Hugging Face's logo

seb-835
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
seb-835 commited on
Commit
1cfab05
·
verified ·
1 Parent(s): 0f39882

first commit

Browse files
Files changed (22) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-149984.onnx +1 -1
  3. SnowballTarget/SnowballTarget-149984.pt +1 -1
  4. SnowballTarget/SnowballTarget-199984.onnx +1 -1
  5. SnowballTarget/SnowballTarget-199984.pt +1 -1
  6. SnowballTarget/SnowballTarget-200112.onnx +1 -1
  7. SnowballTarget/SnowballTarget-200112.pt +1 -1
  8. SnowballTarget/SnowballTarget-249944.onnx +3 -0
  9. SnowballTarget/SnowballTarget-249944.pt +3 -0
  10. SnowballTarget/SnowballTarget-250008.onnx +3 -0
  11. SnowballTarget/SnowballTarget-250008.pt +3 -0
  12. SnowballTarget/SnowballTarget-49936.onnx +1 -1
  13. SnowballTarget/SnowballTarget-49936.pt +1 -1
  14. SnowballTarget/SnowballTarget-99960.onnx +1 -1
  15. SnowballTarget/SnowballTarget-99960.pt +1 -1
  16. SnowballTarget/checkpoint.pt +1 -1
  17. SnowballTarget/events.out.tfevents.1767977742.5e0133544f3e.18492.0 +3 -0
  18. config.json +1 -1
  19. configuration.yaml +6 -6
  20. run_logs/Player-0.log +17 -20
  21. run_logs/timers.json +160 -160
  22. run_logs/training_status.json +26 -17
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cab809d2a29940cee230902e9371c6f5c90b33a41b6b451d603fa79db2e5af5
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6affe1360b6fb236c160cf6398492ec68f2219e77e5baadd23b2d142afeaaef0
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53b9e13fef41bd52cae6bc8bf0bbc4c176fe233363a8f9192461a3f02e0e5e66
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9d8738d06085dc743dffebb14134b4d60544d9b33f97f259e9c44ce0db84ade
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ead0a7ed2e4c9e99a68fc9b1a8f276f0fbae1b30b806feb00fd3227f8984473
3
  size 3850564
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca7bbeeb47d9f546b9fee8ba36683c0dc81657392e4c0e52e670095420661df4
3
  size 3850564
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cab809d2a29940cee230902e9371c6f5c90b33a41b6b451d603fa79db2e5af5
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa7d7d8101e0af70b9644e5207c11517d5d79c8632e90bfc969993f43383295d
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57db7d26f17ae5aaa123f9c874be2c321bf3e784501f564353621e74681fe870
3
  size 3850564
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96e2d1a730df924e3a1c6cd0949c9fc8005b483208ad20608f9d060d43a68705
3
  size 3850564
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cab809d2a29940cee230902e9371c6f5c90b33a41b6b451d603fa79db2e5af5
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49675d870cfc515aa4aa321e2a5bb3c76259cc14397b4064b5b3fcd0c99b6ef0
3
  size 650646
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23858ee2b2c27c684c850af1180da9e94136d768051bdf2af859e97d1ae5e033
3
  size 3850564
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdbec22555af17917a28e68c069ce1515f07f24cac0f100c8586568cc280a74e
3
  size 3850564
SnowballTarget/SnowballTarget-249944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6affe1360b6fb236c160cf6398492ec68f2219e77e5baadd23b2d142afeaaef0
3
+ size 650646
SnowballTarget/SnowballTarget-249944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cce449350c164d105782596e52fda550b67d1c0a3dc5214af946e7176bd49e02
3
+ size 3850564
SnowballTarget/SnowballTarget-250008.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6affe1360b6fb236c160cf6398492ec68f2219e77e5baadd23b2d142afeaaef0
3
+ size 650646
SnowballTarget/SnowballTarget-250008.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05571d38681d2da6faa02eafbd8211e31f32784cba032dab921fceafadc346c3
3
+ size 3850564
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb8740702c30e3a3dc62274db7191f219469abb1b7cc358c1e828da6c21b380d
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:968a9e5305f29911424c362e6687493c71be1b1516ceec4af7161beb1b064d50
3
  size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b81959784c9875d81b4ae3329d15aa85313d7dbe8f067068937a8bf316eacc2b
3
  size 3850487
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:408b7f22239a2a7f32f141b9597a59a5df67de431e11f2f3a762d9cd95513f66
3
  size 3850487
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8856fc08a07ab9a1bb2d9d02fa29c4d1aea66bb911887b12f3e8ee388a265be6
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dce68163eee4d92eeb35de3b20a52fcaf4a8f6ae299f128b185e469f5cdd17d3
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f4773fedd2defa3e63a6b45588c22bffc195c60c1a0b7746577159825dbf4ce
3
  size 3850487
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a066426df99ded477c9b760bf19756eed407e38681c8201dc090b658e0d1446
3
  size 3850487
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8bfc79122f423c720803e8656f6651fb98f39c6a600fec484f4458326819e700
3
  size 3849717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc43124e9a4fae469bf604f356d6518abdef2bfff629c1e3f6c68f059ddb031f
3
  size 3849717
SnowballTarget/events.out.tfevents.1767977742.5e0133544f3e.18492.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f117aff7cb965c09f0c5241807cfc0c34f04d3f77c5f19cec854b743bd535d30
3
+ size 27251
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.001, "beta": 0.006, "epsilon": 0.22, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 250000, "time_horizon": 64, "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": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -5,9 +5,9 @@ behaviors:
5
  hyperparameters:
6
  batch_size: 128
7
  buffer_size: 2048
8
- learning_rate: 0.0003
9
- beta: 0.005
10
- epsilon: 0.2
11
  lambd: 0.95
12
  num_epoch: 3
13
  shared_critic: false
@@ -38,14 +38,14 @@ 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: false
45
  self_play: null
46
  behavioral_cloning: null
47
  env_settings:
48
- env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
49
  env_args: null
50
  base_port: 5005
51
  num_envs: 1
@@ -70,7 +70,7 @@ checkpoint_settings:
70
  initialize_from: null
71
  load_model: false
72
  resume: false
73
- force: false
74
  train_model: false
75
  inference: false
76
  results_dir: results
 
5
  hyperparameters:
6
  batch_size: 128
7
  buffer_size: 2048
8
+ learning_rate: 0.001
9
+ beta: 0.006
10
+ epsilon: 0.22
11
  lambd: 0.95
12
  num_epoch: 3
13
  shared_critic: false
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 250000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: false
45
  self_play: null
46
  behavioral_cloning: null
47
  env_settings:
48
+ env_path: ../../training-envs-executables/linux/SnowballTarget/SnowballTarget
49
  env_args: null
50
  base_port: 5005
51
  num_envs: 1
 
70
  initialize_from: null
71
  load_model: false
72
  resume: false
73
+ force: true
74
  train_model: false
75
  inference: false
76
  results_dir: results
run_logs/Player-0.log CHANGED
@@ -1,12 +1,9 @@
1
- Mono path[0] = '/content/ml-agents/ml-agents/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
2
- Mono config path = '/content/ml-agents/ml-agents/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/ml-agents/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
11
  GfxDevice: creating device client; threaded=0; jobified=0
12
  NullGfxDevice:
@@ -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 0.085 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: 0.638544 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]: 5367 frames, [16.0 KB-32.0 KB]: 90 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
@@ -61,7 +58,7 @@ Memory Statistics:
61
  [ALLOC_TEMP_Loading.AsyncRead]
62
  Initial Block Size 64.0 KB
63
  Current Block Size 64.0 KB
64
- Peak Allocated Bytes 238 B
65
  Overflow Count 0
66
  [ALLOC_TEMP_Loading.PreloadManager]
67
  Initial Block Size 256.0 KB
@@ -175,13 +172,13 @@ Memory Statistics:
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]: 5458 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 7.3 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
  Peak Allocated memory 17.3 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]: 3987 frames, [64.0 KB-128.0 KB]: 1471 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]: 5458 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]: 5458 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]: 5457 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]: 5458 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]: 5458 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  Peak Allocated memory 1.7 KB
 
1
+ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
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
8
  GfxDevice: creating device client; threaded=0; jobified=0
9
  NullGfxDevice:
 
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 0.084 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: 0.637470 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]: 6705 frames, [16.0 KB-32.0 KB]: 113 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
 
58
  [ALLOC_TEMP_Loading.AsyncRead]
59
  Initial Block Size 64.0 KB
60
  Current Block Size 64.0 KB
61
+ Peak Allocated Bytes 198 B
62
  Overflow Count 0
63
  [ALLOC_TEMP_Loading.PreloadManager]
64
  Initial Block Size 256.0 KB
 
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]: 6819 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 7.7 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 6819 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
  Peak Allocated memory 17.3 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]: 5783 frames, [64.0 KB-128.0 KB]: 1036 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 68.2 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 6819 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]: 6819 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]: 6818 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]: 6819 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]: 6819 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": 1.0167862176895142,
6
- "min": 1.0167862176895142,
7
- "max": 2.8266501426696777,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 9663.5361328125,
12
- "min": 9663.5361328125,
13
- "max": 28854.4453125,
14
- "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 199984.0,
18
  "min": 9952.0,
19
- "max": 199984.0,
20
- "count": 20
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 199984.0,
24
  "min": 9952.0,
25
- "max": 199984.0,
26
- "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.687827110290527,
30
- "min": 0.36856335401535034,
31
- "max": 12.687827110290527,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2474.126220703125,
36
- "min": 71.50128936767578,
37
- "max": 2547.2119140625,
38
- "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.06555758277410824,
42
- "min": 0.0642928458875223,
43
- "max": 0.07476968188834957,
44
- "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.26223033109643296,
48
- "min": 0.26223033109643296,
49
- "max": 0.35043234981319127,
50
- "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.2098214656260668,
54
- "min": 0.11045381946114859,
55
- "max": 0.29746738286579355,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.8392858625042672,
60
- "min": 0.44181527784459435,
61
- "max": 1.4873369143289676,
62
- "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
- "value": 8.082097306000005e-06,
66
- "min": 8.082097306000005e-06,
67
- "max": 0.000291882002706,
68
- "count": 20
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
- "value": 3.232838922400002e-05,
72
- "min": 3.232838922400002e-05,
73
- "max": 0.00138516003828,
74
- "count": 20
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
- "value": 0.10269400000000001,
78
- "min": 0.10269400000000001,
79
- "max": 0.19729400000000002,
80
- "count": 20
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
- "value": 0.41077600000000003,
84
- "min": 0.41077600000000003,
85
- "max": 0.96172,
86
- "count": 20
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
- "value": 0.0001444306000000001,
90
- "min": 0.0001444306000000001,
91
- "max": 0.0048649706,
92
- "count": 20
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
- "value": 0.0005777224000000004,
96
- "min": 0.0005777224000000004,
97
- "max": 0.023089828,
98
- "count": 20
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
- "count": 20
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
  "value": 8756.0,
108
  "min": 8756.0,
109
  "max": 10945.0,
110
- "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.113636363636363,
114
- "min": 3.272727272727273,
115
- "max": 25.113636363636363,
116
- "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1105.0,
120
- "min": 144.0,
121
- "max": 1359.0,
122
- "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.113636363636363,
126
- "min": 3.272727272727273,
127
- "max": 25.113636363636363,
128
- "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1105.0,
132
- "min": 144.0,
133
- "max": 1359.0,
134
- "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 20
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 20
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1767453416",
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 /content/ml-agents/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": "1767453850"
160
  },
161
- "total": 434.5404648670001,
162
  "count": 1,
163
- "self": 0.44014338499937367,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.027695359000063036,
167
  "count": 1,
168
- "self": 0.027695359000063036
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 434.07262612300065,
172
  "count": 1,
173
- "self": 0.3476610419274948,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.1570693949997803,
177
  "count": 1,
178
- "self": 3.1570693949997803
179
  },
180
  "TrainerController.advance": {
181
- "total": 430.4911461130728,
182
- "count": 18192,
183
- "self": 0.3513786491685096,
184
  "children": {
185
  "env_step": {
186
- "total": 312.8000760729865,
187
- "count": 18192,
188
- "self": 245.08243390791586,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 67.51103048600635,
192
- "count": 18192,
193
- "self": 1.2399085260512948,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 66.27112195995505,
197
- "count": 18192,
198
- "self": 66.27112195995505
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.2066116790642809,
204
- "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 432.2718909970008,
209
- "count": 18192,
210
  "is_parallel": true,
211
- "self": 216.72822056601444,
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": 0.004894356000022526,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0034208289998787222,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0014735270001438039,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0014735270001438039
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.04127468600017892,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0007002780002949294,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0004544160001387354,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0004544160001387354
244
  },
245
  "communicator.exchange": {
246
- "total": 0.0378254030001699,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.0378254030001699
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0022945889995753532,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0004512950004027516,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0018432939991726016,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0018432939991726016
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 215.54367043098637,
271
- "count": 18191,
272
  "is_parallel": true,
273
- "self": 10.21210613898802,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.397772733084821,
277
- "count": 18191,
278
  "is_parallel": true,
279
- "self": 5.397772733084821
280
  },
281
  "communicator.exchange": {
282
- "total": 163.8732382979215,
283
- "count": 18191,
284
  "is_parallel": true,
285
- "self": 163.8732382979215
286
  },
287
  "steps_from_proto": {
288
- "total": 36.06055326099204,
289
- "count": 18191,
290
  "is_parallel": true,
291
- "self": 6.500174931943093,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 29.560378329048945,
295
- "count": 181910,
296
  "is_parallel": true,
297
- "self": 29.560378329048945
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 117.33969139091778,
311
- "count": 18192,
312
- "self": 0.4222920959819021,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 25.84912771293466,
316
- "count": 18192,
317
- "self": 25.413367003934127,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.4357607090005331,
321
- "count": 4,
322
- "self": 0.4357607090005331
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 91.06827158200122,
328
- "count": 90,
329
- "self": 37.56660485703196,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 53.501666724969255,
333
- "count": 4587,
334
- "self": 53.501666724969255
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 8.890001481631771e-07,
344
  "count": 1,
345
- "self": 8.890001481631771e-07
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.07674868400044943,
349
  "count": 1,
350
- "self": 0.0007499590001316392,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.07599872500031779,
354
  "count": 1,
355
- "self": 0.07599872500031779
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.7475182414054871,
6
+ "min": 0.71663498878479,
7
+ "max": 2.8489346504211426,
8
+ "count": 25
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 7104.4130859375,
12
+ "min": 6810.89892578125,
13
+ "max": 29081.923828125,
14
+ "count": 25
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 249944.0,
18
  "min": 9952.0,
19
+ "max": 249944.0,
20
+ "count": 25
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 249944.0,
24
  "min": 9952.0,
25
+ "max": 249944.0,
26
+ "count": 25
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.4374361038208,
30
+ "min": 0.394808828830719,
31
+ "max": 13.4374361038208,
32
+ "count": 25
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2606.862548828125,
36
+ "min": 76.59291076660156,
37
+ "max": 2735.1162109375,
38
+ "count": 25
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.071493054551812,
42
+ "min": 0.06355938853156141,
43
+ "max": 0.07763451731960089,
44
+ "count": 25
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.285972218207248,
48
+ "min": 0.25423755412624566,
49
+ "max": 0.3881725865980044,
50
+ "count": 25
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.17382255499707716,
54
+ "min": 0.14108746513203882,
55
+ "max": 0.2882686865095998,
56
+ "count": 25
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.6952902199883086,
60
+ "min": 0.5643498605281553,
61
+ "max": 1.3754066886270748,
62
+ "count": 25
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
+ "value": 1.91520980848e-05,
66
+ "min": 1.91520980848e-05,
67
+ "max": 0.0009783520021647998,
68
+ "count": 25
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
+ "value": 7.66083923392e-05,
72
+ "min": 7.66083923392e-05,
73
+ "max": 0.004693760030624001,
74
+ "count": 25
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
+ "value": 0.10229824,
78
+ "min": 0.10229824,
79
+ "max": 0.21740224,
80
+ "count": 25
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
+ "value": 0.40919296,
84
+ "min": 0.40919296,
85
+ "max": 1.0632512,
86
+ "count": 25
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
+ "value": 0.00012472048000000002,
90
+ "min": 0.00012472048000000002,
91
+ "max": 0.005870328480000001,
92
+ "count": 25
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
+ "value": 0.0004988819200000001,
96
+ "min": 0.0004988819200000001,
97
+ "max": 0.0281656224,
98
+ "count": 25
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
+ "count": 25
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
  "value": 8756.0,
108
  "min": 8756.0,
109
  "max": 10945.0,
110
+ "count": 25
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 26.477272727272727,
114
+ "min": 3.772727272727273,
115
+ "max": 26.636363636363637,
116
+ "count": 25
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1165.0,
120
+ "min": 166.0,
121
+ "max": 1465.0,
122
+ "count": 25
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 26.477272727272727,
126
+ "min": 3.772727272727273,
127
+ "max": 26.636363636363637,
128
+ "count": 25
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1165.0,
132
+ "min": 166.0,
133
+ "max": 1465.0,
134
+ "count": 25
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 25
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 25
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1767977742",
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 ./SnowballTarget.yaml --env=../../training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1767978274"
160
  },
161
+ "total": 532.3112778719997,
162
  "count": 1,
163
+ "self": 0.4286831940007687,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.024501590999534528,
167
  "count": 1,
168
+ "self": 0.024501590999534528
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 531.8580930869994,
172
  "count": 1,
173
+ "self": 0.4673537579665208,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.4818936770006985,
177
  "count": 1,
178
+ "self": 2.4818936770006985
179
  },
180
  "TrainerController.advance": {
181
+ "total": 528.8332635740326,
182
+ "count": 22728,
183
+ "self": 0.4606399049689571,
184
  "children": {
185
  "env_step": {
186
+ "total": 381.6540236930405,
187
+ "count": 22728,
188
+ "self": 298.851979642106,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 82.53021616796832,
192
+ "count": 22728,
193
+ "self": 1.568552725923837,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 80.96166344204448,
197
+ "count": 22728,
198
+ "self": 80.96166344204448
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.2718278829661358,
204
+ "count": 22728,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 529.6468840889474,
209
+ "count": 22728,
210
  "is_parallel": true,
211
+ "self": 267.56324332680924,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.002008778000345046,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0006225420020200545,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0013862359983249917,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0013862359983249917
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.06370068799969886,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0012191709993203403,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00038346000019373605,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00038346000019373605
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.05938122600036877,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.05938122600036877
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.002716830999816011,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0003291299999546027,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0023877009998614085,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0023877009998614085
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 262.0836407621382,
271
+ "count": 22727,
272
  "is_parallel": true,
273
+ "self": 12.365990891184083,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 6.582015843963745,
277
+ "count": 22727,
278
  "is_parallel": true,
279
+ "self": 6.582015843963745
280
  },
281
  "communicator.exchange": {
282
+ "total": 200.4483943029445,
283
+ "count": 22727,
284
  "is_parallel": true,
285
+ "self": 200.4483943029445
286
  },
287
  "steps_from_proto": {
288
+ "total": 42.68723972404587,
289
+ "count": 22727,
290
  "is_parallel": true,
291
+ "self": 7.9181404071123325,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 34.769099316933534,
295
+ "count": 227270,
296
  "is_parallel": true,
297
+ "self": 34.769099316933534
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 146.71859997602314,
311
+ "count": 22728,
312
+ "self": 0.6203085009537972,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 31.306125940061975,
316
+ "count": 22728,
317
+ "self": 30.834229514061917,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.47189642600005755,
321
+ "count": 5,
322
+ "self": 0.47189642600005755
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 114.79216553500737,
328
+ "count": 113,
329
+ "self": 46.65109521096747,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 68.1410703240399,
333
+ "count": 5760,
334
+ "self": 68.1410703240399
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 1.014999725157395e-06,
344
  "count": 1,
345
+ "self": 1.014999725157395e-06
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.07558106299984502,
349
  "count": 1,
350
+ "self": 0.000854279000122915,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.0747267839997221,
354
  "count": 1,
355
+ "self": 0.0747267839997221
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -4,8 +4,8 @@
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 16.818181818181817,
8
- "creation_time": 1767453527.948969,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
@@ -13,8 +13,8 @@
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 21.363636363636363,
17
- "creation_time": 1767453637.396343,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
@@ -22,8 +22,8 @@
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 24.363636363636363,
26
- "creation_time": 1767453745.5955017,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
@@ -31,29 +31,38 @@
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 24.727272727272727,
35
- "creation_time": 1767453850.394012,
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": 24.727272727272727,
44
- "creation_time": 1767453850.4820354,
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": 24.727272727272727,
54
- "creation_time": 1767453850.4820354,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 17.0,
8
+ "creation_time": 1767977850.138972,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
 
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
+ "reward": 23.454545454545453,
17
+ "creation_time": 1767977956.2623677,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
 
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 26.09090909090909,
26
+ "creation_time": 1767978062.9853947,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
 
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 26.636363636363637,
35
+ "creation_time": 1767978167.9243758,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 249944,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.onnx",
43
+ "reward": 27.09090909090909,
44
+ "creation_time": 1767978273.992623,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 250008,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-250008.onnx",
52
+ "reward": 27.09090909090909,
53
+ "creation_time": 1767978274.0730927,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-250008.pt"
56
  ]
57
  }
58
  ],
59
  "final_checkpoint": {
60
+ "steps": 250008,
61
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
62
+ "reward": 27.09090909090909,
63
+ "creation_time": 1767978274.0730927,
64
  "auxillary_file_paths": [
65
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-250008.pt"
66
  ]
67
  }
68
  },