Hugging Face's logo

HibaST
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
HibaST commited on
Commit
a44638e
·
verified ·
1 Parent(s): f606395

Push

Browse files
Files changed (28) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-100408.onnx +3 -0
  3. SnowballTarget/SnowballTarget-100408.pt +3 -0
  4. SnowballTarget/SnowballTarget-19992.onnx +1 -1
  5. SnowballTarget/SnowballTarget-19992.pt +1 -1
  6. SnowballTarget/SnowballTarget-29944.onnx +1 -1
  7. SnowballTarget/SnowballTarget-29944.pt +1 -1
  8. SnowballTarget/SnowballTarget-39984.onnx +1 -1
  9. SnowballTarget/SnowballTarget-39984.pt +1 -1
  10. SnowballTarget/SnowballTarget-49936.onnx +1 -1
  11. SnowballTarget/SnowballTarget-49936.pt +1 -1
  12. SnowballTarget/SnowballTarget-59976.onnx +3 -0
  13. SnowballTarget/SnowballTarget-59976.pt +3 -0
  14. SnowballTarget/SnowballTarget-69992.onnx +3 -0
  15. SnowballTarget/SnowballTarget-69992.pt +3 -0
  16. SnowballTarget/SnowballTarget-79968.onnx +3 -0
  17. SnowballTarget/SnowballTarget-79968.pt +3 -0
  18. SnowballTarget/SnowballTarget-89984.onnx +3 -0
  19. SnowballTarget/SnowballTarget-89984.pt +3 -0
  20. SnowballTarget/SnowballTarget-99960.onnx +3 -0
  21. SnowballTarget/SnowballTarget-99960.pt +3 -0
  22. SnowballTarget/checkpoint.pt +1 -1
  23. SnowballTarget/events.out.tfevents.1744037761.e6f70df1ed04.10951.0 +3 -0
  24. config.json +1 -1
  25. configuration.yaml +4 -4
  26. run_logs/Player-0.log +15 -18
  27. run_logs/timers.json +174 -174
  28. run_logs/training_status.json +54 -54
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dad5b750930e33b5275bdd4b4529381ef36b5b3b4cb5a225d67b1cbc90eca7c4
3
  size 657877
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a534b6f0a2a68469b4477d158633d988d1bba1ad701175ebef62922f771a8eb
3
  size 657877
SnowballTarget/SnowballTarget-100408.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a534b6f0a2a68469b4477d158633d988d1bba1ad701175ebef62922f771a8eb
3
+ size 657877
SnowballTarget/SnowballTarget-100408.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7748519e3090db91d85407fb2f0e71c37d72c20f807344771a11ab5eda3feb5
3
+ size 3870374
SnowballTarget/SnowballTarget-19992.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c441041ffec2ad80a44cbcfc800237f8af01aed2e070fe958f1ce3e0a8cc6ba
3
  size 657877
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e9bf0be6d2b6d353e8843204b4e9fae88a0924d1b3640a52c57966b3f466d0c
3
  size 657877
SnowballTarget/SnowballTarget-19992.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:595be72c98df462dcada45757cc78144b98e25f3008ada3d798dce78072dfdc6
3
  size 3870269
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bcca7e9c724d3a355a423d0b7ef18b1f3608a709d08274610474a4cb30738e2
3
  size 3870269
SnowballTarget/SnowballTarget-29944.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e869c9ea0caa54c45ce40112d6c1657bb681ebbed4ed1327510f75eb377ac2c2
3
  size 657877
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9284ccc217ed3fd6d3cc3617b01b6b0d5206968403a91f3111490ced66eeeb22
3
  size 657877
SnowballTarget/SnowballTarget-29944.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4fa313b58978844450ae0d3934dbc9a466493584794a01f0aab69dd98edd4080
3
  size 3870269
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:602d48fde491732d44df60cc807fa2a58cae14881408bedebab2f45271f6da35
3
  size 3870269
SnowballTarget/SnowballTarget-39984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51ea49cf4088e29732b03b5f71a01adecf575c4d36e0cc7ca673e69c16343f5e
3
  size 657877
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7884a57e909776c183f50cbae723f8bc31a0fe319dd1001754927357a44c631
3
  size 657877
SnowballTarget/SnowballTarget-39984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4afb0769ed371dc9f3791788912209ff00038254c2452d384c4fb7b8fca0124
3
  size 3870269
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82d36a613e0f4e8ae3791fb0ed91bcbec7b1ada51da1138d81905eaad88c78e3
3
  size 3870269
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2163b08305840b86770fa8a1627f3b3d237295b2500a9a72166e92a732515649
3
  size 657877
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1b024be966244d7ad5e1de4fb653b8f726d678e6f09971ee12c162022550479
3
  size 657877
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1aedb876421a4ca861ec6de32961d3ccf7b81c577e4d8d68c710b77bdd09d086
3
  size 3870269
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb81e13e397a56784a4cd7f607c9154dbb0754b291ab868e331344fac6eb5cb8
3
  size 3870269
SnowballTarget/SnowballTarget-59976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cdcae4f0b5e88942415cc9ce5cf84d167c72503f1c68c3d6da2f852cef25d70
3
+ size 657877
SnowballTarget/SnowballTarget-59976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d5d305dc159bd2c486a572cb17a24ac04d7cfb0800cf8a5dea4b4165bbfd21a
3
+ size 3870269
SnowballTarget/SnowballTarget-69992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2bfddfb2bbad65ef7fbe3add5258aac7508a3ab7f550d76cbd77f574254553f
3
+ size 657877
SnowballTarget/SnowballTarget-69992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b2fcd930bbf42b54a72057d3bf843467ac30cdd7dbc2245057fd7bc168a9af7
3
+ size 3870269
SnowballTarget/SnowballTarget-79968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7da3cd40f2df95049eb53064bafbd4a3913d563cabee9963e5e671a9529fab5e
3
+ size 657877
SnowballTarget/SnowballTarget-79968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b213bcee306d9c4722fd4dd11811a32264bb0299da0076fdf9d2599d460b89f1
3
+ size 3870269
SnowballTarget/SnowballTarget-89984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:063d79f2334e75529158809c173022546bf611d625f877550f822c0c1bd5d0bd
3
+ size 657877
SnowballTarget/SnowballTarget-89984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0faf46534e2c8268d00f88bcc7ccdbfbef281a36238b5fd9ed9e2603954d8770
3
+ size 3870269
SnowballTarget/SnowballTarget-99960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08a89542d66a4b909f3247c665a3c0d387b3a298fe193f21755f3103259915ea
3
+ size 657877
SnowballTarget/SnowballTarget-99960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73fe4c74ef5f72afb3a06674a99498d7b678f8af51641026cc1b2dfe6cc8c0af
3
+ size 3870269
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f99fd2014e2a7a9f81d82c923e868b19ef8cc7eead9332a101039fe8482bf96
3
  size 3869219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b1f53a21dd54e5f3f56c952c64ce4d58546fdb8fdf0993c7d12ac515b5345f7
3
  size 3869219
SnowballTarget/events.out.tfevents.1744037761.e6f70df1ed04.10951.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:846fa521576b60b5b428c260f2372f7361fb7e8e63cd52bd1cbea67e15c8fe57
3
+ size 33279
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": 5000, "network_settings": {"normalize": true, "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": 50000, "time_horizon": 64, "summary_freq": 1000, "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": 10000, "network_settings": {"normalize": true, "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": 100000, "time_horizon": 64, "summary_freq": 5000, "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
@@ -14,7 +14,7 @@ behaviors:
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
16
  epsilon_schedule: linear
17
- checkpoint_interval: 5000
18
  network_settings:
19
  normalize: true
20
  hidden_units: 256
@@ -38,9 +38,9 @@ behaviors:
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
- max_steps: 50000
42
  time_horizon: 64
43
- summary_freq: 1000
44
  threaded: false
45
  self_play: null
46
  behavioral_cloning: null
@@ -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
 
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
16
  epsilon_schedule: linear
17
+ checkpoint_interval: 10000
18
  network_settings:
19
  normalize: true
20
  hidden_units: 256
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 100000
42
  time_horizon: 64
43
+ summary_freq: 5000
44
  threaded: false
45
  self_play: null
46
  behavioral_cloning: null
 
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 0.412 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: 1.563377 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.
@@ -53,7 +50,7 @@ Memory Statistics:
53
  [ALLOC_TEMP_TLS] TLS Allocator
54
  StackAllocators :
55
  [ALLOC_TEMP_MAIN]
56
- Peak usage frame count: [8.0 KB-16.0 KB]: 1355 frames, [16.0 KB-32.0 KB]: 22 frames, [2.0 MB-4.0 MB]: 1 frames
57
  Initial Block Size 4.0 MB
58
  Current Block Size 4.0 MB
59
  Peak Allocated Bytes 2.0 MB
@@ -169,22 +166,22 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 40
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
- Peak usage frame count: [4.0 MB-8.0 MB]: 1378 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 5.9 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 1378 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
@@ -213,13 +210,13 @@ 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]: 1093 frames, [64.0 KB-128.0 KB]: 285 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 66.4 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 1378 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
@@ -231,13 +228,13 @@ Memory Statistics:
231
  Used Block count 1
232
  Peak Allocated bytes 1.0 MB
233
  [ALLOC_CACHEOBJECTS_MAIN]
234
- Peak usage frame count: [0.5 MB-1.0 MB]: 1378 frames
235
  Requested Block Size 4.0 MB
236
  Peak Block count 1
237
  Peak Allocated memory 0.6 MB
238
  Peak Large allocation bytes 0 B
239
  [ALLOC_CACHEOBJECTS_THREAD]
240
- Peak usage frame count: [0.5 MB-1.0 MB]: 1377 frames, [2.0 MB-4.0 MB]: 1 frames
241
  Requested Block Size 4.0 MB
242
  Peak Block count 1
243
  Peak Allocated memory 2.2 MB
@@ -249,13 +246,13 @@ Memory Statistics:
249
  Used Block count 1
250
  Peak Allocated bytes 1.0 MB
251
  [ALLOC_TYPETREE_MAIN]
252
- Peak usage frame count: [0-1.0 KB]: 1378 frames
253
  Requested Block Size 2.0 MB
254
  Peak Block count 1
255
  Peak Allocated memory 1.0 KB
256
  Peak Large allocation bytes 0 B
257
  [ALLOC_TYPETREE_THREAD]
258
- Peak usage frame count: [1.0 KB-2.0 KB]: 1378 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  Peak Allocated memory 1.7 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 0.160 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: 0.979320 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.
 
50
  [ALLOC_TEMP_TLS] TLS Allocator
51
  StackAllocators :
52
  [ALLOC_TEMP_MAIN]
53
+ Peak usage frame count: [8.0 KB-16.0 KB]: 2693 frames, [16.0 KB-32.0 KB]: 45 frames, [2.0 MB-4.0 MB]: 1 frames
54
  Initial Block Size 4.0 MB
55
  Current Block Size 4.0 MB
56
  Peak Allocated Bytes 2.0 MB
 
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
+ Peak main deferred allocation count 47
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
173
  Peak Allocated bytes 1.0 MB
174
  [ALLOC_DEFAULT_MAIN]
175
+ Peak usage frame count: [4.0 MB-8.0 MB]: 2739 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 6.0 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 2739 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.7 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]: 2325 frames, [64.0 KB-128.0 KB]: 414 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 67.7 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 2739 frames
220
  Requested Block Size 16.0 MB
221
  Peak Block count 1
222
  Peak Allocated memory 39.6 KB
 
228
  Used Block count 1
229
  Peak Allocated bytes 1.0 MB
230
  [ALLOC_CACHEOBJECTS_MAIN]
231
+ Peak usage frame count: [0.5 MB-1.0 MB]: 2739 frames
232
  Requested Block Size 4.0 MB
233
  Peak Block count 1
234
  Peak Allocated memory 0.6 MB
235
  Peak Large allocation bytes 0 B
236
  [ALLOC_CACHEOBJECTS_THREAD]
237
+ Peak usage frame count: [0.5 MB-1.0 MB]: 2738 frames, [2.0 MB-4.0 MB]: 1 frames
238
  Requested Block Size 4.0 MB
239
  Peak Block count 1
240
  Peak Allocated memory 2.2 MB
 
246
  Used Block count 1
247
  Peak Allocated bytes 1.0 MB
248
  [ALLOC_TYPETREE_MAIN]
249
+ Peak usage frame count: [0-1.0 KB]: 2739 frames
250
  Requested Block Size 2.0 MB
251
  Peak Block count 1
252
  Peak Allocated memory 1.0 KB
253
  Peak Large allocation bytes 0 B
254
  [ALLOC_TYPETREE_THREAD]
255
+ Peak usage frame count: [1.0 KB-2.0 KB]: 2739 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -2,213 +2,213 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 2.2464041709899902,
6
- "min": 2.183406352996826,
7
- "max": 2.890059471130371,
8
- "count": 50
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 3162.93701171875,
12
- "min": 1567.7017822265625,
13
- "max": 4304.73583984375,
14
- "count": 50
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 49936.0,
18
- "min": 960.0,
19
- "max": 49936.0,
20
- "count": 50
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 49936.0,
24
- "min": 960.0,
25
- "max": 49936.0,
26
- "count": 50
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 5.641419887542725,
30
- "min": 0.09161143749952316,
31
- "max": 5.641419887542725,
32
- "count": 50
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 84.62129974365234,
36
- "min": 1.3741716146469116,
37
- "max": 140.79539489746094,
38
- "count": 50
39
- },
40
- "SnowballTarget.IsTraining.mean": {
41
- "value": 1.0,
42
- "min": 1.0,
43
- "max": 1.0,
44
- "count": 50
45
- },
46
- "SnowballTarget.IsTraining.sum": {
47
- "value": 1.0,
48
- "min": 1.0,
49
- "max": 1.0,
50
- "count": 50
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.07956860451867767,
54
- "min": 0.056481379854684585,
55
- "max": 0.07962269508553778,
56
- "count": 22
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.07956860451867767,
60
- "min": 0.056481379854684585,
61
- "max": 0.07962269508553778,
62
- "count": 22
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.2733978161624834,
66
- "min": 0.08662013585368793,
67
- "max": 0.336169576235846,
68
- "count": 22
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.2733978161624834,
72
- "min": 0.08662013585368793,
73
- "max": 0.336169576235846,
74
- "count": 22
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 1.0128096624000002e-05,
78
- "min": 1.0128096624000002e-05,
79
- "max": 0.00028732800422399995,
80
- "count": 22
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 1.0128096624000002e-05,
84
- "min": 1.0128096624000002e-05,
85
- "max": 0.00028732800422399995,
86
- "count": 22
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.103376,
90
- "min": 0.103376,
91
- "max": 0.19577599999999998,
92
- "count": 22
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.103376,
96
- "min": 0.103376,
97
- "max": 0.19577599999999998,
98
- "count": 22
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
- "value": 0.0001784624000000001,
102
- "min": 0.0001784624000000001,
103
- "max": 0.0047892224,
104
- "count": 22
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.0001784624000000001,
108
- "min": 0.0001784624000000001,
109
- "max": 0.0047892224,
110
- "count": 22
111
  },
112
  "SnowballTarget.Environment.EpisodeLength.mean": {
113
  "value": 199.0,
114
  "min": 199.0,
115
  "max": 199.0,
116
- "count": 22
117
  },
118
  "SnowballTarget.Environment.EpisodeLength.sum": {
119
- "value": 2189.0,
120
- "min": 2189.0,
121
- "max": 2189.0,
122
- "count": 22
123
  },
124
  "SnowballTarget.Environment.CumulativeReward.mean": {
125
- "value": 13.181818181818182,
126
- "min": 2.6363636363636362,
127
- "max": 15.0,
128
- "count": 26
129
  },
130
  "SnowballTarget.Environment.CumulativeReward.sum": {
131
- "value": 145.0,
132
- "min": 5.0,
133
- "max": 150.0,
134
- "count": 26
135
  },
136
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
137
- "value": 13.181818181818182,
138
- "min": 2.6363636363636362,
139
- "max": 15.0,
140
- "count": 26
141
  },
142
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
143
- "value": 145.0,
144
- "min": 5.0,
145
- "max": 150.0,
146
- "count": 26
 
 
 
 
 
 
 
 
 
 
 
 
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1744036974",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./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": "2.6.0+cu124",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1744037119"
160
  },
161
- "total": 145.08223848300008,
162
  "count": 1,
163
- "self": 0.5854291990001457,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.03689820599993254,
167
  "count": 1,
168
- "self": 0.03689820599993254
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 144.459911078,
172
  "count": 1,
173
- "self": 0.15162600099370138,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 5.783731922000015,
177
  "count": 1,
178
- "self": 5.783731922000015
179
  },
180
  "TrainerController.advance": {
181
- "total": 138.41417005700623,
182
- "count": 4592,
183
- "self": 0.16260276901198267,
184
  "children": {
185
  "env_step": {
186
- "total": 93.99322378599686,
187
- "count": 4592,
188
- "self": 78.9342831149952,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 14.97263455099801,
192
- "count": 4592,
193
- "self": 0.4780821950016616,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 14.494552355996348,
197
- "count": 4592,
198
- "self": 14.494552355996348
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.08630612000365545,
204
- "count": 4592,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 143.56266594199883,
209
- "count": 4592,
210
  "is_parallel": true,
211
- "self": 75.56295954600819,
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": 0.008945437999955175,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0062500510005065735,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0026953869994486013,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0026953869994486013
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.04651200600005723,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0008553680002023611,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0004508819999955449,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0004508819999955449
244
  },
245
  "communicator.exchange": {
246
- "total": 0.042861442999992505,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.042861442999992505
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0023443129998668155,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0004549630000383331,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0018893499998284824,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0018893499998284824
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 67.99970639599064,
271
- "count": 4591,
272
  "is_parallel": true,
273
- "self": 3.290133136991244,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 1.8501562850015034,
277
- "count": 4591,
278
  "is_parallel": true,
279
- "self": 1.8501562850015034
280
  },
281
  "communicator.exchange": {
282
- "total": 52.90719391299922,
283
- "count": 4591,
284
  "is_parallel": true,
285
- "self": 52.90719391299922
286
  },
287
  "steps_from_proto": {
288
- "total": 9.952223060998676,
289
- "count": 4591,
290
  "is_parallel": true,
291
- "self": 1.9109727180123173,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 8.041250342986359,
295
- "count": 45910,
296
  "is_parallel": true,
297
- "self": 8.041250342986359
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 44.25834350199739,
311
- "count": 4592,
312
- "self": 0.21211755099352558,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 12.73914934100344,
316
- "count": 4592,
317
- "self": 11.251446006003562,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 1.4877033349998783,
321
  "count": 10,
322
- "self": 1.4877033349998783
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 31.307076610000422,
328
- "count": 22,
329
- "self": 11.848179405002611,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 19.45889720499781,
333
- "count": 1119,
334
- "self": 19.45889720499781
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 1.4620000001741573e-06,
344
  "count": 1,
345
- "self": 1.4620000001741573e-06
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.11038163600005646,
349
  "count": 1,
350
- "self": 0.0011854340000354568,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.109196202000021,
354
  "count": 1,
355
- "self": 0.109196202000021
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 1.3752208948135376,
6
+ "min": 1.3752208948135376,
7
+ "max": 2.8792243003845215,
8
+ "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 7019.12744140625,
12
+ "min": 6500.197265625,
13
+ "max": 14695.560546875,
14
+ "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 99960.0,
18
+ "min": 4976.0,
19
+ "max": 99960.0,
20
+ "count": 20
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 99960.0,
24
+ "min": 4976.0,
25
+ "max": 99960.0,
26
+ "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 10.686447143554688,
30
+ "min": 0.07361346483230591,
31
+ "max": 10.686447143554688,
32
+ "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 1036.5853271484375,
36
+ "min": 7.140506267547607,
37
+ "max": 1123.251953125,
38
+ "count": 20
 
 
 
 
 
 
 
 
 
 
 
 
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.06302493172709137,
42
+ "min": 0.060685857383742034,
43
+ "max": 0.07596640078140898,
44
+ "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.12604986345418273,
48
+ "min": 0.12137171476748407,
49
+ "max": 0.22474944917713385,
50
+ "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.2708837576940948,
54
+ "min": 0.10067576895851423,
55
+ "max": 0.31874683367855405,
56
+ "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.5417675153881896,
60
+ "min": 0.20135153791702845,
61
+ "max": 0.9013772790922838,
62
+ "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
+ "value": 6.564097812000004e-06,
66
+ "min": 6.564097812000004e-06,
67
+ "max": 0.000290364003212,
68
+ "count": 20
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
+ "value": 1.3128195624000008e-05,
72
+ "min": 1.3128195624000008e-05,
73
+ "max": 0.000742392052536,
74
+ "count": 20
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
+ "value": 0.10218800000000001,
78
+ "min": 0.10218800000000001,
79
+ "max": 0.19678800000000002,
80
+ "count": 20
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
+ "value": 0.20437600000000003,
84
+ "min": 0.20437600000000003,
85
+ "max": 0.547464,
86
+ "count": 20
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
+ "value": 0.00011918120000000008,
90
+ "min": 0.00011918120000000008,
91
+ "max": 0.0048397212,
92
+ "count": 20
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
+ "value": 0.00023836240000000016,
96
+ "min": 0.00023836240000000016,
97
+ "max": 0.012378453600000002,
98
+ "count": 20
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
+ "count": 20
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
+ "value": 4378.0,
108
+ "min": 4378.0,
109
+ "max": 6567.0,
110
+ "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 22.818181818181817,
114
+ "min": 2.4545454545454546,
115
+ "max": 22.818181818181817,
116
+ "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 502.0,
120
+ "min": 54.0,
121
+ "max": 725.0,
122
+ "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 22.818181818181817,
126
+ "min": 2.4545454545454546,
127
+ "max": 22.818181818181817,
128
+ "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 502.0,
132
+ "min": 54.0,
133
+ "max": 725.0,
134
+ "count": 20
135
+ },
136
+ "SnowballTarget.IsTraining.mean": {
137
+ "value": 1.0,
138
+ "min": 1.0,
139
+ "max": 1.0,
140
+ "count": 20
141
+ },
142
+ "SnowballTarget.IsTraining.sum": {
143
+ "value": 1.0,
144
+ "min": 1.0,
145
+ "max": 1.0,
146
+ "count": 20
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1744037760",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
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": "2.6.0+cu124",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1744038042"
160
  },
161
+ "total": 281.903147904,
162
  "count": 1,
163
+ "self": 0.5345222400001148,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.03393595599982291,
167
  "count": 1,
168
+ "self": 0.03393595599982291
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 281.33468970800004,
172
  "count": 1,
173
+ "self": 0.297205634022248,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.958993692999684,
177
  "count": 1,
178
+ "self": 2.958993692999684
179
  },
180
  "TrainerController.advance": {
181
+ "total": 277.9517094909779,
182
+ "count": 9128,
183
+ "self": 0.3209863119691363,
184
  "children": {
185
  "env_step": {
186
+ "total": 191.080019893996,
187
+ "count": 9128,
188
+ "self": 160.9206809839343,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 29.981188425026176,
192
+ "count": 9128,
193
+ "self": 1.0280603210212576,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 28.953128104004918,
197
+ "count": 9128,
198
+ "self": 28.953128104004918
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.17815048503553044,
204
+ "count": 9128,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 280.00207520498907,
209
+ "count": 9128,
210
  "is_parallel": true,
211
+ "self": 141.3386076509646,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.003488911999738775,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0010046499996860803,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.002484262000052695,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.002484262000052695
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.08540399899993645,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006688529997518344,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004942169998685131,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004942169998685131
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.08211564400016869,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.08211564400016869
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0021252850001474144,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0004290730003049248,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0016962119998424896,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0016962119998424896
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 138.66346755402446,
271
+ "count": 9127,
272
  "is_parallel": true,
273
+ "self": 6.582037075058906,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 3.602298950992008,
277
+ "count": 9127,
278
  "is_parallel": true,
279
+ "self": 3.602298950992008
280
  },
281
  "communicator.exchange": {
282
+ "total": 108.36501480700053,
283
+ "count": 9127,
284
  "is_parallel": true,
285
+ "self": 108.36501480700053
286
  },
287
  "steps_from_proto": {
288
+ "total": 20.114116720973016,
289
+ "count": 9127,
290
  "is_parallel": true,
291
+ "self": 4.061979567959497,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 16.05213715301352,
295
+ "count": 91270,
296
  "is_parallel": true,
297
+ "self": 16.05213715301352
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 86.55070328501279,
311
+ "count": 9128,
312
+ "self": 0.38456874204575797,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 24.10928821096786,
316
+ "count": 9128,
317
+ "self": 22.6672349959681,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 1.4420532149997598,
321
  "count": 10,
322
+ "self": 1.4420532149997598
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 62.05684633199917,
328
+ "count": 45,
329
+ "self": 23.125513341992246,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 38.93133299000692,
333
+ "count": 2292,
334
+ "self": 38.93133299000692
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 1.5740001799713355e-06,
344
  "count": 1,
345
+ "self": 1.5740001799713355e-06
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.12677931600001102,
349
  "count": 1,
350
+ "self": 0.0018980419999934384,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.12488127400001758,
354
  "count": 1,
355
+ "self": 0.12488127400001758
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -2,103 +2,103 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 9952,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-9952.onnx",
7
- "reward": 3.909090909090909,
8
- "creation_time": 1744037008.3371391,
9
  "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-9952.pt"
11
  ]
12
  },
13
  {
14
- "steps": 14992,
15
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-14992.onnx",
16
- "reward": 6.0,
17
- "creation_time": 1744037021.8986883,
18
  "auxillary_file_paths": [
19
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-14992.pt"
20
  ]
21
  },
22
  {
23
- "steps": 19992,
24
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-19992.onnx",
25
- "reward": 8.363636363636363,
26
- "creation_time": 1744037036.8903506,
27
  "auxillary_file_paths": [
28
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-19992.pt"
29
  ]
30
  },
31
  {
32
- "steps": 24968,
33
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-24968.onnx",
34
- "reward": 9.818181818181818,
35
- "creation_time": 1744037050.4286144,
36
  "auxillary_file_paths": [
37
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-24968.pt"
38
  ]
39
  },
40
  {
41
- "steps": 29944,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-29944.onnx",
43
- "reward": 10.818181818181818,
44
- "creation_time": 1744037062.4029884,
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-29944.pt"
47
  ]
48
  },
49
  {
50
- "steps": 34984,
51
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-34984.onnx",
52
- "reward": 11.454545454545455,
53
- "creation_time": 1744037075.9918327,
54
  "auxillary_file_paths": [
55
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-34984.pt"
56
  ]
57
  },
58
  {
59
- "steps": 39984,
60
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-39984.onnx",
61
- "reward": 12.909090909090908,
62
- "creation_time": 1744037091.5316777,
63
  "auxillary_file_paths": [
64
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-39984.pt"
65
  ]
66
  },
67
  {
68
- "steps": 44960,
69
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-44960.onnx",
70
- "reward": 12.909090909090908,
71
- "creation_time": 1744037104.879977,
72
  "auxillary_file_paths": [
73
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-44960.pt"
74
  ]
75
  },
76
  {
77
- "steps": 49936,
78
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
79
- "reward": 13.181818181818182,
80
- "creation_time": 1744037118.3437827,
81
  "auxillary_file_paths": [
82
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
83
  ]
84
  },
85
  {
86
- "steps": 50512,
87
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-50512.onnx",
88
- "reward": 13.181818181818182,
89
- "creation_time": 1744037118.6858354,
90
  "auxillary_file_paths": [
91
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-50512.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
- "steps": 50512,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
- "reward": 13.181818181818182,
99
- "creation_time": 1744037118.6858354,
100
  "auxillary_file_paths": [
101
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-50512.pt"
102
  ]
103
  }
104
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 19992,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-19992.onnx",
7
+ "reward": 10.090909090909092,
8
+ "creation_time": 1744037819.750369,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-19992.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 29944,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-29944.onnx",
16
+ "reward": 12.0,
17
+ "creation_time": 1744037845.5590613,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-29944.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 39984,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-39984.onnx",
25
+ "reward": 14.636363636363637,
26
+ "creation_time": 1744037873.7477229,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-39984.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 49936,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
34
+ "reward": 16.90909090909091,
35
+ "creation_time": 1744037900.4458563,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 59976,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-59976.onnx",
43
+ "reward": 20.09090909090909,
44
+ "creation_time": 1744037927.682929,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-59976.pt"
47
  ]
48
  },
49
  {
50
+ "steps": 69992,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-69992.onnx",
52
+ "reward": 19.636363636363637,
53
+ "creation_time": 1744037954.9802897,
54
  "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-69992.pt"
56
  ]
57
  },
58
  {
59
+ "steps": 79968,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-79968.onnx",
61
+ "reward": 21.363636363636363,
62
+ "creation_time": 1744037985.5028467,
63
  "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-79968.pt"
65
  ]
66
  },
67
  {
68
+ "steps": 89984,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-89984.onnx",
70
+ "reward": 22.272727272727273,
71
+ "creation_time": 1744038012.8001678,
72
  "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-89984.pt"
74
  ]
75
  },
76
  {
77
+ "steps": 99960,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
79
+ "reward": 22.818181818181817,
80
+ "creation_time": 1744038041.8376045,
81
  "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
83
  ]
84
  },
85
  {
86
+ "steps": 100408,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-100408.onnx",
88
+ "reward": 22.818181818181817,
89
+ "creation_time": 1744038042.036252,
90
  "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-100408.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 100408,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 22.818181818181817,
99
+ "creation_time": 1744038042.036252,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-100408.pt"
102
  ]
103
  }
104
  },