Hugging Face's logo

Cesar514
/
SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
unity-ml-agents
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
Cesar514 commited on
Commit
5f42dfc
·
1 Parent(s): 8cefb11

Push

Browse files
Files changed (28) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-109912.onnx +3 -0
  3. SnowballTarget/SnowballTarget-109912.pt +3 -0
  4. SnowballTarget/SnowballTarget-19992.onnx +3 -0
  5. SnowballTarget/SnowballTarget-19992.pt +3 -0
  6. SnowballTarget/SnowballTarget-29944.onnx +3 -0
  7. SnowballTarget/SnowballTarget-29944.pt +3 -0
  8. SnowballTarget/SnowballTarget-39984.onnx +3 -0
  9. SnowballTarget/SnowballTarget-39984.pt +3 -0
  10. SnowballTarget/SnowballTarget-49936.onnx +3 -0
  11. SnowballTarget/SnowballTarget-49936.pt +3 -0
  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 +2 -2
  23. SnowballTarget/{events.out.tfevents.1677690909.a453ba9e88e3.2313.0 → events.out.tfevents.1677691191.a453ba9e88e3.3777.0} +2 -2
  24. config.json +1 -1
  25. configuration.yaml +2 -2
  26. run_logs/Player-0.log +13 -17
  27. run_logs/timers.json +162 -154
  28. run_logs/training_status.json +90 -9
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b7b09723c061888c21f9f03d9c902d2e2d7f48e1aa7851e08f585d2d1ee6bfa
3
  size 645119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87ceef4d230bcfd71a8a54317a084c1aced9f1529b1259afcbb47b3cbda582a1
3
  size 645119
SnowballTarget/SnowballTarget-109912.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87ceef4d230bcfd71a8a54317a084c1aced9f1529b1259afcbb47b3cbda582a1
3
+ size 645119
SnowballTarget/SnowballTarget-109912.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06db5b0d8de7eb8a05db9a2b636919641c025b2ada4bf9469d8e0589b8898a18
3
+ size 3845587
SnowballTarget/SnowballTarget-19992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e828916f36fc68d3f621d82ef80ff6e8836f8002cebe56daae7f1597011a58eb
3
+ size 645119
SnowballTarget/SnowballTarget-19992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af71785aa866682da164cbf54e3af3e61e84888e5ba96fa17d9dd62bd69dd4b7
3
+ size 3845587
SnowballTarget/SnowballTarget-29944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfa35d4a28e48bb38cc243d510a0ad05d478d47d9a17562ab4738cc58bfb62d5
3
+ size 645119
SnowballTarget/SnowballTarget-29944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6c959a38f0d0c5a7c69e935599ac09a11e676ddeb3be68864c2f5bd161ad4bb
3
+ size 3845587
SnowballTarget/SnowballTarget-39984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9f9153286500087fa16d26707b9c8ed2944c231c26af14f26ab0b4c53dcb557
3
+ size 645119
SnowballTarget/SnowballTarget-39984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82b4840ddbf1a729e5f89a700eacc0c75f51972a38c48f96ab4f8e393910a9ac
3
+ size 3845587
SnowballTarget/SnowballTarget-49936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d73d88eec0f8a858f9ac3ed9b1242f2b02df0aa882af23ab8f2ad26c6b35bb46
3
+ size 645119
SnowballTarget/SnowballTarget-49936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0864bdbb855027ed6853b05328bdd9a9325ae80ae6c1c694aba7b2c06fdf262
3
+ size 3845587
SnowballTarget/SnowballTarget-59976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6ce56597e397a366c3b647797964d9c56af8ab1c7d4efb43572d76d051aacd0
3
+ size 645119
SnowballTarget/SnowballTarget-59976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a00c1a5f3d331eb6effa0b96b8118015e23efef92d92120f82e0c265860af949
3
+ size 3845587
SnowballTarget/SnowballTarget-69992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:090cae1a41842c03c46b723617f7c41bc8eddd772851da112bd58cda94352424
3
+ size 645119
SnowballTarget/SnowballTarget-69992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b786a81a4c5e7aaee5d366d2bea0aab9809477df38cd5dde7b58cb9f9c3a553
3
+ size 3845587
SnowballTarget/SnowballTarget-79968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e91c5045a346bb0b328e82112ecdb579e62cae3a828d7a140ea820915875a98c
3
+ size 645119
SnowballTarget/SnowballTarget-79968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d6d0b6f8f113989c0a6ed36c4c854096c0682704db94c52776a863928aaf99f
3
+ size 3845587
SnowballTarget/SnowballTarget-89984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d65517e15e879ba9d6f33a5050321ffa1497fcc4ba9b908cb4c3dd02b2332550
3
+ size 645119
SnowballTarget/SnowballTarget-89984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e254bf448cfb4b6127a19112adc426cdab52a83b6160654fb26d60756e8d0c00
3
+ size 3845587
SnowballTarget/SnowballTarget-99960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57759ff763fdca345530e0ac9aa8a04b1ec0767a1d6621266ecfa41b36cf228b
3
+ size 645119
SnowballTarget/SnowballTarget-99960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f4aa7f3556c09fd0ad7216e6477c271ba7949766b4af82addcf0ee4439594c9
3
+ size 3845587
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d801471fa3aec9192978a2e4277ff0789c62d8185d1e75de1da34c93a1368a75
3
- size 3845592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06db5b0d8de7eb8a05db9a2b636919641c025b2ada4bf9469d8e0589b8898a18
3
+ size 3845587
SnowballTarget/{events.out.tfevents.1677690909.a453ba9e88e3.2313.0 → events.out.tfevents.1677691191.a453ba9e88e3.3777.0} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8885b4ebe459a4a7e4b7b8c272668f90dbe3e740c9bde9d4db23637ae5f1b401
3
- size 7925
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00608348f57a4cceb33625f77e403ad63ef78e8e64f522c064d3aaffc4b239a0
3
+ size 14965
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, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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": 0.95, "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, "checkpoint_interval": 50000, "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, "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}, "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, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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": 0.95, "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, "checkpoint_interval": 10000, "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, "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}, "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
@@ -35,7 +35,7 @@ behaviors:
35
  deterministic: false
36
  init_path: null
37
  keep_checkpoints: 10
38
- checkpoint_interval: 50000
39
  max_steps: 200000
40
  time_horizon: 64
41
  summary_freq: 10000
@@ -66,7 +66,7 @@ checkpoint_settings:
66
  initialize_from: null
67
  load_model: false
68
  resume: false
69
- force: false
70
  train_model: false
71
  inference: false
72
  results_dir: results
 
35
  deterministic: false
36
  init_path: null
37
  keep_checkpoints: 10
38
+ checkpoint_interval: 10000
39
  max_steps: 200000
40
  time_horizon: 64
41
  summary_freq: 10000
 
66
  initialize_from: null
67
  load_model: false
68
  resume: false
69
+ force: true
70
  train_model: false
71
  inference: false
72
  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:2642:(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 0.087 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)
@@ -45,16 +42,15 @@ 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: 0.761882 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
- GRPC Exception: Status(StatusCode=Cancelled, Detail="CANCELLED"). Disconnecting from trainer.
52
  Setting up 1 worker threads for Enlighten.
53
  Memory Statistics:
54
  [ALLOC_TEMP_TLS] TLS Allocator
55
  StackAllocators :
56
  [ALLOC_TEMP_MAIN]
57
- Peak usage frame count: [8.0 KB-16.0 KB]: 557 frames, [16.0 KB-32.0 KB]: 9 frames, [2.0 MB-4.0 MB]: 1 frames
58
  Initial Block Size 4.0 MB
59
  Current Block Size 4.0 MB
60
  Peak Allocated Bytes 2.0 MB
@@ -170,22 +166,22 @@ Memory Statistics:
170
  Peak Allocated Bytes 0 B
171
  Overflow Count 0
172
  [ALLOC_DEFAULT] Dual Thread Allocator
173
- Peak main deferred allocation count 39
174
  [ALLOC_BUCKET]
175
  Large Block size 4.0 MB
176
  Used Block count 1
177
  Peak Allocated bytes 1.0 MB
178
  [ALLOC_DEFAULT_MAIN]
179
- Peak usage frame count: [4.0 MB-8.0 MB]: 567 frames
180
  Requested Block Size 16.0 MB
181
  Peak Block count 1
182
  Peak Allocated memory 5.9 MB
183
  Peak Large allocation bytes 0 B
184
  [ALLOC_DEFAULT_THREAD]
185
- Peak usage frame count: [16.0 MB-32.0 MB]: 567 frames
186
  Requested Block Size 16.0 MB
187
  Peak Block count 1
188
- Peak Allocated memory 17.3 MB
189
  Peak Large allocation bytes 16.0 MB
190
  [ALLOC_TEMP_JOB_1_FRAME]
191
  Initial Block Size 2.0 MB
@@ -214,13 +210,13 @@ Memory Statistics:
214
  Used Block count 1
215
  Peak Allocated bytes 1.0 MB
216
  [ALLOC_GFX_MAIN]
217
- Peak usage frame count: [32.0 KB-64.0 KB]: 496 frames, [64.0 KB-128.0 KB]: 71 frames
218
  Requested Block Size 16.0 MB
219
  Peak Block count 1
220
  Peak Allocated memory 66.0 KB
221
  Peak Large allocation bytes 0 B
222
  [ALLOC_GFX_THREAD]
223
- Peak usage frame count: [32.0 KB-64.0 KB]: 567 frames
224
  Requested Block Size 16.0 MB
225
  Peak Block count 1
226
  Peak Allocated memory 39.6 KB
@@ -232,13 +228,13 @@ Memory Statistics:
232
  Used Block count 1
233
  Peak Allocated bytes 1.0 MB
234
  [ALLOC_CACHEOBJECTS_MAIN]
235
- Peak usage frame count: [0.5 MB-1.0 MB]: 567 frames
236
  Requested Block Size 4.0 MB
237
  Peak Block count 1
238
  Peak Allocated memory 0.6 MB
239
  Peak Large allocation bytes 0 B
240
  [ALLOC_CACHEOBJECTS_THREAD]
241
- Peak usage frame count: [0.5 MB-1.0 MB]: 566 frames, [2.0 MB-4.0 MB]: 1 frames
242
  Requested Block Size 4.0 MB
243
  Peak Block count 1
244
  Peak Allocated memory 2.2 MB
@@ -250,13 +246,13 @@ Memory Statistics:
250
  Used Block count 1
251
  Peak Allocated bytes 1.0 MB
252
  [ALLOC_TYPETREE_MAIN]
253
- Peak usage frame count: [0-1.0 KB]: 567 frames
254
  Requested Block Size 2.0 MB
255
  Peak Block count 1
256
  Peak Allocated memory 1.0 KB
257
  Peak Large allocation bytes 0 B
258
  [ALLOC_TYPETREE_THREAD]
259
- Peak usage frame count: [1.0 KB-2.0 KB]: 567 frames
260
  Requested Block Size 2.0 MB
261
  Peak Block count 1
262
  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 0.088 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: 0.665326 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.
49
  Memory Statistics:
50
  [ALLOC_TEMP_TLS] TLS Allocator
51
  StackAllocators :
52
  [ALLOC_TEMP_MAIN]
53
+ Peak usage frame count: [8.0 KB-16.0 KB]: 2964 frames, [16.0 KB-32.0 KB]: 50 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]: 3015 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
  Peak Allocated memory 5.9 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 3015 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]: 2620 frames, [64.0 KB-128.0 KB]: 395 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
  Peak Allocated memory 66.0 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 3015 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]: 3015 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]: 3014 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]: 3015 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]: 3015 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
@@ -2,220 +2,220 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 2.773995876312256,
6
- "min": 2.773995876312256,
7
- "max": 2.8692355155944824,
8
- "count": 2
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 28591.576171875,
12
- "min": 28591.576171875,
13
- "max": 29383.841796875,
14
- "count": 2
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 19992.0,
18
  "min": 9952.0,
19
- "max": 19992.0,
20
- "count": 2
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 19992.0,
24
  "min": 9952.0,
25
- "max": 19992.0,
26
- "count": 2
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 0.5726273655891418,
30
- "min": 0.147334024310112,
31
- "max": 0.5726273655891418,
32
- "count": 2
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 117.38861083984375,
36
- "min": 28.582801818847656,
37
- "max": 117.38861083984375,
38
- "count": 2
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
- "count": 2
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
- "count": 2
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06799672417566363,
54
- "min": 0.0635242219334531,
55
- "max": 0.06799672417566363,
56
- "count": 2
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.3399836208783181,
60
- "min": 0.2540968877338124,
61
- "max": 0.3399836208783181,
62
- "count": 2
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.10964079529923551,
66
- "min": 0.07155623769572497,
67
- "max": 0.10964079529923551,
68
- "count": 2
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.5482039764961776,
72
- "min": 0.2862249507828999,
73
- "max": 0.5482039764961776,
74
- "count": 2
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 0.000277032007656,
78
- "min": 0.000277032007656,
79
  "max": 0.000291882002706,
80
- "count": 2
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 0.00138516003828,
84
- "min": 0.001167528010824,
85
  "max": 0.00138516003828,
86
- "count": 2
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.19234400000000001,
90
- "min": 0.19234400000000001,
91
  "max": 0.19729400000000002,
92
- "count": 2
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.96172,
96
- "min": 0.7891760000000001,
97
  "max": 0.96172,
98
- "count": 2
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
- "value": 0.0046179656,
102
- "min": 0.0046179656,
103
  "max": 0.0048649706,
104
- "count": 2
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.023089828,
108
- "min": 0.0194598824,
109
  "max": 0.023089828,
110
- "count": 2
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 6.381818181818182,
114
- "min": 3.522727272727273,
115
- "max": 6.381818181818182,
116
- "count": 2
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 351.0,
120
- "min": 155.0,
121
- "max": 351.0,
122
- "count": 2
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 6.381818181818182,
126
- "min": 3.522727272727273,
127
- "max": 6.381818181818182,
128
- "count": 2
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 351.0,
132
- "min": 155.0,
133
- "max": 351.0,
134
- "count": 2
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 2
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 2
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1677690902",
152
  "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
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": "0.29.0.dev0",
155
  "mlagents_envs_version": "0.29.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.8.1+cu102",
158
  "numpy_version": "1.22.4",
159
- "end_time_seconds": "1677690959"
160
  },
161
- "total": 57.057522927000036,
162
  "count": 1,
163
- "self": 0.19455147500002568,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.12869011099996897,
167
  "count": 1,
168
- "self": 0.12869011099996897
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 56.73428134100004,
172
  "count": 1,
173
- "self": 0.05467043700139129,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 9.745152264000012,
177
  "count": 1,
178
- "self": 9.745152264000012
179
  },
180
  "TrainerController.advance": {
181
- "total": 46.69803345599871,
182
- "count": 1890,
183
- "self": 0.02846104999957788,
184
  "children": {
185
  "env_step": {
186
- "total": 46.66957240599913,
187
- "count": 1890,
188
- "self": 32.4225230240005,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 14.219574842000497,
192
- "count": 1890,
193
- "self": 0.15459914099926664,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 14.06497570100123,
197
- "count": 1890,
198
- "self": 3.197259389003875,
199
  "children": {
200
  "TorchPolicy.sample_actions": {
201
- "total": 10.867716311997356,
202
- "count": 1890,
203
- "self": 10.867716311997356
204
  }
205
  }
206
  }
207
  }
208
  },
209
  "workers": {
210
- "total": 0.027474539998138425,
211
- "count": 1889,
212
  "self": 0.0,
213
  "children": {
214
  "worker_root": {
215
- "total": 56.44349898399946,
216
- "count": 1889,
217
  "is_parallel": true,
218
- "self": 31.668323080998448,
219
  "children": {
220
  "run_training.setup": {
221
  "total": 0.0,
@@ -224,48 +224,48 @@
224
  "self": 0.0,
225
  "children": {
226
  "steps_from_proto": {
227
- "total": 0.005927119000034509,
228
  "count": 1,
229
  "is_parallel": true,
230
- "self": 0.0046233269999902404,
231
  "children": {
232
  "_process_rank_one_or_two_observation": {
233
- "total": 0.0013037920000442682,
234
  "count": 10,
235
  "is_parallel": true,
236
- "self": 0.0013037920000442682
237
  }
238
  }
239
  },
240
  "UnityEnvironment.step": {
241
- "total": 0.06998756699999831,
242
  "count": 1,
243
  "is_parallel": true,
244
- "self": 0.0006314280001333827,
245
  "children": {
246
  "UnityEnvironment._generate_step_input": {
247
- "total": 0.00036928599990915245,
248
  "count": 1,
249
  "is_parallel": true,
250
- "self": 0.00036928599990915245
251
  },
252
  "communicator.exchange": {
253
- "total": 0.06721094199997424,
254
  "count": 1,
255
  "is_parallel": true,
256
- "self": 0.06721094199997424
257
  },
258
  "steps_from_proto": {
259
- "total": 0.0017759109999815337,
260
  "count": 1,
261
  "is_parallel": true,
262
- "self": 0.0003889860000754197,
263
  "children": {
264
  "_process_rank_one_or_two_observation": {
265
- "total": 0.001386924999906114,
266
  "count": 10,
267
  "is_parallel": true,
268
- "self": 0.001386924999906114
269
  }
270
  }
271
  }
@@ -274,34 +274,34 @@
274
  }
275
  },
276
  "UnityEnvironment.step": {
277
- "total": 24.775175903001013,
278
- "count": 1888,
279
  "is_parallel": true,
280
- "self": 1.0005609239989326,
281
  "children": {
282
  "UnityEnvironment._generate_step_input": {
283
- "total": 0.5416260569996894,
284
- "count": 1888,
285
  "is_parallel": true,
286
- "self": 0.5416260569996894
287
  },
288
  "communicator.exchange": {
289
- "total": 20.084928497000647,
290
- "count": 1888,
291
  "is_parallel": true,
292
- "self": 20.084928497000647
293
  },
294
  "steps_from_proto": {
295
- "total": 3.148060425001745,
296
- "count": 1888,
297
  "is_parallel": true,
298
- "self": 0.6749315049964935,
299
  "children": {
300
  "_process_rank_one_or_two_observation": {
301
- "total": 2.4731289200052515,
302
- "count": 18880,
303
  "is_parallel": true,
304
- "self": 2.4731289200052515
305
  }
306
  }
307
  }
@@ -316,9 +316,9 @@
316
  }
317
  },
318
  "trainer_threads": {
319
- "total": 4.258399997070228e-05,
320
  "count": 1,
321
- "self": 4.258399997070228e-05,
322
  "children": {
323
  "thread_root": {
324
  "total": 0.0,
@@ -327,28 +327,36 @@
327
  "self": 0.0,
328
  "children": {
329
  "trainer_advance": {
330
- "total": 46.31070583801579,
331
- "count": 46739,
332
  "is_parallel": true,
333
- "self": 1.1014963490375749,
334
  "children": {
335
  "process_trajectory": {
336
- "total": 27.44743387197809,
337
- "count": 46739,
338
  "is_parallel": true,
339
- "self": 27.44743387197809
 
 
 
 
 
 
 
 
340
  },
341
  "_update_policy": {
342
- "total": 17.761775617000126,
343
- "count": 9,
344
  "is_parallel": true,
345
- "self": 6.11111961200163,
346
  "children": {
347
  "TorchPPOOptimizer.update": {
348
- "total": 11.650656004998496,
349
- "count": 456,
350
  "is_parallel": true,
351
- "self": 11.650656004998496
352
  }
353
  }
354
  }
@@ -359,14 +367,14 @@
359
  }
360
  },
361
  "TrainerController._save_models": {
362
- "total": 0.23638259999995626,
363
  "count": 1,
364
- "self": 0.0012184499998966203,
365
  "children": {
366
  "RLTrainer._checkpoint": {
367
- "total": 0.23516415000005964,
368
  "count": 1,
369
- "self": 0.23516415000005964
370
  }
371
  }
372
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 1.0398240089416504,
6
+ "min": 1.0398240089416504,
7
+ "max": 2.866269826889038,
8
+ "count": 10
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 10683.15234375,
12
+ "min": 10683.15234375,
13
+ "max": 29353.46875,
14
+ "count": 10
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 99960.0,
18
  "min": 9952.0,
19
+ "max": 99960.0,
20
+ "count": 10
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 99960.0,
24
  "min": 9952.0,
25
+ "max": 99960.0,
26
+ "count": 10
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 2.3127219676971436,
30
+ "min": 0.2507854402065277,
31
+ "max": 2.3127219676971436,
32
+ "count": 10
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 471.7952880859375,
36
+ "min": 48.652374267578125,
37
+ "max": 471.7952880859375,
38
+ "count": 10
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 10
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 10
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.06389200429628403,
54
+ "min": 0.062248186127844204,
55
+ "max": 0.07397499721789477,
56
+ "count": 10
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.3194600214814201,
60
+ "min": 0.24899274451137682,
61
+ "max": 0.36987498608947383,
62
+ "count": 10
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.15586212218976486,
66
+ "min": 0.07571165587504247,
67
+ "max": 0.15882034897804262,
68
+ "count": 10
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.7793106109488244,
72
+ "min": 0.3028466235001699,
73
+ "max": 0.7941017448902131,
74
+ "count": 10
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 0.00015823204725600002,
78
+ "min": 0.00015823204725600002,
79
  "max": 0.000291882002706,
80
+ "count": 10
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 0.0007911602362800001,
84
+ "min": 0.0006923281692239998,
85
  "max": 0.00138516003828,
86
+ "count": 10
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.15274400000000002,
90
+ "min": 0.15274400000000002,
91
  "max": 0.19729400000000002,
92
+ "count": 10
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.7637200000000001,
96
+ "min": 0.630776,
97
  "max": 0.96172,
98
+ "count": 10
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 0.0026419256000000005,
102
+ "min": 0.0026419256000000005,
103
  "max": 0.0048649706,
104
+ "count": 10
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.013209628000000003,
108
+ "min": 0.0115557224,
109
  "max": 0.023089828,
110
+ "count": 10
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 22.618181818181817,
114
+ "min": 4.0227272727272725,
115
+ "max": 22.618181818181817,
116
+ "count": 10
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1244.0,
120
+ "min": 177.0,
121
+ "max": 1244.0,
122
+ "count": 10
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 22.618181818181817,
126
+ "min": 4.0227272727272725,
127
+ "max": 22.618181818181817,
128
+ "count": 10
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1244.0,
132
+ "min": 177.0,
133
+ "max": 1244.0,
134
+ "count": 10
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 10
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 10
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1677691188",
152
  "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
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": "0.29.0.dev0",
155
  "mlagents_envs_version": "0.29.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.8.1+cu102",
158
  "numpy_version": "1.22.4",
159
+ "end_time_seconds": "1677691448"
160
  },
161
+ "total": 260.20794596199994,
162
  "count": 1,
163
+ "self": 0.006016890999944735,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.10764882199998738,
167
  "count": 1,
168
+ "self": 0.10764882199998738
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 260.094280249,
172
  "count": 1,
173
+ "self": 0.8553450709955541,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 7.026263712999935,
177
  "count": 1,
178
+ "self": 7.026263712999935
179
  },
180
  "TrainerController.advance": {
181
+ "total": 252.09290672800478,
182
+ "count": 10049,
183
+ "self": 0.16911708899385758,
184
  "children": {
185
  "env_step": {
186
+ "total": 251.92378963901092,
187
+ "count": 10049,
188
+ "self": 172.526267241009,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 79.24467633799225,
192
+ "count": 10049,
193
+ "self": 0.9792645899973422,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 78.2654117479949,
197
+ "count": 10049,
198
+ "self": 17.849673215000962,
199
  "children": {
200
  "TorchPolicy.sample_actions": {
201
+ "total": 60.41573853299394,
202
+ "count": 10049,
203
+ "self": 60.41573853299394
204
  }
205
  }
206
  }
207
  }
208
  },
209
  "workers": {
210
+ "total": 0.15284606000966505,
211
+ "count": 10048,
212
  "self": 0.0,
213
  "children": {
214
  "worker_root": {
215
+ "total": 258.6776240289953,
216
+ "count": 10048,
217
  "is_parallel": true,
218
+ "self": 128.7869458539932,
219
  "children": {
220
  "run_training.setup": {
221
  "total": 0.0,
 
224
  "self": 0.0,
225
  "children": {
226
  "steps_from_proto": {
227
+ "total": 0.00216344599994045,
228
  "count": 1,
229
  "is_parallel": true,
230
+ "self": 0.0007475899999462854,
231
  "children": {
232
  "_process_rank_one_or_two_observation": {
233
+ "total": 0.0014158559999941644,
234
  "count": 10,
235
  "is_parallel": true,
236
+ "self": 0.0014158559999941644
237
  }
238
  }
239
  },
240
  "UnityEnvironment.step": {
241
+ "total": 0.07644220099996346,
242
  "count": 1,
243
  "is_parallel": true,
244
+ "self": 0.0005894959999750427,
245
  "children": {
246
  "UnityEnvironment._generate_step_input": {
247
+ "total": 0.0004214379999893936,
248
  "count": 1,
249
  "is_parallel": true,
250
+ "self": 0.0004214379999893936
251
  },
252
  "communicator.exchange": {
253
+ "total": 0.07340030000000297,
254
  "count": 1,
255
  "is_parallel": true,
256
+ "self": 0.07340030000000297
257
  },
258
  "steps_from_proto": {
259
+ "total": 0.0020309669999960533,
260
  "count": 1,
261
  "is_parallel": true,
262
+ "self": 0.00046088700003110716,
263
  "children": {
264
  "_process_rank_one_or_two_observation": {
265
+ "total": 0.0015700799999649462,
266
  "count": 10,
267
  "is_parallel": true,
268
+ "self": 0.0015700799999649462
269
  }
270
  }
271
  }
 
274
  }
275
  },
276
  "UnityEnvironment.step": {
277
+ "total": 129.8906781750021,
278
+ "count": 10047,
279
  "is_parallel": true,
280
+ "self": 5.248739870997497,
281
  "children": {
282
  "UnityEnvironment._generate_step_input": {
283
+ "total": 2.8828429830062987,
284
+ "count": 10047,
285
  "is_parallel": true,
286
+ "self": 2.8828429830062987
287
  },
288
  "communicator.exchange": {
289
+ "total": 104.55522575800114,
290
+ "count": 10047,
291
  "is_parallel": true,
292
+ "self": 104.55522575800114
293
  },
294
  "steps_from_proto": {
295
+ "total": 17.20386956299717,
296
+ "count": 10047,
297
  "is_parallel": true,
298
+ "self": 3.7718461520039455,
299
  "children": {
300
  "_process_rank_one_or_two_observation": {
301
+ "total": 13.432023410993224,
302
+ "count": 100470,
303
  "is_parallel": true,
304
+ "self": 13.432023410993224
305
  }
306
  }
307
  }
 
316
  }
317
  },
318
  "trainer_threads": {
319
+ "total": 0.0009472699998696044,
320
  "count": 1,
321
+ "self": 0.0009472699998696044,
322
  "children": {
323
  "thread_root": {
324
  "total": 0.0,
 
327
  "self": 0.0,
328
  "children": {
329
  "trainer_advance": {
330
+ "total": 250.73056016997555,
331
+ "count": 220460,
332
  "is_parallel": true,
333
+ "self": 5.610790782031017,
334
  "children": {
335
  "process_trajectory": {
336
+ "total": 142.3387238549443,
337
+ "count": 220460,
338
  "is_parallel": true,
339
+ "self": 139.62837210494422,
340
+ "children": {
341
+ "RLTrainer._checkpoint": {
342
+ "total": 2.710351750000086,
343
+ "count": 10,
344
+ "is_parallel": true,
345
+ "self": 2.710351750000086
346
+ }
347
+ }
348
  },
349
  "_update_policy": {
350
+ "total": 102.78104553300022,
351
+ "count": 50,
352
  "is_parallel": true,
353
+ "self": 36.61635267699944,
354
  "children": {
355
  "TorchPPOOptimizer.update": {
356
+ "total": 66.16469285600078,
357
+ "count": 2547,
358
  "is_parallel": true,
359
+ "self": 66.16469285600078
360
  }
361
  }
362
  }
 
367
  }
368
  },
369
  "TrainerController._save_models": {
370
+ "total": 0.11881746699987161,
371
  "count": 1,
372
+ "self": 0.0014952389997233695,
373
  "children": {
374
  "RLTrainer._checkpoint": {
375
+ "total": 0.11732222800014824,
376
  "count": 1,
377
+ "self": 0.11732222800014824
378
  }
379
  }
380
  }
run_logs/training_status.json CHANGED
@@ -2,22 +2,103 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 20504,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-20504.onnx",
7
- "reward": 7.090909090909091,
8
- "creation_time": 1677690959.7399228,
9
  "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-20504.pt"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  ]
12
  }
13
  ],
14
  "final_checkpoint": {
15
- "steps": 20504,
16
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
17
- "reward": 7.090909090909091,
18
- "creation_time": 1677690959.7399228,
19
  "auxillary_file_paths": [
20
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-20504.pt"
21
  ]
22
  }
23
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 19992,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-19992.onnx",
7
+ "reward": 7.545454545454546,
8
+ "creation_time": 1677691242.0172856,
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": 9.0,
17
+ "creation_time": 1677691264.1643503,
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": 13.545454545454545,
26
+ "creation_time": 1677691287.2966907,
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": 15.545454545454545,
35
+ "creation_time": 1677691310.4563038,
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": 16.363636363636363,
44
+ "creation_time": 1677691333.5020227,
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": 19.90909090909091,
53
+ "creation_time": 1677691355.4099302,
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": 22.545454545454547,
62
+ "creation_time": 1677691379.234315,
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": 23.454545454545453,
71
+ "creation_time": 1677691400.772039,
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": 22.363636363636363,
80
+ "creation_time": 1677691424.7146888,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 109912,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-109912.onnx",
88
+ "reward": null,
89
+ "creation_time": 1677691448.4780314,
90
+ "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-109912.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 109912,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": null,
99
+ "creation_time": 1677691448.4780314,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-109912.pt"
102
  ]
103
  }
104
  },