Hugging Face's logo

NBKi
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
NBKi commited on
Commit
154551d
·
verified ·
1 Parent(s): c08f793

Second Push

Browse files
Files changed (28) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-1599976.onnx +3 -0
  3. SnowballTarget/SnowballTarget-1599976.pt +3 -0
  4. SnowballTarget/SnowballTarget-1649992.onnx +3 -0
  5. SnowballTarget/SnowballTarget-1649992.pt +3 -0
  6. SnowballTarget/SnowballTarget-1699936.onnx +3 -0
  7. SnowballTarget/SnowballTarget-1699936.pt +3 -0
  8. SnowballTarget/SnowballTarget-1749960.onnx +3 -0
  9. SnowballTarget/SnowballTarget-1749960.pt +3 -0
  10. SnowballTarget/SnowballTarget-1799984.onnx +3 -0
  11. SnowballTarget/SnowballTarget-1799984.pt +3 -0
  12. SnowballTarget/SnowballTarget-1849984.onnx +3 -0
  13. SnowballTarget/SnowballTarget-1849984.pt +3 -0
  14. SnowballTarget/SnowballTarget-1899944.onnx +3 -0
  15. SnowballTarget/SnowballTarget-1899944.pt +3 -0
  16. SnowballTarget/SnowballTarget-1949968.onnx +3 -0
  17. SnowballTarget/SnowballTarget-1949968.pt +3 -0
  18. SnowballTarget/SnowballTarget-1999992.onnx +3 -0
  19. SnowballTarget/SnowballTarget-1999992.pt +3 -0
  20. SnowballTarget/SnowballTarget-2000504.onnx +3 -0
  21. SnowballTarget/SnowballTarget-2000504.pt +3 -0
  22. SnowballTarget/checkpoint.pt +1 -1
  23. SnowballTarget/events.out.tfevents.1735587284.9abb403de233.31265.0 +3 -0
  24. config.json +1 -1
  25. configuration.yaml +1 -1
  26. run_logs/Player-0.log +16 -19
  27. run_logs/timers.json +161 -161
  28. run_logs/training_status.json +74 -29
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d2a3af1a7feb041fefa4bad92179f32818d13b10a9f5780649e62fa88cccadf
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76d33f36cffb3809b9f955756e0547cd585f78eb8269fed5b10106053a760244
3
  size 650646
SnowballTarget/SnowballTarget-1599976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24e3a934224964b60f07e9dc9affb41ff07e49736978606f7e09bbf6fc9885a4
3
+ size 650646
SnowballTarget/SnowballTarget-1599976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1ab33d198a6f0e25d288fae4917e98c6d5a52514f3fb5f0446658f3b8556552
3
+ size 3849254
SnowballTarget/SnowballTarget-1649992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc51e14fc7e8d32f3c87339a52da0801595600e2962cf103b2afa0e1900a4d35
3
+ size 650646
SnowballTarget/SnowballTarget-1649992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:951f361d58a5adbabe022498c2b0daeb9c66f38c4311b760cd790621d42e2d04
3
+ size 3849254
SnowballTarget/SnowballTarget-1699936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c54f7842a5b20e4e197d0697790949ae2e14dce8b2fc017f86d224bfeaba9bf
3
+ size 650646
SnowballTarget/SnowballTarget-1699936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cef6e3fbb5ae6c6f64fd437a387ffeca14cc232e1700e26e1f0d443a8c4750e6
3
+ size 3849254
SnowballTarget/SnowballTarget-1749960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76eecc0c3f5f3c149cca8ab2b60640295dd4ed391069dbaf534b1d272d2b821b
3
+ size 650646
SnowballTarget/SnowballTarget-1749960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2e1e6c7bf62c4a32053aa241c2b940f25d2893bd8091fdbb377b6cfddac5689
3
+ size 3849254
SnowballTarget/SnowballTarget-1799984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5927b3645b4963a1f0c431b4ccc73bb98407d7b38dbb256333926a9bde75c3f5
3
+ size 650646
SnowballTarget/SnowballTarget-1799984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aecabff1cf798b0289df1a534c74ceb908346044f66b13b2fc5c01101fd0ab7b
3
+ size 3849254
SnowballTarget/SnowballTarget-1849984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5de1501b8eef9267054fd8de8245f797589ff6054c2bf03b79c5afd69357a0f1
3
+ size 650646
SnowballTarget/SnowballTarget-1849984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b5deb9051b860be3d6fdbd6c1bce9d9eb80b726af28556e197b16df19b11996
3
+ size 3849254
SnowballTarget/SnowballTarget-1899944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f29827144a3a204658de64a46fcced440a01797e9c0535b9b133021c7d42eee
3
+ size 650646
SnowballTarget/SnowballTarget-1899944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cf2cdad6993a547156a54b807df495f6dd2df8f9b40e7f6ca437700862a4177
3
+ size 3849254
SnowballTarget/SnowballTarget-1949968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a915737b73cbe65c731817ab4d8ffc94d9c9f978f5ba1b7b1323975f4d30d7a0
3
+ size 650646
SnowballTarget/SnowballTarget-1949968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d9824e2a7cb0e1fdee60031c6157096a2c829e2b2850bd5c026eb60ad8ab32a
3
+ size 3849254
SnowballTarget/SnowballTarget-1999992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76d33f36cffb3809b9f955756e0547cd585f78eb8269fed5b10106053a760244
3
+ size 650646
SnowballTarget/SnowballTarget-1999992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd8fd07621c283f9aa9df6b28ce0126c6f602770f652f32e90a41e08c37f2563
3
+ size 3849254
SnowballTarget/SnowballTarget-2000504.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76d33f36cffb3809b9f955756e0547cd585f78eb8269fed5b10106053a760244
3
+ size 650646
SnowballTarget/SnowballTarget-2000504.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87898126f4c3b58a9c5159ed2f139dcd838e154841a013dc469e97b4d63486af
3
+ size 3849254
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb634707ee363563004ae374633ce10af7de6732bc814a029cb17568a1f4cdac
3
  size 3848290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4220a2ed8b5872c138b656631317c3bd0de19b1c8e77f855b792a843119831b
3
  size 3848290
SnowballTarget/events.out.tfevents.1735587284.9abb403de233.31265.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e9ded3a2f58b34acb8203aa3cd95c376ef246be8efdbdc3594377022b1b0a8b
3
+ size 184257
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 16384, "learning_rate": 0.00015, "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": 0.995, "strength": 0.1, "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": 16384, "learning_rate": 0.00015, "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": 0.995, "strength": 0.1, "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": 2000000, "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}
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
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 2000000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
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 0.203 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: 1.241425 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 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]: 5462 frames
179
  Requested Block Size 16.0 MB
180
- Peak Block count 1
181
- Peak Allocated memory 6.7 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 17.7 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]: 4298 frames, [64.0 KB-128.0 KB]: 1164 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 66.8 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 0.174 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: 1.066894 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]: 53652 frames, [16.0 KB-32.0 KB]: 909 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 38
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]: 14180 frames, [8.0 MB-16.0 MB]: 28435 frames, [16.0 MB-32.0 MB]: 11947 frames
176
  Requested Block Size 16.0 MB
177
+ Peak Block count 2
178
+ Peak Allocated memory 24.1 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 54562 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.8 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]: 52357 frames, [64.0 KB-128.0 KB]: 2205 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 66.4 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 54562 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]: 54562 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]: 54561 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]: 54562 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]: 54562 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
@@ -2,153 +2,153 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 2.4771385192871094,
6
- "min": 2.4771385192871094,
7
- "max": 2.890329122543335,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 23733.46484375,
12
- "min": 23733.46484375,
13
- "max": 29758.828125,
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": 0.3181571066379547,
30
- "min": -0.11466383934020996,
31
- "max": 0.3181571066379547,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 62.04063415527344,
36
- "min": -22.48594856262207,
37
- "max": 62.04063415527344,
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": 10.590909090909092,
54
- "min": 1.7045454545454546,
55
- "max": 10.590909090909092,
56
- "count": 20
57
  },
58
  "SnowballTarget.Environment.CumulativeReward.sum": {
59
- "value": 466.0,
60
- "min": 75.0,
61
- "max": 560.0,
62
- "count": 20
63
  },
64
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
- "value": 1.0590909335084937,
66
- "min": 0.17045454867184162,
67
- "max": 1.0590909335084937,
68
- "count": 20
69
  },
70
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
- "value": 46.60000107437372,
72
- "min": 7.500000141561031,
73
- "max": 56.00000114738941,
74
- "count": 20
75
  },
76
  "SnowballTarget.IsTraining.mean": {
77
  "value": 1.0,
78
  "min": 1.0,
79
  "max": 1.0,
80
- "count": 20
81
  },
82
  "SnowballTarget.IsTraining.sum": {
83
  "value": 1.0,
84
  "min": 1.0,
85
  "max": 1.0,
86
- "count": 20
87
  },
88
  "SnowballTarget.Losses.PolicyLoss.mean": {
89
- "value": 0.07117141246668655,
90
- "min": 0.06662335806572454,
91
- "max": 0.07320026658725262,
92
- "count": 11
93
  },
94
  "SnowballTarget.Losses.PolicyLoss.sum": {
95
- "value": 0.07117141246668655,
96
- "min": 0.06662335806572454,
97
- "max": 0.07320026658725262,
98
- "count": 11
99
  },
100
  "SnowballTarget.Losses.ValueLoss.mean": {
101
- "value": 0.003100606662543453,
102
- "min": 0.0007912670892370633,
103
- "max": 0.003100606662543453,
104
- "count": 11
105
  },
106
  "SnowballTarget.Losses.ValueLoss.sum": {
107
- "value": 0.003100606662543453,
108
- "min": 0.0007912670892370633,
109
- "max": 0.003100606662543453,
110
- "count": 11
111
  },
112
  "SnowballTarget.Policy.LearningRate.mean": {
113
- "value": 1.0872092752e-05,
114
- "min": 1.0872092752e-05,
115
- "max": 0.000137394008404,
116
- "count": 11
117
  },
118
  "SnowballTarget.Policy.LearningRate.sum": {
119
- "value": 1.0872092752e-05,
120
- "min": 1.0872092752e-05,
121
- "max": 0.000137394008404,
122
- "count": 11
123
  },
124
  "SnowballTarget.Policy.Epsilon.mean": {
125
- "value": 0.10724800000000001,
126
- "min": 0.10724800000000001,
127
- "max": 0.19159600000000004,
128
- "count": 11
129
  },
130
  "SnowballTarget.Policy.Epsilon.sum": {
131
- "value": 0.10724800000000001,
132
- "min": 0.10724800000000001,
133
- "max": 0.19159600000000004,
134
- "count": 11
135
  },
136
  "SnowballTarget.Policy.Beta.mean": {
137
- "value": 0.00037167520000000004,
138
- "min": 0.00037167520000000004,
139
- "max": 0.004580640400000001,
140
- "count": 11
141
  },
142
  "SnowballTarget.Policy.Beta.sum": {
143
- "value": 0.00037167520000000004,
144
- "min": 0.00037167520000000004,
145
- "max": 0.004580640400000001,
146
- "count": 11
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1735586193",
152
  "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0",
@@ -156,59 +156,59 @@
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.5.1+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1735586842"
160
  },
161
- "total": 649.008088224,
162
  "count": 1,
163
- "self": 0.6528435009986424,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.12207272200066654,
167
  "count": 1,
168
- "self": 0.12207272200066654
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 648.2331720010006,
172
  "count": 1,
173
- "self": 0.8721127570024692,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 7.783921408999959,
177
  "count": 1,
178
- "self": 7.783921408999959
179
  },
180
  "TrainerController.advance": {
181
- "total": 639.4747533359987,
182
- "count": 18204,
183
- "self": 0.44850319998204213,
184
  "children": {
185
  "env_step": {
186
- "total": 639.0262501360166,
187
- "count": 18204,
188
- "self": 508.85246015394387,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 129.73698221701216,
192
- "count": 18204,
193
- "self": 2.5454235019506086,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 127.19155871506155,
197
- "count": 18204,
198
- "self": 127.19155871506155
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.436807765060621,
204
- "count": 18204,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 646.178916808025,
209
- "count": 18204,
210
  "is_parallel": true,
211
- "self": 328.287299311045,
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": 0.0038180170004125102,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0010995310012731352,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.002718485999139375,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.002718485999139375
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.0963127209997765,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0010946109987344244,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00044590700053959154,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00044590700053959154
244
  },
245
  "communicator.exchange": {
246
- "total": 0.09151514699988184,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.09151514699988184
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0032570560006206506,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0005833000013808487,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.002673755999239802,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.002673755999239802
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 317.89161749697996,
271
- "count": 18203,
272
  "is_parallel": true,
273
- "self": 15.742080203000114,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 7.819314688924351,
277
- "count": 18203,
278
  "is_parallel": true,
279
- "self": 7.819314688924351
280
  },
281
  "communicator.exchange": {
282
- "total": 248.9399362570839,
283
- "count": 18203,
284
  "is_parallel": true,
285
- "self": 248.9399362570839
286
  },
287
  "steps_from_proto": {
288
- "total": 45.390286347971596,
289
- "count": 18203,
290
  "is_parallel": true,
291
- "self": 8.745531815848153,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 36.64475453212344,
295
- "count": 182030,
296
  "is_parallel": true,
297
- "self": 36.64475453212344
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00023684699954173993,
313
  "count": 1,
314
- "self": 0.00023684699954173993,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 628.2859272532469,
324
- "count": 1204247,
325
  "is_parallel": true,
326
- "self": 27.669322973758426,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 439.56680371448965,
330
- "count": 1204247,
331
  "is_parallel": true,
332
- "self": 438.7991688834909,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 0.7676348309987588,
336
- "count": 4,
337
  "is_parallel": true,
338
- "self": 0.7676348309987588
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 161.0498005649988,
344
- "count": 11,
345
  "is_parallel": true,
346
- "self": 62.65300950596429,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 98.39679105903451,
350
- "count": 4344,
351
  "is_parallel": true,
352
- "self": 98.39679105903451
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.1021476519999851,
364
  "count": 1,
365
- "self": 0.002203349000410526,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.09994430299957457,
369
  "count": 1,
370
- "self": 0.09994430299957457
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.7335434556007385,
6
+ "min": 0.7335434556007385,
7
+ "max": 2.8903188705444336,
8
+ "count": 200
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 7512.21826171875,
12
+ "min": 6999.51611328125,
13
+ "max": 29917.69140625,
14
+ "count": 200
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 1999992.0,
18
  "min": 9952.0,
19
+ "max": 1999992.0,
20
+ "count": 200
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 1999992.0,
24
  "min": 9952.0,
25
+ "max": 1999992.0,
26
+ "count": 200
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 2.804928779602051,
30
+ "min": -0.0671207457780838,
31
+ "max": 2.804928779602051,
32
+ "count": 200
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 575.0103759765625,
36
+ "min": -13.021425247192383,
37
+ "max": 575.0103759765625,
38
+ "count": 200
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 200
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 10945.0,
48
  "min": 8756.0,
49
+ "max": 11343.0,
50
+ "count": 200
51
  },
52
  "SnowballTarget.Environment.CumulativeReward.mean": {
53
+ "value": 27.87272727272727,
54
+ "min": 2.3863636363636362,
55
+ "max": 28.2,
56
+ "count": 200
57
  },
58
  "SnowballTarget.Environment.CumulativeReward.sum": {
59
+ "value": 1533.0,
60
+ "min": 105.0,
61
+ "max": 1551.0,
62
+ "count": 200
63
  },
64
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
+ "value": 2.787272757156329,
66
+ "min": 0.23863636803897945,
67
+ "max": 2.8200000217015093,
68
+ "count": 200
69
  },
70
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
+ "value": 153.30000164359808,
72
+ "min": 10.500000193715096,
73
+ "max": 155.100001193583,
74
+ "count": 200
75
  },
76
  "SnowballTarget.IsTraining.mean": {
77
  "value": 1.0,
78
  "min": 1.0,
79
  "max": 1.0,
80
+ "count": 200
81
  },
82
  "SnowballTarget.IsTraining.sum": {
83
  "value": 1.0,
84
  "min": 1.0,
85
  "max": 1.0,
86
+ "count": 200
87
  },
88
  "SnowballTarget.Losses.PolicyLoss.mean": {
89
+ "value": 0.06807530643518384,
90
+ "min": 0.06400337870404274,
91
+ "max": 0.07612948228112752,
92
+ "count": 118
93
  },
94
  "SnowballTarget.Losses.PolicyLoss.sum": {
95
+ "value": 0.06807530643518384,
96
+ "min": 0.06400337870404274,
97
+ "max": 0.07612948228112752,
98
+ "count": 118
99
  },
100
  "SnowballTarget.Losses.ValueLoss.mean": {
101
+ "value": 0.0016766203549159033,
102
+ "min": 0.0012503485261483795,
103
+ "max": 0.003760265681120086,
104
+ "count": 118
105
  },
106
  "SnowballTarget.Losses.ValueLoss.sum": {
107
+ "value": 0.0016766203549159033,
108
+ "min": 0.0012503485261483795,
109
+ "max": 0.003760265681120086,
110
+ "count": 118
111
  },
112
  "SnowballTarget.Policy.LearningRate.mean": {
113
+ "value": 1.0644992903999983e-06,
114
+ "min": 1.0644992903999983e-06,
115
+ "max": 0.00014873940084040002,
116
+ "count": 118
117
  },
118
  "SnowballTarget.Policy.LearningRate.sum": {
119
+ "value": 1.0644992903999983e-06,
120
+ "min": 1.0644992903999983e-06,
121
+ "max": 0.00014873940084040002,
122
+ "count": 118
123
  },
124
  "SnowballTarget.Policy.Epsilon.mean": {
125
+ "value": 0.10070960000000005,
126
+ "min": 0.10070960000000005,
127
+ "max": 0.19915960000000002,
128
+ "count": 118
129
  },
130
  "SnowballTarget.Policy.Epsilon.sum": {
131
+ "value": 0.10070960000000005,
132
+ "min": 0.10070960000000005,
133
+ "max": 0.19915960000000002,
134
+ "count": 118
135
  },
136
  "SnowballTarget.Policy.Beta.mean": {
137
+ "value": 4.5409039999999954e-05,
138
+ "min": 4.5409039999999954e-05,
139
+ "max": 0.004958064040000001,
140
+ "count": 118
141
  },
142
  "SnowballTarget.Policy.Beta.sum": {
143
+ "value": 4.5409039999999954e-05,
144
+ "min": 4.5409039999999954e-05,
145
+ "max": 0.004958064040000001,
146
+ "count": 118
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1735587283",
152
  "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0",
 
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.5.1+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1735593713"
160
  },
161
+ "total": 6430.14934202,
162
  "count": 1,
163
+ "self": 1.1948224280013164,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.11315851000017574,
167
  "count": 1,
168
+ "self": 0.11315851000017574
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 6428.841361081999,
172
  "count": 1,
173
+ "self": 8.99585830144406,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.3011489050004457,
177
  "count": 1,
178
+ "self": 3.3011489050004457
179
  },
180
  "TrainerController.advance": {
181
+ "total": 6416.401148671554,
182
+ "count": 181872,
183
+ "self": 4.145781111599717,
184
  "children": {
185
  "env_step": {
186
+ "total": 6412.255367559955,
187
+ "count": 181872,
188
+ "self": 5112.956623629537,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 1295.060977182069,
192
+ "count": 181872,
193
+ "self": 24.128962340185353,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 1270.9320148418838,
197
+ "count": 181872,
198
+ "self": 1270.9320148418838
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 4.237766748348804,
204
+ "count": 181872,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 6409.453978358057,
209
+ "count": 181872,
210
  "is_parallel": true,
211
+ "self": 3285.7820006785623,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.005012800999793399,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.00137477699900046,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0036380240007929388,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0036380240007929388
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.04326236700035224,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0008554580008421908,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004659260002881638,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004659260002881638
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03892191699924297,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03892191699924297
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0030190659999789204,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00048076099938043626,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.002538305000598484,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.002538305000598484
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 3123.6719776794944,
271
+ "count": 181871,
272
  "is_parallel": true,
273
+ "self": 150.9198243530318,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 76.59267247502885,
277
+ "count": 181871,
278
  "is_parallel": true,
279
+ "self": 76.59267247502885
280
  },
281
  "communicator.exchange": {
282
+ "total": 2449.197534630912,
283
+ "count": 181871,
284
  "is_parallel": true,
285
+ "self": 2449.197534630912
286
  },
287
  "steps_from_proto": {
288
+ "total": 446.9619462205219,
289
+ "count": 181871,
290
  "is_parallel": true,
291
+ "self": 87.61080271079481,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 359.3511435097271,
295
+ "count": 1818710,
296
  "is_parallel": true,
297
+ "self": 359.3511435097271
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.0005380050006351667,
313
  "count": 1,
314
+ "self": 0.0005380050006351667,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 6309.161478470472,
324
+ "count": 11826943,
325
  "is_parallel": true,
326
+ "self": 274.49397868472533,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 4280.637665592756,
330
+ "count": 11826943,
331
  "is_parallel": true,
332
+ "self": 4273.37227616075,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 7.2653894320064865,
336
+ "count": 40,
337
  "is_parallel": true,
338
+ "self": 7.2653894320064865
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 1754.0298341929902,
344
+ "count": 118,
345
  "is_parallel": true,
346
+ "self": 640.3592346847399,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 1113.6705995082502,
350
+ "count": 46491,
351
  "is_parallel": true,
352
+ "self": 1113.6705995082502
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.14266719899933378,
364
  "count": 1,
365
+ "self": 0.001825680998081225,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.14084151800125255,
369
  "count": 1,
370
+ "self": 0.14084151800125255
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -2,58 +2,103 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 1.9090909090909092,
8
- "creation_time": 1735586353.2822528,
9
  "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
12
  },
13
  {
14
- "steps": 99960,
15
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 4.766233766233766,
17
- "creation_time": 1735586517.0345619,
18
  "auxillary_file_paths": [
19
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
21
  },
22
  {
23
- "steps": 149984,
24
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 8.753246753246753,
26
- "creation_time": 1735586678.7499735,
27
  "auxillary_file_paths": [
28
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
30
  },
31
  {
32
- "steps": 199984,
33
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 10.318181818181818,
35
- "creation_time": 1735586841.362898,
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": 10.318181818181818,
44
- "creation_time": 1735586841.5024064,
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": 10.318181818181818,
54
- "creation_time": 1735586841.5024064,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 1599976,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1599976.onnx",
7
+ "reward": 27.454545454545453,
8
+ "creation_time": 1735592434.788186,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-1599976.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 1649992,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1649992.onnx",
16
+ "reward": 26.0,
17
+ "creation_time": 1735592594.0301185,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-1649992.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 1699936,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1699936.onnx",
25
+ "reward": null,
26
+ "creation_time": 1735592755.244557,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-1699936.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 1749960,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1749960.onnx",
34
+ "reward": null,
35
+ "creation_time": 1735592916.4644635,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-1749960.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 1799984,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1799984.onnx",
43
+ "reward": 27.431818181818183,
44
+ "creation_time": 1735593064.590253,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-1799984.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 1849984,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1849984.onnx",
52
+ "reward": 27.272727272727273,
53
+ "creation_time": 1735593225.261539,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-1849984.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 1899944,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1899944.onnx",
61
+ "reward": 27.805194805194805,
62
+ "creation_time": 1735593385.2985065,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-1899944.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 1949968,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1949968.onnx",
70
+ "reward": 27.87012987012987,
71
+ "creation_time": 1735593549.0564017,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-1949968.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 1999992,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1999992.onnx",
79
+ "reward": 27.883116883116884,
80
+ "creation_time": 1735593711.860443,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-1999992.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 2000504,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-2000504.onnx",
88
+ "reward": 27.883116883116884,
89
+ "creation_time": 1735593712.1155138,
90
+ "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-2000504.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 2000504,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 27.883116883116884,
99
+ "creation_time": 1735593712.1155138,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-2000504.pt"
102
  ]
103
  }
104
  },