Hugging Face's logo

JoeBater
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
JoeBater commited on
Commit
4b8da20
·
verified ·
1 Parent(s): 614b643

Fourth Push

Browse files
Files changed (26) 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-249944.onnx +3 -0
  7. SnowballTarget/SnowballTarget-249944.pt +3 -0
  8. SnowballTarget/SnowballTarget-299968.onnx +3 -0
  9. SnowballTarget/SnowballTarget-299968.pt +3 -0
  10. SnowballTarget/SnowballTarget-349992.onnx +3 -0
  11. SnowballTarget/SnowballTarget-349992.pt +3 -0
  12. SnowballTarget/SnowballTarget-399992.onnx +3 -0
  13. SnowballTarget/SnowballTarget-399992.pt +3 -0
  14. SnowballTarget/SnowballTarget-400312.onnx +3 -0
  15. SnowballTarget/SnowballTarget-400312.pt +3 -0
  16. SnowballTarget/SnowballTarget-49936.onnx +1 -1
  17. SnowballTarget/SnowballTarget-49936.pt +1 -1
  18. SnowballTarget/SnowballTarget-99960.onnx +1 -1
  19. SnowballTarget/SnowballTarget-99960.pt +1 -1
  20. SnowballTarget/checkpoint.pt +1 -1
  21. SnowballTarget/events.out.tfevents.1725453953.0d8b602b2909.6500.0 +3 -0
  22. config.json +1 -1
  23. configuration.yaml +2 -2
  24. run_logs/Player-0.log +15 -18
  25. run_logs/timers.json +168 -168
  26. run_logs/training_status.json +53 -17
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d97f35ae1bab10bfd83e9e64bb95e28569b27da9597b84d7b93cb45eb397bb4a
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a46fef5e90a8087c6d407364ec469a586cd5f01ed4ac1b37f605d50c126ae136
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9020c776387e7377da53b970849f772d9701108ac14b987b3612b153821710a
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5259664bc48e4ab023b9bdffd862630fcb8fad6e58d9481cb33a203cf8b26794
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cced89dd491c4f41e1955474be80ba5f92f591764c41d335e80eb34402cfd1b
3
  size 3849115
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22cb015a1d4487be91ce8faa7e497f8b446ce0d01cc176e17ce518ebd1e54b2d
3
  size 3849115
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d97f35ae1bab10bfd83e9e64bb95e28569b27da9597b84d7b93cb45eb397bb4a
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8626862abb37457088a435fe2084196cebd3d1303175f2fa34b4a267cc33c4f1
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:afb90de5180da4b6cf5282444ab75caabda45e373fc1434e3f7666bdc38235fe
3
  size 3849115
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f25bfa238a2e6a43f4b0a174afd5610dc23bfc5c5752aa410449453c4bd37ee1
3
  size 3849115
SnowballTarget/SnowballTarget-249944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c204e5329b5e39e8b6b36a18853c6cb8ae8c375ad706019b393a1fc1e02bbc6b
3
+ size 650646
SnowballTarget/SnowballTarget-249944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e400235fccb3ebf7390351e1833b6f1416f2fece43c74f5edacb7dd0bfe478ff
3
+ size 3849115
SnowballTarget/SnowballTarget-299968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7fdcdde8b39f26bc187d007916e588bbc7cdaea3310a598527da535a8bc2df6
3
+ size 650646
SnowballTarget/SnowballTarget-299968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8402ec7cb32da35987f64880dd6015a8ede3e11253c02d47a493ef0ee9dfa85b
3
+ size 3849115
SnowballTarget/SnowballTarget-349992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edf93db5678ceabee67a15d90264c549f9c61b0a139a7dc9261c4a476a20a9bb
3
+ size 650646
SnowballTarget/SnowballTarget-349992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f77e65490a40992cf9bbe7e9dd82dc736e1b3c68d70d7aafea4b6574de6dd008
3
+ size 3849115
SnowballTarget/SnowballTarget-399992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a46fef5e90a8087c6d407364ec469a586cd5f01ed4ac1b37f605d50c126ae136
3
+ size 650646
SnowballTarget/SnowballTarget-399992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48a357973e7febcba1afe2d6a10c2630cb685733173d7a26c3272817b7ba3a25
3
+ size 3849115
SnowballTarget/SnowballTarget-400312.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a46fef5e90a8087c6d407364ec469a586cd5f01ed4ac1b37f605d50c126ae136
3
+ size 650646
SnowballTarget/SnowballTarget-400312.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:518e9eb41165d8f756f0712ead3c15b5b010bed10344de9edff54f2bd402c792
3
+ size 3849115
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c22d4284b92d1b6e823b28615b861472e7ecfdc4e50848fa073f17b5b1bff53b
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42dea6fa959c87dfa2abe8ed112cc39bfdeb4ee73cac0e97061f747377887ace
3
  size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9106023827024dceade797d334287bafeed69444a020506b43f06d0c7721b08d
3
  size 3849040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03a1da4480f6a64fbca266e7f317eb6f18d2fe4e0145579a21868e8e56329280
3
  size 3849040
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2990101d4004e0621127ce7dd575e1f7c19788ccb0fac2b274f8000490734568
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64fa8aa8e3ab45dfc2619badcfc030cfba78dcbbcd5348cae63770bf245e313f
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af234d1c674dbf55249eea2e67b493537db4472d80f3e5d8ac9690d7efaa79e5
3
  size 3849040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af10b72dcc1c4e5462352a64c09d328c640301b38ff217861403bf6d3aa22739
3
  size 3849040
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99fbaa9693cc72e19f1ff49905fd1df5732539487779cf24a259f78f6f216c28
3
  size 3848290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24df927a3c49f959148185706e54bf1e48724bb3d219a031a671b7d656646671
3
  size 3848290
SnowballTarget/events.out.tfevents.1725453953.0d8b602b2909.6500.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c56d4fb6217c0b611cf031e0ff498c07c99011c3cff7f405c893720d5c8c5f3
3
+ size 40156
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": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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": 400000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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
@@ -38,7 +38,7 @@ behaviors:
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
- max_steps: 200000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
@@ -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
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 400000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
 
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 0.103 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: 0.729068 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]: 5370 frames, [16.0 KB-32.0 KB]: 91 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 37
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]: 5462 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.5 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 5462 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.9 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]: 4708 frames, [64.0 KB-128.0 KB]: 754 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]: 5462 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]: 5462 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]: 5461 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]: 5462 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]: 5462 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 0.153 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: 0.975908 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]: 10737 frames, [16.0 KB-32.0 KB]: 182 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 41
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]: 10920 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 8.8 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 10920 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]: 10065 frames, [64.0 KB-128.0 KB]: 855 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 66.8 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 10920 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]: 10920 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]: 10919 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]: 10920 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]: 10920 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": 0.9373330473899841,
6
- "min": 0.9373330473899841,
7
- "max": 2.8643720149993896,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8980.587890625,
12
- "min": 8980.587890625,
13
- "max": 29397.05078125,
14
- "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 199984.0,
18
  "min": 9952.0,
19
- "max": 199984.0,
20
- "count": 20
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 199984.0,
24
  "min": 9952.0,
25
- "max": 199984.0,
26
- "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.769098281860352,
30
- "min": 0.3617739975452423,
31
- "max": 12.769098281860352,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2489.97412109375,
36
- "min": 70.18415832519531,
37
- "max": 2581.089599609375,
38
- "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
- "count": 20
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 8756.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
- "count": 20
51
- },
52
- "SnowballTarget.Environment.CumulativeReward.mean": {
53
- "value": 25.181818181818183,
54
- "min": 3.6136363636363638,
55
- "max": 25.181818181818183,
56
- "count": 20
57
- },
58
- "SnowballTarget.Environment.CumulativeReward.sum": {
59
- "value": 1108.0,
60
- "min": 159.0,
61
- "max": 1385.0,
62
- "count": 20
63
- },
64
- "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
- "value": 25.181818181818183,
66
- "min": 3.6136363636363638,
67
- "max": 25.181818181818183,
68
- "count": 20
69
- },
70
- "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
- "value": 1108.0,
72
- "min": 159.0,
73
- "max": 1385.0,
74
- "count": 20
75
  },
76
  "SnowballTarget.Losses.PolicyLoss.mean": {
77
- "value": 0.06987765758651007,
78
- "min": 0.06259998128179908,
79
- "max": 0.07805273623528718,
80
- "count": 20
81
  },
82
  "SnowballTarget.Losses.PolicyLoss.sum": {
83
- "value": 0.2795106303460403,
84
- "min": 0.2604347842884725,
85
- "max": 0.36956131774315826,
86
- "count": 20
87
  },
88
  "SnowballTarget.Losses.ValueLoss.mean": {
89
- "value": 0.18032612096445233,
90
- "min": 0.12864354022267258,
91
- "max": 0.27835796408209146,
92
- "count": 20
93
  },
94
  "SnowballTarget.Losses.ValueLoss.sum": {
95
- "value": 0.7213044838578093,
96
- "min": 0.5145741608906903,
97
- "max": 1.3455678171971264,
98
- "count": 20
99
  },
100
  "SnowballTarget.Policy.LearningRate.mean": {
101
- "value": 8.082097306000005e-06,
102
- "min": 8.082097306000005e-06,
103
- "max": 0.00029184900271699997,
104
- "count": 20
105
  },
106
  "SnowballTarget.Policy.LearningRate.sum": {
107
- "value": 3.232838922400002e-05,
108
- "min": 3.232838922400002e-05,
109
- "max": 0.00138516003828,
110
- "count": 20
111
  },
112
  "SnowballTarget.Policy.Epsilon.mean": {
113
- "value": 0.10269400000000001,
114
- "min": 0.10269400000000001,
115
- "max": 0.19728300000000004,
116
- "count": 20
117
  },
118
  "SnowballTarget.Policy.Epsilon.sum": {
119
- "value": 0.41077600000000003,
120
- "min": 0.41077600000000003,
121
- "max": 0.96172,
122
- "count": 20
123
  },
124
  "SnowballTarget.Policy.Beta.mean": {
125
- "value": 0.0001444306000000001,
126
- "min": 0.0001444306000000001,
127
- "max": 0.0048644217,
128
- "count": 20
129
  },
130
  "SnowballTarget.Policy.Beta.sum": {
131
- "value": 0.0005777224000000004,
132
- "min": 0.0005777224000000004,
133
- "max": 0.023089828,
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": "1725452837",
152
  "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]",
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": "1.1.0.dev0",
155
  "mlagents_envs_version": "1.1.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.4.0+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1725453324"
160
  },
161
- "total": 487.700521837,
162
  "count": 1,
163
- "self": 0.48108534499993993,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.0663818200000037,
167
  "count": 1,
168
- "self": 0.0663818200000037
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 487.15305467200005,
172
  "count": 1,
173
- "self": 0.66380439699509,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 2.1688778989999946,
177
  "count": 1,
178
- "self": 2.1688778989999946
179
  },
180
  "TrainerController.advance": {
181
- "total": 484.24192170600503,
182
- "count": 18205,
183
- "self": 0.3251167240002246,
184
  "children": {
185
  "env_step": {
186
- "total": 483.9168049820048,
187
- "count": 18205,
188
- "self": 373.01660735300106,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 110.55774927799922,
192
- "count": 18205,
193
- "self": 1.6372911020024503,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 108.92045817599677,
197
- "count": 18205,
198
- "self": 108.92045817599677
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.34244835100452065,
204
- "count": 18205,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 485.9318569990047,
209
- "count": 18205,
210
  "is_parallel": true,
211
- "self": 227.92830747600698,
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": 0.0024863480000476557,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.000710510000146769,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0017758379999008866,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0017758379999008866
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.04067934300002207,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0008000610000635788,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0004790790000015477,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0004790790000015477
244
  },
245
  "communicator.exchange": {
246
- "total": 0.037083150999990266,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.037083150999990266
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0023170519999666794,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00046226599994270146,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.001854786000023978,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.001854786000023978
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 258.00354952299773,
271
- "count": 18204,
272
  "is_parallel": true,
273
- "self": 11.7186065879946,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 6.1948302860022295,
277
- "count": 18204,
278
  "is_parallel": true,
279
- "self": 6.1948302860022295
280
  },
281
  "communicator.exchange": {
282
- "total": 201.9083923829956,
283
- "count": 18204,
284
  "is_parallel": true,
285
- "self": 201.9083923829956
286
  },
287
  "steps_from_proto": {
288
- "total": 38.1817202660053,
289
- "count": 18204,
290
  "is_parallel": true,
291
- "self": 7.395677356997908,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 30.786042909007392,
295
- "count": 182040,
296
  "is_parallel": true,
297
- "self": 30.786042909007392
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.0001874069999985295,
313
  "count": 1,
314
- "self": 0.0001874069999985295,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 478.732554026972,
324
- "count": 637741,
325
  "is_parallel": true,
326
- "self": 13.856838520912618,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 256.0251156450591,
330
- "count": 637741,
331
  "is_parallel": true,
332
- "self": 255.17942633905903,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 0.8456893060000539,
336
- "count": 4,
337
  "is_parallel": true,
338
- "self": 0.8456893060000539
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 208.85059986100032,
344
- "count": 90,
345
  "is_parallel": true,
346
- "self": 64.3202146309971,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 144.53038523000322,
350
- "count": 4584,
351
  "is_parallel": true,
352
- "self": 144.53038523000322
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.0782632629999398,
364
  "count": 1,
365
- "self": 0.0011008479999645715,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.07716241499997523,
369
  "count": 1,
370
- "self": 0.07716241499997523
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.7051005959510803,
6
+ "min": 0.7031011581420898,
7
+ "max": 2.862201690673828,
8
+ "count": 40
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 7158.88623046875,
12
+ "min": 6790.55078125,
13
+ "max": 29532.197265625,
14
+ "count": 40
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 399992.0,
18
  "min": 9952.0,
19
+ "max": 399992.0,
20
+ "count": 40
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 399992.0,
24
  "min": 9952.0,
25
+ "max": 399992.0,
26
+ "count": 40
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.540824890136719,
30
+ "min": 0.35199105739593506,
31
+ "max": 13.561790466308594,
32
+ "count": 40
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2640.4609375,
36
+ "min": 68.28626251220703,
37
+ "max": 2780.1669921875,
38
+ "count": 40
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 40
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 8756.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.06690554917012753,
54
+ "min": 0.06088974203117757,
55
+ "max": 0.07555335789505739,
56
+ "count": 40
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.2676221966805101,
60
+ "min": 0.25626725806653794,
61
+ "max": 0.37144413653361114,
62
+ "count": 40
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.19295535842869796,
66
+ "min": 0.13255297954139464,
67
+ "max": 0.27097845048296687,
68
+ "count": 40
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.7718214337147918,
72
+ "min": 0.5302119181655786,
73
+ "max": 1.3548922524148344,
74
+ "count": 40
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 3.891098702999994e-06,
78
+ "min": 3.891098702999994e-06,
79
+ "max": 0.000295941001353,
80
+ "count": 40
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 1.5564394811999976e-05,
84
+ "min": 1.5564394811999976e-05,
85
+ "max": 0.0014425800191399996,
86
+ "count": 40
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.101297,
90
+ "min": 0.101297,
91
+ "max": 0.19864700000000002,
92
+ "count": 40
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.405188,
96
+ "min": 0.405188,
97
+ "max": 0.98086,
98
+ "count": 40
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 7.472029999999992e-05,
102
+ "min": 7.472029999999992e-05,
103
+ "max": 0.004932485299999999,
104
+ "count": 40
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.00029888119999999966,
108
+ "min": 0.00029888119999999966,
109
+ "max": 0.024044914,
110
+ "count": 40
111
+ },
112
+ "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 26.636363636363637,
114
+ "min": 3.477272727272727,
115
+ "max": 26.954545454545453,
116
+ "count": 40
117
+ },
118
+ "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1172.0,
120
+ "min": 153.0,
121
+ "max": 1473.0,
122
+ "count": 40
123
+ },
124
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 26.636363636363637,
126
+ "min": 3.477272727272727,
127
+ "max": 26.954545454545453,
128
+ "count": 40
129
+ },
130
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1172.0,
132
+ "min": 153.0,
133
+ "max": 1473.0,
134
+ "count": 40
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 40
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 40
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1725453952",
152
  "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]",
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": "1.1.0.dev0",
155
  "mlagents_envs_version": "1.1.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.4.0+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1725454944"
160
  },
161
+ "total": 991.4360582860002,
162
  "count": 1,
163
+ "self": 0.8433071760002804,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.09433208999985254,
167
  "count": 1,
168
+ "self": 0.09433208999985254
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 990.49841902,
172
  "count": 1,
173
+ "self": 1.404796138976053,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.063632901000119,
177
  "count": 1,
178
+ "self": 2.063632901000119
179
  },
180
  "TrainerController.advance": {
181
+ "total": 986.8909946010235,
182
+ "count": 36400,
183
+ "self": 0.666640316047733,
184
  "children": {
185
  "env_step": {
186
+ "total": 986.2243542849758,
187
+ "count": 36400,
188
+ "self": 762.5765003389361,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 222.96883892899564,
192
+ "count": 36400,
193
+ "self": 3.2384945550181783,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 219.73034437397746,
197
+ "count": 36400,
198
+ "self": 219.73034437397746
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.6790150170440938,
204
+ "count": 36400,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 987.6894136619951,
209
+ "count": 36400,
210
  "is_parallel": true,
211
+ "self": 465.6858180239751,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0034341000000495114,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0009449889992083627,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0024891110008411488,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0024891110008411488
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.041506202999926245,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0007951229997615883,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.000439310000047044,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.000439310000047044
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03784137100001317,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03784137100001317
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.002430399000104444,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0004391139998460858,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.001991285000258358,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.001991285000258358
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 522.00359563802,
271
+ "count": 36399,
272
  "is_parallel": true,
273
+ "self": 23.61631140800364,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 12.593769466023787,
277
+ "count": 36399,
278
  "is_parallel": true,
279
+ "self": 12.593769466023787
280
  },
281
  "communicator.exchange": {
282
+ "total": 407.76271768503784,
283
+ "count": 36399,
284
  "is_parallel": true,
285
+ "self": 407.76271768503784
286
  },
287
  "steps_from_proto": {
288
+ "total": 78.03079707895472,
289
+ "count": 36399,
290
  "is_parallel": true,
291
+ "self": 15.079791963075877,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 62.95100511587884,
295
+ "count": 363990,
296
  "is_parallel": true,
297
+ "self": 62.95100511587884
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.0003482560000520607,
313
  "count": 1,
314
+ "self": 0.0003482560000520607,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 975.9914055799559,
324
+ "count": 1260681,
325
  "is_parallel": true,
326
+ "self": 27.35761915393823,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 517.4998755560196,
330
+ "count": 1260681,
331
  "is_parallel": true,
332
+ "self": 515.6441714610194,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 1.855704095000192,
336
+ "count": 8,
337
  "is_parallel": true,
338
+ "self": 1.855704095000192
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 431.1339108699981,
344
+ "count": 181,
345
  "is_parallel": true,
346
+ "self": 129.55837340199787,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 301.5755374680002,
350
+ "count": 9228,
351
  "is_parallel": true,
352
+ "self": 301.5755374680002
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.1386471230002826,
364
  "count": 1,
365
+ "self": 0.002383123000527121,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.13626399999975547,
369
  "count": 1,
370
+ "self": 0.13626399999975547
371
  }
372
  }
373
  }
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": 13.545454545454545,
8
- "creation_time": 1725452962.154112,
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": 20.90909090909091,
17
- "creation_time": 1725453083.0662804,
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": 24.636363636363637,
26
- "creation_time": 1725453205.104856,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
@@ -31,29 +31,65 @@
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 25.09090909090909,
35
- "creation_time": 1725453324.2524164,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
- "steps": 200112,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 25.09090909090909,
44
- "creation_time": 1725453324.3552895,
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
- "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 25.09090909090909,
54
- "creation_time": 1725453324.3552895,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 11.272727272727273,
8
+ "creation_time": 1725454080.306992,
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": 22.0,
17
+ "creation_time": 1725454201.3960943,
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": 24.727272727272727,
26
+ "creation_time": 1725454324.3688273,
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": 26.636363636363637,
35
+ "creation_time": 1725454448.688427,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 249944,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.onnx",
43
+ "reward": 27.363636363636363,
44
+ "creation_time": 1725454571.6488328,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 299968,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
52
+ "reward": 26.454545454545453,
53
+ "creation_time": 1725454697.1671412,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 349992,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.onnx",
61
+ "reward": 27.181818181818183,
62
+ "creation_time": 1725454822.4348087,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 399992,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.onnx",
70
+ "reward": 26.454545454545453,
71
+ "creation_time": 1725454943.2144022,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 400312,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-400312.onnx",
79
+ "reward": 26.454545454545453,
80
+ "creation_time": 1725454943.4117699,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-400312.pt"
83
  ]
84
  }
85
  ],
86
  "final_checkpoint": {
87
+ "steps": 400312,
88
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
89
+ "reward": 26.454545454545453,
90
+ "creation_time": 1725454943.4117699,
91
  "auxillary_file_paths": [
92
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-400312.pt"
93
  ]
94
  }
95
  },