max": 0.0029755602024440003,
+            "count": 205
         },
         "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10269400000000001,
-            "min": 0.10269400000000001,
-            "max": 0.19729400000000002,
-            "count": 20
+            "value": 0.11909720000000001,
+            "min": 0.11909720000000001,
+            "max": 0.15988520000000003,
+            "count": 205
         },
         "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.41077600000000003,
-            "min": 0.41077600000000003,
-            "max": 0.96172,
-            "count": 20
+            "value": 0.47638880000000006,
+            "min": 0.47638880000000006,
+            "max": 0.7975560000000002,
+            "count": 205
         },
         "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0001444306000000001,
-            "min": 0.0001444306000000001,
-            "max": 0.0048649706,
-            "count": 20
+            "value": 0.0009629502800000004,
+            "min": 0.0009629502800000004,
+            "max": 0.00299827148,
+            "count": 205
         },
         "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.0005777224000000004,
-            "min": 0.0005777224000000004,
-            "max": 0.023089828,
-            "count": 20
+            "value": 0.0038518011200000014,
+            "min": 0.0038518011200000014,
+            "max": 0.014898044400000001,
+            "count": 205
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 26.113636363636363,
-            "min": 3.1818181818181817,
-            "max": 26.113636363636363,
-            "count": 20
+            "value": 28.636363636363637,
+            "min": 10.872727272727273,
+            "max": 29.145454545454545,
+            "count": 205
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1149.0,
-            "min": 140.0,
-            "max": 1432.0,
-            "count": 20
+            "value": 1260.0,
+            "min": 579.0,
+            "max": 1603.0,
+            "count": 205
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 26.113636363636363,
-            "min": 3.1818181818181817,
-            "max": 26.113636363636363,
-            "count": 20
+            "value": 28.636363636363637,
+            "min": 10.872727272727273,
+            "max": 29.145454545454545,
+            "count": 205
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1149.0,
-            "min": 140.0,
-            "max": 1432.0,
-            "count": 20
+            "value": 1260.0,
+            "min": 579.0,
+            "max": 1603.0,
+            "count": 205
         },
         "SnowballTarget.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 205
         },
         "SnowballTarget.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 205
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1759617257",
+        "start_time_seconds": "1759641718",
         "python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [GCC 11.4.0]",
-        "command_line_arguments": "/content/drive/MyDrive/ColabNotebooks/DeepRL/unity_ml_agents/ml-agents/ml-agents/mlagents/trainers/learn.py config/ppo/SnowballTarget.yaml --env=training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --torch-device cpu",
+        "command_line_arguments": "/content/drive/MyDrive/ColabNotebooks/DeepRL/unity_ml_agents/ml-agents/ml-agents/mlagents/trainers/learn.py config/ppo/SnowballTarget.yaml --env=training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --resume --no-graphics --time-scale=20",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
-        "pytorch_version": "2.8.0+cu128",
+        "pytorch_version": "2.2.2+cu118",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1759617977"
+        "end_time_seconds": "1759648498"
     },
-    "total": 720.7424643029999,
+    "total": 6780.427215903001,
     "count": 1,
-    "self": 3.04285879400004,
+    "self": 0.023770914998749504,
     "children": {
         "run_training.setup": {
-            "total": 0.5054450689999612,
+            "total": 0.03404056700128422,
             "count": 1,
-            "self": 0.5054450689999612
+            "self": 0.03404056700128422
         },
         "TrainerController.start_learning": {
-            "total": 717.1941604399999,
+            "total": 6780.369404421001,
             "count": 1,
-            "self": 0.8967849949854099,
+            "self": 9.438188089317919,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 27.97904822999999,
+                    "total": 4.192950361999465,
                     "count": 1,
-                    "self": 27.97904822999999
+                    "self": 4.192950361999465
                 },
                 "TrainerController.advance": {
-                    "total": 688.1857627680142,
-                    "count": 18207,
-                    "self": 0.45647151800312713,
+                    "total": 6766.522339763684,
+                    "count": 187259,
+                    "self": 4.6685647021568,
                     "children": {
                         "env_step": {
-                            "total": 687.7292912500111,
-                            "count": 18207,
-                            "self": 551.11223637699,
+                            "total": 6761.853775061527,
+                            "count": 187259,
+                            "self": 5480.371305527964,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 136.16034631501043,
-                                    "count": 18207,
-                                    "self": 2.495420341008412,
+                                    "total": 1276.6703044718233,
+                                    "count": 187259,
+                                    "self": 25.201322214867105,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 133.66492597400202,
-                                            "count": 18207,
-                                            "self": 133.66492597400202
+                                            "total": 1251.4689822569562,
+                                            "count": 187259,
+                                            "self": 1251.4689822569562
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.45670855801063226,
-                                    "count": 18207,
+                                    "total": 4.812165061739506,
+                                    "count": 187259,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 713.8301045720245,
-                                            "count": 18207,
+                                            "total": 6743.494264420429,
+                                            "count": 187259,
                                             "is_parallel": true,
-                                            "self": 323.0260147560148,
+                                            "self": 2837.1724640803022,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.00796136100007061,
+                                                            "total": 0.002290477999849827,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.005653170000641694,
+                                                            "self": 0.0007419679986924166,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0023081909994289163,
+                                                                    "total": 0.0015485100011574104,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0023081909994289163
+                                                                    "self": 0.0015485100011574104
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04777077600010671,
+                                                            "total": 0.04480024599979515,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007130789999791887,
+                                                            "self": 0.0006656960013060598,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004538260000117589,
+                                                                    "total": 0.0004623589993570931,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004538260000117589
+                                                                    "self": 0.0004623589993570931
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04415833500024746,
+                                                                    "total": 0.0414822330003517,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04415833500024746
+                                                                    "self": 0.0414822330003517
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.002445535999868298,
+                                                                    "total": 0.002189957998780301,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.000475898999866331,
+                                                                    "self": 0.00042489800034672953,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001969637000001967,
+                                                                            "total": 0.0017650599984335713,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001969637000001967
+                                                                            "self": 0.0017650599984335713
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 390.80408981600976,
-                                                    "count": 18206,
+                                                    "total": 3906.321800340127,
+                                                    "count": 187258,
                                                     "is_parallel": true,
-                                                    "self": 16.378712090016506,
+                                                    "self": 164.54901427960613,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 8.630475927984207,
-                                                            "count": 18206,
+                                                            "total": 83.51316091107583,
+                                                            "count": 187258,
                                                             "is_parallel": true,
-                                                            "self": 8.630475927984207
+                                                            "self": 83.51316091107583
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 304.2668674440056,
-                                                            "count": 18206,
+                                                            "total": 3053.320768955846,
+                                                            "count": 187258,
                                                             "is_parallel": true,
-                                                            "self": 304.2668674440056
+                                                            "self": 3053.320768955846
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 61.528034354003466,
-                                                            "count": 18206,
+                                                            "total": 604.9388561935993,
+                                                            "count": 187258,
                                                             "is_parallel": true,
-                                                            "self": 11.493632857002012,
+                                                            "self": 116.33661882368142,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 50.034401497001454,
-                                                                    "count": 182060,
+                                                                    "total": 488.60223736991793,
+                                                                    "count": 1872580,
                                                                     "is_parallel": true,
-                                                                    "self": 50.034401497001454
+                                                                    "self": 488.60223736991793
                                                                 }
                                                             }
                                                         }
@@ -309,9 +309,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 0.00013421300036497996,
+                    "total": 6.0630000007222407e-05,
                     "count": 1,
-                    "self": 0.00013421300036497996,
+                    "self": 6.0630000007222407e-05,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -320,36 +320,36 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 682.5432780908368,
-                                    "count": 582195,
+                                    "total": 6710.570346064002,
+                                    "count": 5475989,
                                     "is_parallel": true,
-                                    "self": 15.422843784749148,
+                                    "self": 143.0828769158761,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 370.06148500908785,
-                                            "count": 582195,
+                                            "total": 3645.7056422951628,
+                                            "count": 5475990,
                                             "is_parallel": true,
-                                            "self": 368.71366196308827,
+                                            "self": 3644.880095744167,
                                             "children": {
                                                 "RLTrainer._checkpoint": {
-                                                    "total": 1.3478230459995757,
+                                                    "total": 0.8255465509955684,
                                                     "count": 4,
                                                     "is_parallel": true,
-                                                    "self": 1.3478230459995757
+                                                    "self": 0.8255465509955684
                                                 }
                                             }
                                         },
                                         "_update_policy": {
-                                            "total": 297.0589492969998,
-                                            "count": 90,
+                                            "total": 2921.7818268529627,
+                                            "count": 935,
                                             "is_parallel": true,
-                                            "self": 63.11306371699675,
+                                            "self": 622.6791587437492,
                                             "children": {
                                                 "TorchPPOOptimizer.update": {
-                                                    "total": 233.94588558000305,
-                                                    "count": 4587,
+                                                    "total": 2299.1026681092135,
+                                                    "count": 47717,
                                                     "is_parallel": true,
-                                                    "self": 233.94588558000305
+                                                    "self": 2299.1026681092135
                                                 }
                                             }
                                         }
@@ -360,14 +360,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.13243023399991216,
+                    "total": 0.2158655759994872,
                     "count": 1,
-                    "self": 0.013348662999760563,
+                    "self": 0.020677766000517295,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.1190815710001516,
+                            "total": 0.1951878099989699,
                             "count": 1,
-                            "self": 0.1190815710001516
+                            "self": 0.1951878099989699
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,64 +2,109 @@
     "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 14.090909090909092,
-                "creation_time": 1759617455.0387928,
+                "steps": 999992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-999992.onnx",
+                "reward": 26.545454545454547,
+                "creation_time": 1759637744.9498353,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-999992.pt"
                 ]
             },
             {
-                "steps": 99960,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 22.90909090909091,
-                "creation_time": 1759617633.4812636,
+                "steps": 1000120,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000120.onnx",
+                "reward": 26.545454545454547,
+                "creation_time": 1759637745.1293166,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000120.pt"
                 ]
             },
             {
-                "steps": 149984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 25.363636363636363,
-                "creation_time": 1759617804.8444421,
+                "steps": 1499968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1499968.onnx",
+                "reward": 27.636363636363637,
+                "creation_time": 1759639566.6795788,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1499968.pt"
                 ]
             },
             {
-                "steps": 199984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 25.09090909090909,
-                "creation_time": 1759617974.6280048,
+                "steps": 1999944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1999944.onnx",
+                "reward": 28.09090909090909,
+                "creation_time": 1759641191.290944,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1999944.pt"
                 ]
             },
             {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 25.09090909090909,
-                "creation_time": 1759617974.7832618,
+                "steps": 2000328,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-2000328.onnx",
+                "reward": 28.09090909090909,
+                "creation_time": 1759641191.5194392,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-2000328.pt"
+                ]
+            },
+            {
+                "steps": 2499984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-2499984.onnx",
+                "reward": 25.727272727272727,
+                "creation_time": 1759643354.0291789,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-2499984.pt"
+                ]
+            },
+            {
+                "steps": 2999960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-2999960.onnx",
+                "reward": 27.272727272727273,
+                "creation_time": 1759644998.6946094,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-2999960.pt"
+                ]
+            },
+            {
+                "steps": 3499936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-3499936.onnx",
+                "reward": 28.0,
+                "creation_time": 1759646655.927263,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-3499936.pt"
+                ]
+            },
+            {
+                "steps": 3999976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-3999976.onnx",
+                "reward": 28.818181818181817,
+                "creation_time": 1759648300.1980343,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-3999976.pt"
+                ]
+            },
+            {
+                "steps": 4059440,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-4059440.onnx",
+                "reward": null,
+                "creation_time": 1759648498.824494,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-4059440.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200112,
+            "steps": 4059440,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 25.09090909090909,
-            "creation_time": 1759617974.7832618,
+            "reward": null,
+            "creation_time": 1759648498.824494,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-4059440.pt"
             ]
         }
     },
     "metadata": {
         "stats_format_version": "0.3.0",
         "mlagents_version": "1.2.0.dev0",
-        "torch_version": "2.8.0+cu128"
+        "torch_version": "2.2.2+cu118"
     }
 }