Hugging Face's logo

Deinigu
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
 Metrics Community
Deinigu commited on
Commit
66bb524
·
verified ·
1 Parent(s): 7c13340

Second training

Browse files
Files changed (28) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-349904.onnx +3 -0
  3. SnowballTarget/SnowballTarget-349904.pt +3 -0
  4. SnowballTarget/SnowballTarget-399992.onnx +3 -0
  5. SnowballTarget/SnowballTarget-399992.pt +3 -0
  6. SnowballTarget/SnowballTarget-449992.onnx +3 -0
  7. SnowballTarget/SnowballTarget-449992.pt +3 -0
  8. SnowballTarget/SnowballTarget-499888.onnx +3 -0
  9. SnowballTarget/SnowballTarget-499888.pt +3 -0
  10. SnowballTarget/SnowballTarget-549976.onnx +3 -0
  11. SnowballTarget/SnowballTarget-549976.pt +3 -0
  12. SnowballTarget/SnowballTarget-599936.onnx +3 -0
  13. SnowballTarget/SnowballTarget-599936.pt +3 -0
  14. SnowballTarget/SnowballTarget-601216.onnx +3 -0
  15. SnowballTarget/SnowballTarget-601216.pt +3 -0
  16. SnowballTarget/checkpoint.pt +1 -1
  17. SnowballTarget/events.out.tfevents.1762516276.1696528d3eb8.13852.0 +3 -0
  18. SnowballTarget/events.out.tfevents.1762516310.1696528d3eb8.14051.0 +3 -0
  19. SnowballTarget/events.out.tfevents.1762516326.1696528d3eb8.14172.0 +3 -0
  20. SnowballTarget/events.out.tfevents.1762516380.1696528d3eb8.14451.0 +3 -0
  21. SnowballTarget/events.out.tfevents.1762516416.1696528d3eb8.14658.0 +3 -0
  22. SnowballTarget/events.out.tfevents.1762516478.1696528d3eb8.14973.0 +3 -0
  23. SnowballTarget/events.out.tfevents.1762516961.1696528d3eb8.17069.0 +3 -0
  24. config.json +1 -1
  25. configuration.yaml +2 -2
  26. run_logs/Player-0.log +14 -17
  27. run_logs/timers.json +162 -162
  28. run_logs/training_status.json +46 -28
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d62a0f07d4d14d0bcd11ce3bb11267188ae6449c22af14cc61b81aa70fc3066
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6585d80c29790a373df80fe4ff475e06f1f3580daf21556880f03f1287deedfd
3
  size 650646
SnowballTarget/SnowballTarget-349904.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e06883af0a54913f4103034e13accbfcd9fe22349fed9d5c332536e9aa6e4537
3
+ size 650646
SnowballTarget/SnowballTarget-349904.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df030c82a18fca63bb33d47638b3b42acfdce5318e8aff7eacd13d22fd383762
3
+ size 3850564
SnowballTarget/SnowballTarget-399992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f96e6752002978b5e6c52764e9c5ca3829f6eae79c621cba5ee1713f0c82343
3
+ size 650646
SnowballTarget/SnowballTarget-399992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d46c3a164e723dce6a4cb45d5f9631146aaa3377fee8de2a023fa2f9bf98df92
3
+ size 3850564
SnowballTarget/SnowballTarget-449992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a8701db369a38a873481f4b1d28dfc1fbff8906717f5f1ff8da077cf9fd1375
3
+ size 650646
SnowballTarget/SnowballTarget-449992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b377310a81362e77ad1ad2a3ad6083bd348a53e08d6f33edcf66a22b5d85a6d5
3
+ size 3850564
SnowballTarget/SnowballTarget-499888.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2da6f6520f8ffbfbdf79a3953fa04e5d2b05c5adc670763de0bc8f28d60ad668
3
+ size 650646
SnowballTarget/SnowballTarget-499888.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7802173a8d296843d588f00448b30b97e0e00c2fb2ba996bab28598df250edbc
3
+ size 3850564
SnowballTarget/SnowballTarget-549976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f0b5d59dd6f2ebbdebe038cd12fe90e85c1c1173c2d7700f0462dce9e3aeae7
3
+ size 650646
SnowballTarget/SnowballTarget-549976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcb4763c0b676054b40403c9b495b4f6f2dce961edfef8bf7f2ae6b43331dc88
3
+ size 3850564
SnowballTarget/SnowballTarget-599936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6585d80c29790a373df80fe4ff475e06f1f3580daf21556880f03f1287deedfd
3
+ size 650646
SnowballTarget/SnowballTarget-599936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:241a6c125e858e271db27eafcef316b58c9baf20a20e60c641a56072a3d87d94
3
+ size 3850564
SnowballTarget/SnowballTarget-601216.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6585d80c29790a373df80fe4ff475e06f1f3580daf21556880f03f1287deedfd
3
+ size 650646
SnowballTarget/SnowballTarget-601216.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dde4ef79e73ffa1be74af00888871fa806f6020dfe90487debfec79417cb19bd
3
+ size 3850564
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03ac616c4cdf1fe3d9dab4ce8f9586a2e00dced6508903d56ab2879c11004757
3
  size 3849717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06e6442f3ac1f9c1543765a11284c1e7c8443b9c8afbc3152d3148cf3786d20c
3
  size 3849717
SnowballTarget/events.out.tfevents.1762516276.1696528d3eb8.13852.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d415bf4c5fedc2d98a809bed99306d354f4a762708fa8b89955be1dd0f585b3
3
+ size 1117
SnowballTarget/events.out.tfevents.1762516310.1696528d3eb8.14051.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:993e2da654be8713104951fbbd63e09442b2fc24385490802bee43bd18c918f7
3
+ size 1117
SnowballTarget/events.out.tfevents.1762516326.1696528d3eb8.14172.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a2c985db463e67b777ba2b58d3be173f2af8900f708c188fdad51cbac91542b
3
+ size 1117
SnowballTarget/events.out.tfevents.1762516380.1696528d3eb8.14451.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1786bbb553785d4c0af3c2d249104edb21f156b66788214f1a12ec76e099312
3
+ size 1117
SnowballTarget/events.out.tfevents.1762516416.1696528d3eb8.14658.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b71b219c03ea90e7dc0cd6c2506691d9503e8459ddc865cbbd2a9a861c335070
3
+ size 1117
SnowballTarget/events.out.tfevents.1762516478.1696528d3eb8.14973.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00cb0eca41063fb6c49066785e8c612daf13215236a3a9332953d0eab1f092fa
3
+ size 11335
SnowballTarget/events.out.tfevents.1762516961.1696528d3eb8.17069.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3efbbacb589da797cae34ed1a64db48722c4e428ff862f9b2d1845c1637484ec
3
+ size 35134
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 1024, "buffer_size": 4096, "learning_rate": 0.0001, "beta": 0.0005, "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": 7, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 128, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 1024, "buffer_size": 4096, "learning_rate": 0.0001, "beta": 0.0005, "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": 7, "even_checkpoints": false, "max_steps": 600000, "time_horizon": 128, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": true, "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: 7
40
  even_checkpoints: false
41
- max_steps: 200000
42
  time_horizon: 128
43
  summary_freq: 10000
44
  threaded: false
@@ -69,7 +69,7 @@ checkpoint_settings:
69
  run_id: SnowballTarget1
70
  initialize_from: null
71
  load_model: false
72
- resume: false
73
  force: false
74
  train_model: false
75
  inference: false
 
38
  init_path: null
39
  keep_checkpoints: 7
40
  even_checkpoints: false
41
+ max_steps: 600000
42
  time_horizon: 128
43
  summary_freq: 10000
44
  threaded: false
 
69
  run_id: SnowballTarget1
70
  initialize_from: null
71
  load_model: false
72
+ resume: true
73
  force: false
74
  train_model: false
75
  inference: false
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 0.082 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: 0.642780 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]: 5368 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
@@ -169,19 +166,19 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 44
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]: 5460 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 7.4 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 5460 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
  Peak Allocated memory 17.2 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]: 3847 frames, [64.0 KB-128.0 KB]: 1613 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 67.3 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 5460 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]: 5460 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]: 5459 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]: 5460 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]: 5460 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 0.090 seconds
35
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
42
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
43
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
44
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
45
+ UnloadTime: 0.623103 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]: 8062 frames, [16.0 KB-32.0 KB]: 136 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 46
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]: 8199 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 7.8 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 8199 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
  Peak Allocated memory 17.2 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]: 2592 frames, [64.0 KB-128.0 KB]: 5607 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 68.6 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 8199 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]: 8199 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]: 8198 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]: 8199 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]: 8199 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -2,213 +2,213 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 2.3241453170776367,
6
- "min": 2.3241453170776367,
7
- "max": 2.890087842941284,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 22293.201171875,
12
- "min": 22137.365234375,
13
- "max": 31779.72265625,
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": 4.310549736022949,
30
- "min": -0.01074505876749754,
31
- "max": 4.310549736022949,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 435.36553955078125,
36
- "min": -1.0422706604003906,
37
- "max": 435.36553955078125,
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": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
- "count": 20
51
  },
52
  "SnowballTarget.Environment.CumulativeReward.mean": {
53
- "value": 8.961538461538462,
54
- "min": 2.6363636363636362,
55
- "max": 8.961538461538462,
56
- "count": 20
57
  },
58
  "SnowballTarget.Environment.CumulativeReward.sum": {
59
- "value": 466.0,
60
- "min": 116.0,
61
- "max": 466.0,
62
- "count": 20
63
  },
64
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
- "value": 8.961538461538462,
66
- "min": 2.6363636363636362,
67
- "max": 8.961538461538462,
68
- "count": 20
69
  },
70
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
- "value": 466.0,
72
- "min": 116.0,
73
- "max": 466.0,
74
- "count": 20
75
  },
76
  "SnowballTarget.Losses.PolicyLoss.mean": {
77
- "value": 0.026437590531713795,
78
- "min": 0.016743642057311565,
79
- "max": 0.030202925961930305,
80
- "count": 20
81
  },
82
  "SnowballTarget.Losses.PolicyLoss.sum": {
83
- "value": 0.05287518106342759,
84
- "min": 0.03348728411462313,
85
- "max": 0.0800755696551884,
86
- "count": 20
87
  },
88
  "SnowballTarget.Losses.ValueLoss.mean": {
89
- "value": 0.31467231238881743,
90
- "min": 0.12198344524949789,
91
- "max": 0.32054602975646657,
92
- "count": 20
93
  },
94
  "SnowballTarget.Losses.ValueLoss.sum": {
95
- "value": 0.6293446247776349,
96
- "min": 0.24396689049899578,
97
- "max": 0.9477601523200669,
98
- "count": 20
99
  },
100
  "SnowballTarget.Policy.LearningRate.mean": {
101
- "value": 2.100097900000002e-06,
102
- "min": 2.100097900000002e-06,
103
- "max": 9.670000330000001e-05,
104
- "count": 20
105
  },
106
  "SnowballTarget.Policy.LearningRate.sum": {
107
- "value": 4.200195800000004e-06,
108
- "min": 4.200195800000004e-06,
109
- "max": 0.0002472000528,
110
- "count": 20
111
  },
112
  "SnowballTarget.Policy.Epsilon.mean": {
113
- "value": 0.1021,
114
- "min": 0.1021,
115
- "max": 0.19669999999999999,
116
- "count": 20
117
  },
118
  "SnowballTarget.Policy.Epsilon.sum": {
119
- "value": 0.2042,
120
- "min": 0.2042,
121
- "max": 0.5472,
122
- "count": 20
123
  },
124
  "SnowballTarget.Policy.Beta.mean": {
125
- "value": 2.0290000000000007e-05,
126
- "min": 2.0290000000000007e-05,
127
- "max": 0.0004838300000000001,
128
- "count": 20
129
  },
130
  "SnowballTarget.Policy.Beta.sum": {
131
- "value": 4.0580000000000015e-05,
132
- "min": 4.0580000000000015e-05,
133
- "max": 0.00124128,
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": "1762514617",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1762515010"
160
  },
161
- "total": 392.75992730100006,
162
  "count": 1,
163
- "self": 0.4307554690001325,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.025848885999948834,
167
  "count": 1,
168
- "self": 0.025848885999948834
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 392.303322946,
172
  "count": 1,
173
- "self": 0.3759268440167034,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 2.7668223719999787,
177
  "count": 1,
178
- "self": 2.7668223719999787
179
  },
180
  "TrainerController.advance": {
181
- "total": 389.07903029298336,
182
- "count": 18200,
183
- "self": 0.3792768889875333,
184
  "children": {
185
  "env_step": {
186
- "total": 321.31676956099454,
187
- "count": 18200,
188
- "self": 250.54857935896212,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 70.54734476501358,
192
- "count": 18200,
193
- "self": 1.275305534998779,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 69.2720392300148,
197
- "count": 18200,
198
- "self": 69.2720392300148
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.22084543701885195,
204
- "count": 18200,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 390.59533471098644,
209
- "count": 18200,
210
  "is_parallel": true,
211
- "self": 170.57021740298683,
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": 0.004687703000172405,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.003302252000594308,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0013854509995780973,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0013854509995780973
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.037418512000158444,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006120630002897087,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0004695739999078796,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0004695739999078796
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03440155899988895,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03440155899988895
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0019353160000719072,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00036776299975826987,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0015675530003136373,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0015675530003136373
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 220.0251173079996,
271
- "count": 18199,
272
  "is_parallel": true,
273
- "self": 10.229218741002569,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.431949275014631,
277
- "count": 18199,
278
  "is_parallel": true,
279
- "self": 5.431949275014631
280
  },
281
  "communicator.exchange": {
282
- "total": 167.30069428099773,
283
- "count": 18199,
284
  "is_parallel": true,
285
- "self": 167.30069428099773
286
  },
287
  "steps_from_proto": {
288
- "total": 37.063255010984676,
289
- "count": 18199,
290
  "is_parallel": true,
291
- "self": 6.700471101969697,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 30.36278390901498,
295
- "count": 181990,
296
  "is_parallel": true,
297
- "self": 30.36278390901498
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 67.38298384300128,
311
- "count": 18200,
312
- "self": 0.5043809000158035,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 21.229000259985924,
316
- "count": 18200,
317
- "self": 20.836893393985747,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.3921068660001765,
321
- "count": 4,
322
- "self": 0.3921068660001765
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 45.64960268299956,
328
- "count": 45,
329
- "self": 35.14298270399968,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 10.506619978999879,
333
- "count": 540,
334
- "self": 10.506619978999879
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 9.699999736767495e-07,
344
  "count": 1,
345
- "self": 9.699999736767495e-07
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.08154246699996293,
349
  "count": 1,
350
- "self": 0.0009384520001276542,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.08060401499983527,
354
  "count": 1,
355
- "self": 0.08060401499983527
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 1.2791601419448853,
6
+ "min": 1.2791601419448853,
7
+ "max": 2.036785364151001,
8
+ "count": 30
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 14070.76171875,
12
+ "min": 11621.716796875,
13
+ "max": 20791.50390625,
14
+ "count": 30
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 599936.0,
18
+ "min": 309920.0,
19
+ "max": 599936.0,
20
+ "count": 30
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 599936.0,
24
+ "min": 309920.0,
25
+ "max": 599936.0,
26
+ "count": 30
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 7.021315574645996,
30
+ "min": 4.909838676452637,
31
+ "max": 7.07533073425293,
32
+ "count": 30
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 716.1741943359375,
36
+ "min": 451.7051696777344,
37
+ "max": 721.6837158203125,
38
+ "count": 30
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 30
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 30
51
  },
52
  "SnowballTarget.Environment.CumulativeReward.mean": {
53
+ "value": 13.363636363636363,
54
+ "min": 9.886363636363637,
55
+ "max": 14.127659574468085,
56
+ "count": 30
57
  },
58
  "SnowballTarget.Environment.CumulativeReward.sum": {
59
+ "value": 735.0,
60
+ "min": 435.0,
61
+ "max": 747.0,
62
+ "count": 30
63
  },
64
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
+ "value": 13.363636363636363,
66
+ "min": 9.886363636363637,
67
+ "max": 14.127659574468085,
68
+ "count": 30
69
  },
70
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
+ "value": 735.0,
72
+ "min": 435.0,
73
+ "max": 747.0,
74
+ "count": 30
75
  },
76
  "SnowballTarget.Losses.PolicyLoss.mean": {
77
+ "value": 0.01730723716658152,
78
+ "min": 0.013768826169931952,
79
+ "max": 0.034235001677492015,
80
+ "count": 30
81
  },
82
  "SnowballTarget.Losses.PolicyLoss.sum": {
83
+ "value": 0.05192171149974456,
84
+ "min": 0.027537652339863904,
85
+ "max": 0.07840476820213856,
86
+ "count": 30
87
  },
88
  "SnowballTarget.Losses.ValueLoss.mean": {
89
+ "value": 0.30628854119115406,
90
+ "min": 0.2808823101222515,
91
+ "max": 0.36244359364112216,
92
+ "count": 30
93
  },
94
  "SnowballTarget.Losses.ValueLoss.sum": {
95
+ "value": 0.9188656235734622,
96
+ "min": 0.561764620244503,
97
+ "max": 0.9833823864658673,
98
+ "count": 30
99
  },
100
  "SnowballTarget.Policy.LearningRate.mean": {
101
+ "value": 7.654325679999995e-07,
102
+ "min": 7.654325679999995e-07,
103
+ "max": 4.879871786800001e-05,
104
+ "count": 30
105
  },
106
  "SnowballTarget.Policy.LearningRate.sum": {
107
+ "value": 2.2962977039999984e-06,
108
+ "min": 2.2962977039999984e-06,
109
+ "max": 0.000127696172304,
110
+ "count": 30
111
  },
112
  "SnowballTarget.Policy.Epsilon.mean": {
113
+ "value": 0.10076533333333333,
114
+ "min": 0.10076533333333333,
115
+ "max": 0.1487986666666667,
116
+ "count": 30
117
  },
118
  "SnowballTarget.Policy.Epsilon.sum": {
119
+ "value": 0.302296,
120
+ "min": 0.20519733333333337,
121
+ "max": 0.4276960000000001,
122
+ "count": 30
123
  },
124
  "SnowballTarget.Policy.Beta.mean": {
125
+ "value": 1.375013333333333e-05,
126
+ "min": 1.375013333333333e-05,
127
+ "max": 0.0002491134666666667,
128
+ "count": 30
129
  },
130
  "SnowballTarget.Policy.Beta.sum": {
131
+ "value": 4.1250399999999994e-05,
132
+ "min": 4.1250399999999994e-05,
133
+ "max": 0.0006557103999999999,
134
+ "count": 30
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 30
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 30
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1762516960",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1762517552"
160
  },
161
+ "total": 592.2312760890004,
162
  "count": 1,
163
+ "self": 0.6854531370013319,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.025205188999734673,
167
  "count": 1,
168
+ "self": 0.025205188999734673
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 591.5206177629993,
172
  "count": 1,
173
+ "self": 0.634241693968761,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 1.8806869069999266,
177
  "count": 1,
178
+ "self": 1.8806869069999266
179
  },
180
  "TrainerController.advance": {
181
+ "total": 588.891397155031,
182
+ "count": 27328,
183
+ "self": 0.6099100390879357,
184
  "children": {
185
  "env_step": {
186
+ "total": 484.2565340659221,
187
+ "count": 27328,
188
+ "self": 378.1459005417764,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 105.73474780199558,
192
+ "count": 27328,
193
+ "self": 1.931934716001706,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 103.80281308599388,
197
+ "count": 27328,
198
+ "self": 103.80281308599388
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.37588572215008753,
204
+ "count": 27328,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 588.6466735419563,
209
+ "count": 27328,
210
  "is_parallel": true,
211
+ "self": 257.60993185196867,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0025357979998261726,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0007605889991282311,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0017752090006979415,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0017752090006979415
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.036977805999867996,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0005932839994784445,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0003188280002177635,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0003188280002177635
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03413033800006815,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03413033800006815
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0019353560001036385,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0003527700005179213,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0015825859995857172,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0015825859995857172
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 331.0367416899876,
271
+ "count": 27327,
272
  "is_parallel": true,
273
+ "self": 15.200489163059956,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 8.095992872050374,
277
+ "count": 27327,
278
  "is_parallel": true,
279
+ "self": 8.095992872050374
280
  },
281
  "communicator.exchange": {
282
+ "total": 252.92622028195092,
283
+ "count": 27327,
284
  "is_parallel": true,
285
+ "self": 252.92622028195092
286
  },
287
  "steps_from_proto": {
288
+ "total": 54.814039372926345,
289
+ "count": 27327,
290
  "is_parallel": true,
291
+ "self": 10.048774410947317,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 44.76526496197903,
295
+ "count": 273270,
296
  "is_parallel": true,
297
+ "self": 44.76526496197903
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 104.02495305002094,
311
+ "count": 27328,
312
+ "self": 0.8198006880729736,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 31.862228450949715,
316
+ "count": 27328,
317
+ "self": 31.236804354948617,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.6254240960010975,
321
+ "count": 6,
322
+ "self": 0.6254240960010975
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 71.34292391099825,
328
+ "count": 68,
329
+ "self": 54.793426481001916,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 16.549497429996336,
333
+ "count": 816,
334
+ "self": 16.549497429996336
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 1.139000232797116e-06,
344
  "count": 1,
345
+ "self": 1.139000232797116e-06
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.11429086799944344,
349
  "count": 1,
350
+ "self": 0.0016393489995607524,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.11265151899988268,
354
  "count": 1,
355
+ "self": 0.11265151899988268
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -2,58 +2,76 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 49952,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49952.onnx",
7
- "reward": 3.5,
8
- "creation_time": 1762514722.099842,
 
 
 
 
 
 
 
 
 
9
  "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-49952.pt"
11
  ]
12
  },
13
  {
14
- "steps": 99896,
15
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99896.onnx",
16
- "reward": 7.090909090909091,
17
- "creation_time": 1762514819.0264485,
18
  "auxillary_file_paths": [
19
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-99896.pt"
20
  ]
21
  },
22
  {
23
- "steps": 149984,
24
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
  "reward": null,
26
- "creation_time": 1762514917.1551106,
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": 9.125,
35
- "creation_time": 1762515009.988979,
36
  "auxillary_file_paths": [
37
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
- "steps": 200200,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.onnx",
43
- "reward": 10.545454545454545,
44
- "creation_time": 1762515010.0893934,
 
 
 
 
 
 
 
 
 
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
- "steps": 200200,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 10.545454545454545,
54
- "creation_time": 1762515010.0893934,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.pt"
57
  ]
58
  }
59
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 349904,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349904.onnx",
7
+ "reward": null,
8
+ "creation_time": 1762517059.2028866,
9
+ "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-349904.pt"
11
+ ]
12
+ },
13
+ {
14
+ "steps": 399992,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.onnx",
16
+ "reward": 12.363636363636363,
17
+ "creation_time": 1762517157.627532,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 449992,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449992.onnx",
25
+ "reward": 13.263157894736842,
26
+ "creation_time": 1762517255.1124034,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-449992.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 499888,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499888.onnx",
34
  "reward": null,
35
+ "creation_time": 1762517354.1441364,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-499888.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 549976,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-549976.onnx",
43
+ "reward": 15.090909090909092,
44
+ "creation_time": 1762517451.8545153,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-549976.pt"
47
  ]
48
  },
49
  {
50
+ "steps": 599936,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-599936.onnx",
52
+ "reward": null,
53
+ "creation_time": 1762517551.917334,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-599936.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 601216,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-601216.onnx",
61
+ "reward": null,
62
+ "creation_time": 1762517552.311762,
63
  "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-601216.pt"
65
  ]
66
  }
67
  ],
68
  "final_checkpoint": {
69
+ "steps": 601216,
70
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
71
+ "reward": null,
72
+ "creation_time": 1762517552.311762,
73
  "auxillary_file_paths": [
74
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-601216.pt"
75
  ]
76
  }
77
  },