Hugging Face's logo

TxAA
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
TxAA commited on
Commit
3e7e6c2
·
verified ·
1 Parent(s): a86d6f6

First Push

Browse files
Files changed (24) hide show
  1. SnowballTarget.onnx +2 -2
  2. SnowballTarget/SnowballTarget-145904.onnx +3 -0
  3. SnowballTarget/SnowballTarget-145904.pt +3 -0
  4. SnowballTarget/SnowballTarget-149984.onnx +2 -2
  5. SnowballTarget/SnowballTarget-149984.pt +2 -2
  6. SnowballTarget/SnowballTarget-199984.onnx +2 -2
  7. SnowballTarget/SnowballTarget-199984.pt +2 -2
  8. SnowballTarget/SnowballTarget-249944.onnx +3 -0
  9. SnowballTarget/SnowballTarget-249944.pt +3 -0
  10. SnowballTarget/SnowballTarget-299968.onnx +3 -0
  11. SnowballTarget/SnowballTarget-299968.pt +3 -0
  12. SnowballTarget/SnowballTarget-300608.onnx +3 -0
  13. SnowballTarget/SnowballTarget-300608.pt +3 -0
  14. SnowballTarget/SnowballTarget-49936.onnx +2 -2
  15. SnowballTarget/SnowballTarget-49936.pt +2 -2
  16. SnowballTarget/SnowballTarget-99960.onnx +2 -2
  17. SnowballTarget/SnowballTarget-99960.pt +2 -2
  18. SnowballTarget/checkpoint.pt +2 -2
  19. SnowballTarget/events.out.tfevents.1750134367.ec9fa0c92b7e.28463.0 +3 -0
  20. config.json +1 -1
  21. configuration.yaml +5 -5
  22. run_logs/Player-0.log +15 -18
  23. run_logs/timers.json +161 -161
  24. run_logs/training_status.json +35 -17
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d6790256c138b51274fe49e16119de9a1e444f33a55a407ff0ba4f5336928ac
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47e1b4ce56d806414133f00e8f2daf8d64a4eef045a34a7092c45ef91e67d812
3
+ size 813622
SnowballTarget/SnowballTarget-145904.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e606839aa0742d467e8ff755835c4c33ea4e6428835be4cadeef97db5b5af2df
3
+ size 101196
SnowballTarget/SnowballTarget-145904.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ad22dda42418fd3f0a183780892e4ff2004a1cc73f05b76fe14ff379b4756b6
3
+ size 570116
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55c4694456690788ac14268e1467dc56c95f10b556a3b1ae38671bed811113ca
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fb8e172522dadcc5f9bea839602f639e5a6105302d4109e985ad4889669a0c8
3
+ size 813622
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dde187b250118b393090ed3093bd043cbd3004853857c87f2873590ab3f0303f
3
- size 3850564
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:722e0ac6aa3fec94c0e3f41b5afc259d2977b61853287811d747a1ac76768fb8
3
+ size 4823812
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d6790256c138b51274fe49e16119de9a1e444f33a55a407ff0ba4f5336928ac
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:096e20a51d73eb17070a15f43386b0e40a54e5513beef4d7b6d463447b158639
3
+ size 813622
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:775c64314e7246d3e825bb4e73e8dcfeff7b1cfdd0b0c172b1bc20a8486c0b61
3
- size 3850564
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02939adb1f0462844722de47c1c6e857117bd52b76303971272da03ab33177bb
3
+ size 4823812
SnowballTarget/SnowballTarget-249944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5c6ea329e3c41a7830bd3f72c5b2f93c29a04806f42f46cfa9599ecce1afd2c
3
+ size 813622
SnowballTarget/SnowballTarget-249944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5c8dcebc83a8350e6ddc76d103cf9384cff31e5dbf1f2c23e022590e996191a
3
+ size 4823812
SnowballTarget/SnowballTarget-299968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47e1b4ce56d806414133f00e8f2daf8d64a4eef045a34a7092c45ef91e67d812
3
+ size 813622
SnowballTarget/SnowballTarget-299968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a3b3bfe2233eaa4f35c705852b006bbaf4591fb92af46e4fe346a898cb5e646
3
+ size 4823812
SnowballTarget/SnowballTarget-300608.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47e1b4ce56d806414133f00e8f2daf8d64a4eef045a34a7092c45ef91e67d812
3
+ size 813622
SnowballTarget/SnowballTarget-300608.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4778e4c556f62d47a9dfb90b9b6065d7a86e65d4a41f13f318ff6d52c0d1e7be
3
+ size 4823812
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2430d371ab3227463b00432c7601bcac489b3226e34fa2d9bd613f5bba3553c2
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a2aa6163704bfe4aa4f834c45c03033c8798d7f1346b1fba5cc2d7cf26ce1b1
3
+ size 813622
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9771b7f3ccdd8ca1140a64c8c000db6eaf94e9b174f08ffddaf607fabb3d671
3
- size 3850487
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00446836f5147e87d7a22037866372ff4ff763edb71982c5e92d0c2ed31ef3d9
3
+ size 4823735
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d88dfcdb48b239b821fb5a02f4f352c03efa936b5a39dbfd924066919b82b0a
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ccbd87ba1f0ee8da93ce9c576d0f14b0886a5f893540a8f11a23176ba5009f1
3
+ size 813622
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2780668aaf8bc5fc567079216af49627c4f9850aff48896ee8775c21897b747f
3
- size 3850487
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08d6d455379708dc2e3e27150a05137ef15cf408a9af34aa08955236790b26e4
3
+ size 4823735
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1bb0838e352a98dd2ab92cddf2398e9260793502c4194187422b21bcda71ab24
3
- size 3849717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bb3ac529adb6bf574ad9869f336b2f385f4d23cd7c468dd7463d05e6e19de3c
3
+ size 4822965
SnowballTarget/events.out.tfevents.1750134367.ec9fa0c92b7e.28463.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a14c6bc2c891d1f75465d73d1b52a4393ecee1b41c0c8a29eba5337ed22bfb0
3
+ size 32853
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": 0.003, "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": 300, "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, "even_checkpoints": false, "max_steps": 300000, "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
@@ -5,7 +5,7 @@ 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
@@ -17,7 +17,7 @@ behaviors:
17
  checkpoint_interval: 50000
18
  network_settings:
19
  normalize: false
20
- hidden_units: 256
21
  num_layers: 2
22
  vis_encode_type: simple
23
  memory: null
@@ -25,7 +25,7 @@ behaviors:
25
  deterministic: false
26
  reward_signals:
27
  extrinsic:
28
- gamma: 0.99
29
  strength: 1.0
30
  network_settings:
31
  normalize: false
@@ -38,7 +38,7 @@ behaviors:
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
- max_steps: 200000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: false
@@ -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: 0.003
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
 
17
  checkpoint_interval: 50000
18
  network_settings:
19
  normalize: false
20
+ hidden_units: 300
21
  num_layers: 2
22
  vis_encode_type: simple
23
  memory: null
 
25
  deterministic: false
26
  reward_signals:
27
  extrinsic:
28
+ gamma: 0.95
29
  strength: 1.0
30
  network_settings:
31
  normalize: false
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 300000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: false
 
70
  initialize_from: null
71
  load_model: false
72
  resume: false
73
+ force: true
74
  train_model: false
75
  inference: false
76
  results_dir: results
run_logs/Player-0.log CHANGED
@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
5
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
6
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
7
- Unable to load player prefs
8
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
9
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
- - Completed reload, in 0.083 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: 0.675098 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
@@ -169,22 +166,22 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 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]: 5458 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.6 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 17.9 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
@@ -213,13 +210,13 @@ Memory Statistics:
213
  Used Block count 1
214
  Peak Allocated bytes 1.0 MB
215
  [ALLOC_GFX_MAIN]
216
- Peak usage frame count: [32.0 KB-64.0 KB]: 4963 frames, [64.0 KB-128.0 KB]: 495 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 66.8 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 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
 
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 0.079 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: 0.623560 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 36
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 7.5 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 17.8 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]: 7554 frames, [64.0 KB-128.0 KB]: 645 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 66.4 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 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": 0.8825609683990479,
6
- "min": 0.8825609683990479,
7
- "max": 2.8550424575805664,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8387.859375,
12
- "min": 8387.859375,
13
- "max": 29144.2734375,
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": 13.015496253967285,
30
- "min": 0.2516481578350067,
31
- "max": 13.0677490234375,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2538.021728515625,
36
- "min": 48.81974411010742,
37
- "max": 2675.735595703125,
38
- "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.06306582486928057,
42
- "min": 0.06240164902598788,
43
- "max": 0.08274843645074939,
44
- "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.2522632994771223,
48
- "min": 0.24960659610395153,
49
- "max": 0.3761074514283488,
50
- "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.19895658444832354,
54
- "min": 0.14572787230980455,
55
- "max": 0.27945946032802266,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.7958263377932941,
60
- "min": 0.5829114892392182,
61
- "max": 1.3886851621609106,
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": 25.227272727272727,
114
- "min": 4.090909090909091,
115
- "max": 25.886363636363637,
116
- "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1110.0,
120
- "min": 180.0,
121
- "max": 1407.0,
122
- "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.227272727272727,
126
- "min": 4.090909090909091,
127
- "max": 25.886363636363637,
128
- "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1110.0,
132
- "min": 180.0,
133
- "max": 1407.0,
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": "1750130871",
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": "2.7.1+cu126",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1750131279"
160
  },
161
- "total": 407.9883321909997,
162
  "count": 1,
163
- "self": 0.432158026000252,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.023199219999696652,
167
  "count": 1,
168
- "self": 0.023199219999696652
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 407.53297494499975,
172
  "count": 1,
173
- "self": 0.32009736501549924,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.4623287449999225,
177
  "count": 1,
178
- "self": 3.4623287449999225
179
  },
180
  "TrainerController.advance": {
181
- "total": 403.6734330669842,
182
- "count": 18192,
183
- "self": 0.3503698769568473,
184
  "children": {
185
  "env_step": {
186
- "total": 287.76694650002764,
187
- "count": 18192,
188
- "self": 220.81512003406306,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 66.75641503897305,
192
- "count": 18192,
193
- "self": 1.1815939779885412,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 65.5748210609845,
197
- "count": 18192,
198
- "self": 65.5748210609845
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.1954114269915408,
204
- "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 406.3072446800229,
209
- "count": 18192,
210
  "is_parallel": true,
211
- "self": 211.8054435060194,
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": 0.005104694999772619,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0036813989991060225,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0014232960006665962,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0014232960006665962
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03441239799985851,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0005600789995696687,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00038924800037420937,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00038924800037420937
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03157980900004986,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03157980900004986
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0018832619998647715,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0003615419991547242,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0015217200007100473,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0015217200007100473
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 194.5018011740035,
271
- "count": 18191,
272
  "is_parallel": true,
273
- "self": 9.420915110028545,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.132842034025543,
277
- "count": 18191,
278
  "is_parallel": true,
279
- "self": 5.132842034025543
280
  },
281
  "communicator.exchange": {
282
- "total": 149.11309534700194,
283
- "count": 18191,
284
  "is_parallel": true,
285
- "self": 149.11309534700194
286
  },
287
  "steps_from_proto": {
288
- "total": 30.83494868294747,
289
- "count": 18191,
290
  "is_parallel": true,
291
- "self": 5.237341403956179,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 25.59760727899129,
295
- "count": 181910,
296
  "is_parallel": true,
297
- "self": 25.59760727899129
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 115.55611668999973,
311
- "count": 18192,
312
- "self": 0.3779235970450827,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 24.820622448954055,
316
- "count": 18192,
317
- "self": 24.439744479954243,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.38087796899981186,
321
- "count": 4,
322
- "self": 0.38087796899981186
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 90.35757064400059,
328
- "count": 90,
329
- "self": 36.79533735500354,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 53.56223328899705,
333
- "count": 4587,
334
- "self": 53.56223328899705
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 9.589998626324814e-07,
344
  "count": 1,
345
- "self": 9.589998626324814e-07
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.0771148090002498,
349
  "count": 1,
350
- "self": 0.0008023760005926306,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.07631243299965718,
354
  "count": 1,
355
- "self": 0.07631243299965718
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.8226982951164246,
6
+ "min": 0.8151152729988098,
7
+ "max": 2.8385403156280518,
8
+ "count": 30
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 8470.501953125,
12
+ "min": 7818.5859375,
13
+ "max": 28975.818359375,
14
+ "count": 30
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 299968.0,
18
  "min": 9952.0,
19
+ "max": 299968.0,
20
+ "count": 30
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 299968.0,
24
  "min": 9952.0,
25
+ "max": 299968.0,
26
+ "count": 30
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 2.73716402053833,
30
+ "min": 0.2946099042892456,
31
+ "max": 2.8057615756988525,
32
+ "count": 30
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 558.3814697265625,
36
+ "min": 57.154319763183594,
37
+ "max": 569.9742431640625,
38
+ "count": 30
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.06735629658557145,
42
+ "min": 0.06132185949165574,
43
+ "max": 0.07102779475806564,
44
+ "count": 30
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.33678148292785726,
48
+ "min": 0.24528743796662297,
49
+ "max": 0.3551389737903282,
50
+ "count": 30
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.1151236929729873,
54
+ "min": 0.10468905375284307,
55
+ "max": 0.15780233004513908,
56
+ "count": 30
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.5756184648649365,
60
+ "min": 0.4187562150113723,
61
+ "max": 0.7890116502256954,
62
+ "count": 30
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
+ "value": 5.2880098237333316e-05,
66
+ "min": 5.2880098237333316e-05,
67
+ "max": 0.0029458800018039998,
68
+ "count": 30
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
+ "value": 0.00026440049118666657,
72
+ "min": 0.00026440049118666657,
73
+ "max": 0.014234400025519999,
74
+ "count": 30
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
+ "value": 0.10176266666666667,
78
+ "min": 0.10176266666666667,
79
+ "max": 0.198196,
80
+ "count": 30
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
+ "value": 0.5088133333333333,
84
+ "min": 0.42025066666666666,
85
+ "max": 0.97448,
86
+ "count": 30
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
+ "value": 9.795706666666662e-05,
90
+ "min": 9.795706666666662e-05,
91
+ "max": 0.0049099804000000006,
92
+ "count": 30
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
+ "value": 0.0004897853333333331,
96
+ "min": 0.0004897853333333331,
97
+ "max": 0.023726551999999998,
98
+ "count": 30
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
+ "count": 30
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
+ "value": 10945.0,
108
  "min": 8756.0,
109
  "max": 10945.0,
110
+ "count": 30
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 26.745454545454546,
114
+ "min": 4.431818181818182,
115
+ "max": 27.522727272727273,
116
+ "count": 30
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1471.0,
120
+ "min": 195.0,
121
+ "max": 1494.0,
122
+ "count": 30
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 26.745454545454546,
126
+ "min": 4.431818181818182,
127
+ "max": 27.522727272727273,
128
+ "count": 30
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1471.0,
132
+ "min": 195.0,
133
+ "max": 1494.0,
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": "1750134366",
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 --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": "2.7.1+cu126",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1750134984"
160
  },
161
+ "total": 617.5898268199999,
162
  "count": 1,
163
+ "self": 0.4242266400005974,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.02051469699927111,
167
  "count": 1,
168
+ "self": 0.02051469699927111
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 617.145085483,
172
  "count": 1,
173
+ "self": 0.510020779005572,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.645923903000039,
177
  "count": 1,
178
+ "self": 2.645923903000039
179
  },
180
  "TrainerController.advance": {
181
+ "total": 613.9033552939936,
182
+ "count": 27328,
183
+ "self": 0.5512030380250508,
184
  "children": {
185
  "env_step": {
186
+ "total": 435.2854105390479,
187
+ "count": 27328,
188
+ "self": 335.42945103009333,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 99.54599657300514,
192
+ "count": 27328,
193
+ "self": 1.7795548820204203,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 97.76644169098472,
197
+ "count": 27328,
198
+ "self": 97.76644169098472
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.3099629359494429,
204
+ "count": 27328,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 615.3837970100285,
209
+ "count": 27328,
210
  "is_parallel": true,
211
+ "self": 320.6325693310464,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0019725530000869185,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0005746789984186762,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0013978740016682423,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0013978740016682423
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.05693476099986583,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0005850790003023576,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00034602100004121894,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00034602100004121894
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.054280879999168974,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.054280879999168974
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0017227810003532795,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0003785740018429351,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0013442069985103444,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0013442069985103444
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 294.7512276789821,
271
+ "count": 27327,
272
  "is_parallel": true,
273
+ "self": 14.211104192042512,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 7.789133433874667,
277
+ "count": 27327,
278
  "is_parallel": true,
279
+ "self": 7.789133433874667
280
  },
281
  "communicator.exchange": {
282
+ "total": 227.60525451303965,
283
+ "count": 27327,
284
  "is_parallel": true,
285
+ "self": 227.60525451303965
286
  },
287
  "steps_from_proto": {
288
+ "total": 45.14573554002527,
289
+ "count": 27327,
290
  "is_parallel": true,
291
+ "self": 7.8797047321313585,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 37.26603080789391,
295
+ "count": 273270,
296
  "is_parallel": true,
297
+ "self": 37.26603080789391
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 178.06674171692066,
311
+ "count": 27328,
312
+ "self": 0.625410519946854,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 38.640372097965155,
316
+ "count": 27328,
317
+ "self": 38.03764590196624,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.6027261959989119,
321
+ "count": 6,
322
+ "self": 0.6027261959989119
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 138.80095909900865,
328
+ "count": 136,
329
+ "self": 57.684035995044724,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 81.11692310396393,
333
+ "count": 6933,
334
+ "self": 81.11692310396393
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 1.0280000424245372e-06,
344
  "count": 1,
345
+ "self": 1.0280000424245372e-06
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.08578447900072206,
349
  "count": 1,
350
+ "self": 0.0011015160007445957,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.08468296299997746,
354
  "count": 1,
355
+ "self": 0.08468296299997746
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": 14.727272727272727,
8
- "creation_time": 1750130976.0541162,
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": 24.363636363636363,
17
- "creation_time": 1750131077.5487132,
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": 24.727272727272727,
26
- "creation_time": 1750131178.2289898,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
@@ -31,29 +31,47 @@
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 25.363636363636363,
35
- "creation_time": 1750131278.7201416,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
- "steps": 200112,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 25.363636363636363,
44
- "creation_time": 1750131278.8076997,
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
- "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 25.363636363636363,
54
- "creation_time": 1750131278.8076997,
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": 16.454545454545453,
8
+ "creation_time": 1750134470.1565642,
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": 23.545454545454547,
17
+ "creation_time": 1750134573.2789834,
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": 23.09090909090909,
26
+ "creation_time": 1750134675.3630228,
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": 26.09090909090909,
35
+ "creation_time": 1750134775.816186,
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": 27.545454545454547,
44
+ "creation_time": 1750134879.7608528,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 299968,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
52
+ "reward": 27.545454545454547,
53
+ "creation_time": 1750134983.5068662,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 300608,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-300608.onnx",
61
+ "reward": 27.545454545454547,
62
+ "creation_time": 1750134983.6470845,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-300608.pt"
65
  ]
66
  }
67
  ],
68
  "final_checkpoint": {
69
+ "steps": 300608,
70
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
71
+ "reward": 27.545454545454547,
72
+ "creation_time": 1750134983.6470845,
73
  "auxillary_file_paths": [
74
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-300608.pt"
75
  ]
76
  }
77
  },