Hugging Face's logo

Youtaaa
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
 Metrics Community
Youtaaa commited on
Commit
16d4fe1
·
verified ·
1 Parent(s): 80a265c

First Push - SnowballTarget

Browse files
Files changed (18) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-149984.onnx +1 -1
  3. SnowballTarget/SnowballTarget-149984.pt +1 -1
  4. SnowballTarget/SnowballTarget-199984.onnx +1 -1
  5. SnowballTarget/SnowballTarget-199984.pt +1 -1
  6. SnowballTarget/SnowballTarget-200112.onnx +1 -1
  7. SnowballTarget/SnowballTarget-200112.pt +1 -1
  8. SnowballTarget/SnowballTarget-49936.onnx +1 -1
  9. SnowballTarget/SnowballTarget-49936.pt +1 -1
  10. SnowballTarget/SnowballTarget-99960.onnx +1 -1
  11. SnowballTarget/SnowballTarget-99960.pt +1 -1
  12. SnowballTarget/checkpoint.pt +1 -1
  13. SnowballTarget/events.out.tfevents.1774516993.93bd6bb4963f.30321.0 +3 -0
  14. config.json +1 -1
  15. configuration.yaml +1 -1
  16. run_logs/Player-0.log +5 -8
  17. run_logs/timers.json +98 -98
  18. run_logs/training_status.json +12 -12
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1467ca6eee8b0d9354920191311004adb988ef6db1a3dfe2c2ed2d6a240febed
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2fd884ecaca8915499b599df1944a5b90aca7e186ed50f1e637f415c6e38858
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be03bef452c38a3e5eaee84aad5f852ff7adb7b7db9aafa7b75256f5e0a48388
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e6893c50a307867496522fd9b4bc5c67c532fe543bb2d7d391b4c00381fd69c
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80c9847ec4511cd37edf69a4460c07f2d8656e4dfd048fd65c1bf6d84745e2e6
3
  size 3849902
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28fce7142d85b0c7ae947377e7aba478784bb1cc3657beb61b195f95d4d204a3
3
  size 3849902
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1467ca6eee8b0d9354920191311004adb988ef6db1a3dfe2c2ed2d6a240febed
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2fd884ecaca8915499b599df1944a5b90aca7e186ed50f1e637f415c6e38858
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a5918ddb8fb5bfaeab21866901b3f852449137f40bb90e550dba3853e44e909
3
  size 3849902
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2153e124d18445fa65cf289e4f1a9d4ded36cd6f7c81c8cae4f3ec1ce121a6f8
3
  size 3849902
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1467ca6eee8b0d9354920191311004adb988ef6db1a3dfe2c2ed2d6a240febed
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2fd884ecaca8915499b599df1944a5b90aca7e186ed50f1e637f415c6e38858
3
  size 650646
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a54b0e52e6f3b3645c7f5c2008c7b8c86d4a4ad6abc324f2df9b828c1f8eb0bc
3
  size 3849902
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5baf7c52b872f4dc67b99cc206708aaa950a75f61e39206793a1d6666d89301
3
  size 3849902
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aab5974c73721d7ae52587d4e234b8d1cabeb65108b8dac7fb5ca7adbfb41dd9
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b47c484520b8e795562640eca538dc3b9394bba489d4f85548fb131415774c17
3
  size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8654e0fac2e6cfaea9adf40aceac3b2c4344b1d8461ca81ddb6db5177dc00d23
3
  size 3849827
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c9ff1d9da793bf1a7c70501a65c0035c7c5343fb0b094bee4f58c74d69782e9
3
  size 3849827
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccf0818a9d839fc28f8669ea68810683762931de2a2ac64d89477c68537e26a5
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb5937c6daef58db5478e495756d81ae0981df713654c0ca215959ee64feb827
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0d10a67f208de9948f90ec1ba391fc3dae7d1c3c40e736ca02b10d35f07e14e
3
  size 3849827
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45587702177cb98087549a12764f8f90985c200249d579f85b8042ac560a3374
3
  size 3849827
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:04e449f09d2cbdaae7d585ebd1146a21277abed8cca173dc3b4268038f6b9aed
3
  size 3849077
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46c903ff3594d4f542eb191ddfcdd982b3baba80a048ccbff71c6aa700e3ea11
3
  size 3849077
SnowballTarget/events.out.tfevents.1774516993.93bd6bb4963f.30321.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32dfd62fca00e0d3c4fb9a12427587ed74400aa791fbdcf4d07e06c243b56a23
3
+ size 23589
config.json CHANGED
@@ -1 +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": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "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": null}, "debug": false}
 
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": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -70,7 +70,7 @@ checkpoint_settings:
70
  initialize_from: null
71
  load_model: false
72
  resume: false
73
- force: false
74
  train_model: false
75
  inference: false
76
  results_dir: results
 
70
  initialize_from: null
71
  load_model: false
72
  resume: false
73
+ force: true
74
  train_model: false
75
  inference: false
76
  results_dir: results
run_logs/Player-0.log CHANGED
@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
5
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
6
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
7
- Unable to load player prefs
8
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
9
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
- - Completed reload, in 0.217 seconds
38
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  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
45
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
46
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
47
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
48
- UnloadTime: 0.881739 ms
49
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
50
  requesting resize 84 x 84
51
  Setting up 1 worker threads for Enlighten.
@@ -178,13 +175,13 @@ Memory Statistics:
178
  Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.8 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
  Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.6 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
@@ -213,7 +210,7 @@ Memory Statistics:
213
  Used Block count 1
214
  Peak Allocated bytes 1.0 MB
215
  [ALLOC_GFX_MAIN]
216
- Peak usage frame count: [32.0 KB-64.0 KB]: 5100 frames, [64.0 KB-128.0 KB]: 358 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
  Peak Allocated memory 66.4 KB
 
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
 
 
 
5
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
6
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
7
  Forcing GfxDevice: Null
 
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.090 seconds
35
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
42
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
43
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
44
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
45
+ UnloadTime: 0.696018 ms
46
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
47
  requesting resize 84 x 84
48
  Setting up 1 worker threads for Enlighten.
 
175
  Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 7.1 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
  Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.3 MB
185
  Peak Large allocation bytes 16.0 MB
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
 
210
  Used Block count 1
211
  Peak Allocated bytes 1.0 MB
212
  [ALLOC_GFX_MAIN]
213
+ Peak usage frame count: [32.0 KB-64.0 KB]: 4965 frames, [64.0 KB-128.0 KB]: 493 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
  Peak Allocated memory 66.4 KB
run_logs/timers.json CHANGED
@@ -2,15 +2,15 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.8421187996864319,
6
- "min": 0.8294015526771545,
7
- "max": 2.862067699432373,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8003.4970703125,
12
- "min": 8003.4970703125,
13
- "max": 29215.986328125,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,39 +26,39 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.93126392364502,
30
- "min": 0.578868567943573,
31
- "max": 12.945226669311523,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2521.596435546875,
36
- "min": 112.30050659179688,
37
- "max": 2640.826171875,
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.06596056137955292,
42
- "min": 0.06252342511816453,
43
- "max": 0.07189556669681241,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.26384224551821167,
48
- "min": 0.2500937004726581,
49
- "max": 0.35947783348406204,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.2147451358682969,
54
- "min": 0.14058841464073196,
55
- "max": 0.2829120778569988,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.8589805434731876,
60
- "min": 0.5623536585629278,
61
- "max": 1.3469010889530182,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 24.84090909090909,
114
- "min": 4.136363636363637,
115
- "max": 25.618181818181817,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1093.0,
120
- "min": 182.0,
121
- "max": 1409.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 24.84090909090909,
126
- "min": 4.136363636363637,
127
- "max": 25.618181818181817,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1093.0,
132
- "min": 182.0,
133
- "max": 1409.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
@@ -148,67 +148,67 @@
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1774515907",
152
  "python_version": "3.10.12 (main, Mar 26 2026, 08:57:09) [GCC 11.4.0]",
153
- "command_line_arguments": "/content/ml-agents/ml-agents/mlagents/trainers/learn.py ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1774516598"
160
  },
161
- "total": 691.0420400199996,
162
  "count": 1,
163
- "self": 0.5393680859997403,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.04395901799989588,
167
  "count": 1,
168
- "self": 0.04395901799989588
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 690.458712916,
172
  "count": 1,
173
- "self": 0.695101081975281,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.9992803519999143,
177
  "count": 1,
178
- "self": 3.9992803519999143
179
  },
180
  "TrainerController.advance": {
181
- "total": 685.6588675920248,
182
  "count": 18192,
183
- "self": 0.7597590580558062,
184
  "children": {
185
  "env_step": {
186
- "total": 499.50885010496995,
187
  "count": 18192,
188
- "self": 386.74676743300006,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 112.33429610399344,
192
  "count": 18192,
193
- "self": 2.2981345710272763,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 110.03616153296616,
197
  "count": 18192,
198
- "self": 110.03616153296616
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.42778656797645453,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 687.1033201259816,
209
  "count": 18192,
210
  "is_parallel": true,
211
- "self": 355.29735936896077,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
@@ -217,48 +217,48 @@
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
- "total": 0.00567378000005192,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0038776699993832153,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0017961100006687047,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0017961100006687047
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.046606675000020914,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0008353890002581466,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0007151039999371278,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0007151039999371278
244
  },
245
  "communicator.exchange": {
246
- "total": 0.04219078799997078,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.04219078799997078
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0028653939998548594,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0005732739991799463,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.002292120000674913,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.002292120000674913
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 331.8059607570208,
271
  "count": 18191,
272
  "is_parallel": true,
273
- "self": 15.749062510966269,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 9.289236497021193,
277
  "count": 18191,
278
  "is_parallel": true,
279
- "self": 9.289236497021193
280
  },
281
  "communicator.exchange": {
282
- "total": 247.05889551302835,
283
  "count": 18191,
284
  "is_parallel": true,
285
- "self": 247.05889551302835
286
  },
287
  "steps_from_proto": {
288
- "total": 59.708766236004976,
289
  "count": 18191,
290
  "is_parallel": true,
291
- "self": 11.343388004057033,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 48.36537823194794,
295
  "count": 181910,
296
  "is_parallel": true,
297
- "self": 48.36537823194794
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 185.390258428999,
311
  "count": 18192,
312
- "self": 0.8655924619638427,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 42.93650429603531,
316
  "count": 18192,
317
- "self": 42.41495265703452,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.5215516390007906,
321
  "count": 4,
322
- "self": 0.5215516390007906
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 141.58816167099985,
328
  "count": 90,
329
- "self": 65.6881444659748,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 75.90001720502505,
333
  "count": 4587,
334
- "self": 75.90001720502505
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 1.1669999366858974e-06,
344
  "count": 1,
345
- "self": 1.1669999366858974e-06
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.10546272300007331,
349
  "count": 1,
350
- "self": 0.0008940550001170777,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.10456866799995623,
354
  "count": 1,
355
- "self": 0.10456866799995623
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.9620283246040344,
6
+ "min": 0.9620283246040344,
7
+ "max": 2.867304563522339,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 9143.1171875,
12
+ "min": 9143.1171875,
13
+ "max": 29269.4453125,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.138323783874512,
30
+ "min": 0.25758981704711914,
31
+ "max": 13.138323783874512,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2561.97314453125,
36
+ "min": 49.97242736816406,
37
+ "max": 2669.353515625,
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.06012399918536711,
42
+ "min": 0.06012399918536711,
43
+ "max": 0.07639028564752902,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.24049599674146843,
48
+ "min": 0.24049599674146843,
49
+ "max": 0.36016795410393443,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.19520237910396912,
54
+ "min": 0.13120590685067846,
55
+ "max": 0.29419944841487733,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.7808095164158765,
60
+ "min": 0.5248236274027138,
61
+ "max": 1.4709972420743866,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 25.886363636363637,
114
+ "min": 3.590909090909091,
115
+ "max": 26.01818181818182,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1139.0,
120
+ "min": 158.0,
121
+ "max": 1431.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.886363636363637,
126
+ "min": 3.590909090909091,
127
+ "max": 26.01818181818182,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1139.0,
132
+ "min": 158.0,
133
+ "max": 1431.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1774516993",
152
  "python_version": "3.10.12 (main, Mar 26 2026, 08:57:09) [GCC 11.4.0]",
153
+ "command_line_arguments": "/content/ml-agents/ml-agents/mlagents/trainers/learn.py /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1774517652"
160
  },
161
+ "total": 658.9953637879998,
162
  "count": 1,
163
+ "self": 0.5389557970001988,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.027067356999850745,
167
  "count": 1,
168
+ "self": 0.027067356999850745
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 658.4293406339998,
172
  "count": 1,
173
+ "self": 0.6504912779387269,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.505038341999807,
177
  "count": 1,
178
+ "self": 2.505038341999807
179
  },
180
  "TrainerController.advance": {
181
+ "total": 655.1626470660617,
182
  "count": 18192,
183
+ "self": 0.6973801380472651,
184
  "children": {
185
  "env_step": {
186
+ "total": 474.3225228539809,
187
  "count": 18192,
188
+ "self": 367.14831215703,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 106.77208549002307,
192
  "count": 18192,
193
+ "self": 2.0967400040494795,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 104.6753454859736,
197
  "count": 18192,
198
+ "self": 104.6753454859736
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.4021252069278489,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 655.2187336440315,
209
  "count": 18192,
210
  "is_parallel": true,
211
+ "self": 339.599060131035,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.002587308000329358,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0007766989997435303,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0018106090005858277,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0018106090005858277
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.042542885999864666,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006956380002520746,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0005574859997068415,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0005574859997068415
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03868434799960596,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03868434799960596
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0026054140002997883,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0005307650003487652,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.002074648999951023,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.002074648999951023
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 315.61967351299654,
271
  "count": 18191,
272
  "is_parallel": true,
273
+ "self": 14.092061497235136,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 8.780506324909311,
277
  "count": 18191,
278
  "is_parallel": true,
279
+ "self": 8.780506324909311
280
  },
281
  "communicator.exchange": {
282
+ "total": 235.25572917790169,
283
  "count": 18191,
284
  "is_parallel": true,
285
+ "self": 235.25572917790169
286
  },
287
  "steps_from_proto": {
288
+ "total": 57.49137651295041,
289
  "count": 18191,
290
  "is_parallel": true,
291
+ "self": 10.688042399899132,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 46.80333411305128,
295
  "count": 181910,
296
  "is_parallel": true,
297
+ "self": 46.80333411305128
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 180.14274407403354,
311
  "count": 18192,
312
+ "self": 0.8370863640507196,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 40.909788694981216,
316
  "count": 18192,
317
+ "self": 40.39082906698059,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.5189596280006299,
321
  "count": 4,
322
+ "self": 0.5189596280006299
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 138.3958690150016,
328
  "count": 90,
329
+ "self": 66.3936062779585,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 72.00226273704311,
333
  "count": 4587,
334
+ "self": 72.00226273704311
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 1.3170001693652011e-06,
344
  "count": 1,
345
+ "self": 1.3170001693652011e-06
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.11116263099938806,
349
  "count": 1,
350
+ "self": 0.0012555889989016578,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.1099070420004864,
354
  "count": 1,
355
+ "self": 0.1099070420004864
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -4,8 +4,8 @@
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 13.454545454545455,
8
- "creation_time": 1774516083.484805,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
@@ -13,8 +13,8 @@
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 22.90909090909091,
17
- "creation_time": 1774516257.5857074,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
@@ -22,8 +22,8 @@
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 23.90909090909091,
26
- "creation_time": 1774516431.0897186,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
@@ -31,8 +31,8 @@
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 26.09090909090909,
35
- "creation_time": 1774516598.0796702,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
@@ -40,8 +40,8 @@
40
  {
41
  "steps": 200112,
42
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 26.09090909090909,
44
- "creation_time": 1774516598.2026603,
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
@@ -50,8 +50,8 @@
50
  "final_checkpoint": {
51
  "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 26.09090909090909,
54
- "creation_time": 1774516598.2026603,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
 
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 15.727272727272727,
8
+ "creation_time": 1774517156.249616,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
 
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
+ "reward": 22.454545454545453,
17
+ "creation_time": 1774517319.344353,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
 
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 25.363636363636363,
26
+ "creation_time": 1774517486.635206,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
 
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 25.181818181818183,
35
+ "creation_time": 1774517651.4590328,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
 
40
  {
41
  "steps": 200112,
42
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
+ "reward": 25.181818181818183,
44
+ "creation_time": 1774517651.5890005,
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
 
50
  "final_checkpoint": {
51
  "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
+ "reward": 25.181818181818183,
54
+ "creation_time": 1774517651.5890005,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]