Hugging Face's logo

GeerBox
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
GeerBox commited on
Commit
a43e451
·
verified ·
1 Parent(s): d2c7b4d

Second Push

Browse files
Files changed (29) hide show
  1. SnowballTarget.onnx +2 -2
  2. SnowballTarget/SnowballTarget-149984.onnx +2 -2
  3. SnowballTarget/SnowballTarget-149984.pt +2 -2
  4. SnowballTarget/SnowballTarget-199984.onnx +2 -2
  5. SnowballTarget/SnowballTarget-199984.pt +2 -2
  6. SnowballTarget/SnowballTarget-249944.onnx +3 -0
  7. SnowballTarget/SnowballTarget-249944.pt +3 -0
  8. SnowballTarget/SnowballTarget-299968.onnx +3 -0
  9. SnowballTarget/SnowballTarget-299968.pt +3 -0
  10. SnowballTarget/SnowballTarget-349992.onnx +3 -0
  11. SnowballTarget/SnowballTarget-349992.pt +3 -0
  12. SnowballTarget/SnowballTarget-399992.onnx +3 -0
  13. SnowballTarget/SnowballTarget-399992.pt +3 -0
  14. SnowballTarget/SnowballTarget-449952.onnx +3 -0
  15. SnowballTarget/SnowballTarget-449952.pt +3 -0
  16. SnowballTarget/SnowballTarget-479512.onnx +3 -0
  17. SnowballTarget/SnowballTarget-479512.pt +3 -0
  18. SnowballTarget/SnowballTarget-499952.onnx +3 -0
  19. SnowballTarget/SnowballTarget-499952.pt +3 -0
  20. SnowballTarget/SnowballTarget-500016.onnx +3 -0
  21. SnowballTarget/SnowballTarget-500016.pt +3 -0
  22. SnowballTarget/checkpoint.pt +2 -2
  23. SnowballTarget/events.out.tfevents.1754449827.a89c10424462.9739.0 +3 -0
  24. SnowballTarget/events.out.tfevents.1754451080.a89c10424462.15098.0 +3 -0
  25. config.json +1 -1
  26. configuration.yaml +5 -5
  27. run_logs/Player-0.log +17 -20
  28. run_logs/timers.json +173 -173
  29. run_logs/training_status.json +74 -29
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:898a8fd023b0a705e213f1fa3e9e63a464eb6c5681e1b62499f9f9459433e6e6
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07b751d301dac99243a31c8bc634dabc375909d49a3740ade799d2836b76f240
3
+ size 657877
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:983f627bac623f92eb10c1cdfc9c7f818a156f4bfc1e1a3c184f8d850aad02d6
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff02be92b3eaeeaa6b763cbd4e682054e7ff1e09eac25beea5bc9129304ff036
3
+ size 657877
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d5ddbb255ef0ca3f318bc986d5ac390189a97b79e985001f36719bfa8843279
3
- size 3850564
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:635131c1b868c54bb09591ea3bf0bd621f67ddf0a96e01b0da3d1be8edbc0ad7
3
+ size 3872655
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:898a8fd023b0a705e213f1fa3e9e63a464eb6c5681e1b62499f9f9459433e6e6
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94dcb9152a252c47cfdee046c38fa087cd4e7ed222d9d48cca596b0b85084ba8
3
+ size 657877
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b162433c627f3bebb51137b2b44c68c1e323ace5ed132f6ed4ca44ffed3fbe24
3
- size 3850564
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:148a22c1bcc4e73a947a115464b0fda4d66598dd447af8c9b849ce8c3ec25a52
3
+ size 3872655
SnowballTarget/SnowballTarget-249944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baa524f0c98acebe2f249231d04637892b403c40d010d98a0eb873eaf7a1a9cf
3
+ size 657877
SnowballTarget/SnowballTarget-249944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c26e83afea0994ccff6b735e52a7a33dbd07e7960b7893550ffa90db32d8212d
3
+ size 3872655
SnowballTarget/SnowballTarget-299968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e047ae2c73c858e8185ccbea649824bb3dbaaa7a575c58c6e002b96574f24e1
3
+ size 657877
SnowballTarget/SnowballTarget-299968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c645c1df019a81ff50f68962296e7cd2d832028b1dddacf6583bb3b38080181
3
+ size 3872655
SnowballTarget/SnowballTarget-349992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3911e41165ba2133abc043c8aad4884096d02cf26f3868cfdfcb68fc2348ec9c
3
+ size 657877
SnowballTarget/SnowballTarget-349992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8f5d93a8649fe8d215df95373b3cb2feabb510695d82896fe471a3704733284
3
+ size 3872655
SnowballTarget/SnowballTarget-399992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41db4dfc602f3248ae743fc1c46ba7a67c5ffcce0d9fb8131643e4865e85ef5b
3
+ size 657877
SnowballTarget/SnowballTarget-399992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0310c00ee51b34d432aa3fcbefdf42cccfbf1e1a1834a03c4090fe9c66f971ea
3
+ size 3872655
SnowballTarget/SnowballTarget-449952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b831ff4d89916eb44d196ae3b70a14a9bfc4a52b1cdec37f01f3cf26eef60fe
3
+ size 657877
SnowballTarget/SnowballTarget-449952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30d74da7da03e650f0984dd5a5f662dc692ccc78dff7dbe17e39e4a37a4d4f2
3
+ size 3872655
SnowballTarget/SnowballTarget-479512.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62064ca5f1da8fa2c8a81f9558b0f71e8f4ee5f55be14b1dfe7c6f0b70fb8614
3
+ size 657877
SnowballTarget/SnowballTarget-479512.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:367a8b18ff9216c1535e1d831868fefe91b45c0db8d8c788ed8516029a811993
3
+ size 3872655
SnowballTarget/SnowballTarget-499952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe5f81d9f4813efa34eff457fa404cd1e69b38bbad74ecc096a090317862f271
3
+ size 657877
SnowballTarget/SnowballTarget-499952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e76bcb2c45082edbf714982ecc89624891d0b48bec50c9f40e5fbf0a0b46a558
3
+ size 3872655
SnowballTarget/SnowballTarget-500016.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07b751d301dac99243a31c8bc634dabc375909d49a3740ade799d2836b76f240
3
+ size 657877
SnowballTarget/SnowballTarget-500016.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66b7ad4a5dbdbf2b9b550fc26d5964f3ca255d50a256cd45071082966f572782
3
+ size 3872655
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:816be25d19e082b214e1050b821f9b93c325c025689993ed8b0b4d920246df9d
3
- size 3849717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a3a5bfc323620c354ada45d2957affd320aa50ecd9233fcb463dbf86b855006
3
+ size 3871478
SnowballTarget/events.out.tfevents.1754449827.a89c10424462.9739.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a9a689ee1459e8613796fbadbf3b18e33fc20723c07bc3b730a444dd73033f6
3
+ size 51135
SnowballTarget/events.out.tfevents.1754451080.a89c10424462.15098.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f800002617b300013d67a8c4523e2054b0761c23342005cd24cd59206cf4b49c
3
+ size 2900
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": 0.0001, "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": true, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.999, "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": 500000, "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": true, "force": false, "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
@@ -16,7 +16,7 @@ behaviors:
16
  epsilon_schedule: linear
17
  checkpoint_interval: 50000
18
  network_settings:
19
- normalize: false
20
  hidden_units: 256
21
  num_layers: 2
22
  vis_encode_type: simple
@@ -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
@@ -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
 
5
  hyperparameters:
6
  batch_size: 128
7
  buffer_size: 2048
8
+ learning_rate: 0.0001
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
 
16
  epsilon_schedule: linear
17
  checkpoint_interval: 50000
18
  network_settings:
19
+ normalize: true
20
  hidden_units: 256
21
  num_layers: 2
22
  vis_encode_type: simple
 
25
  deterministic: false
26
  reward_signals:
27
  extrinsic:
28
+ gamma: 0.999
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: 500000
42
  time_horizon: 64
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 0.088 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: 0.734163 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
@@ -169,23 +166,23 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 40
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
- Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 22.6 MB
182
- Peak Large allocation bytes 16.0 MB
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [1.0 MB-2.0 MB]: 5458 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 1.9 MB
188
- Peak Large allocation bytes 0 B
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
191
  Used Block Count 1
@@ -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]: 5148 frames, [64.0 KB-128.0 KB]: 310 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 66.4 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 0.086 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: 0.706347 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]: 550 frames, [16.0 KB-32.0 KB]: 9 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 28
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]: 560 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 5.3 MB
179
+ Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 560 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
188
  Used Block Count 1
 
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]: 552 frames, [64.0 KB-128.0 KB]: 8 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 65.6 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 560 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]: 560 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]: 559 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]: 560 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]: 560 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": 0.7150829434394836,
6
- "min": 0.7035196423530579,
7
- "max": 2.8546743392944336,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 6796.1484375,
12
- "min": 6796.1484375,
13
- "max": 29140.515625,
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": 13.03364086151123,
30
- "min": 0.4669889211654663,
31
- "max": 13.03364086151123,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2541.56005859375,
36
- "min": 90.5958480834961,
37
- "max": 2633.62060546875,
38
- "count": 20
 
 
 
 
 
 
 
 
 
 
 
 
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.06897075751618889,
42
- "min": 0.061393152202557144,
43
- "max": 0.07416319965028806,
44
- "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.27588303006475556,
48
- "min": 0.2542521318021713,
49
- "max": 0.3708159982514403,
50
- "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.19258074590242377,
54
- "min": 0.12373484313195826,
55
- "max": 0.2846018724581775,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.7703229836096951,
60
- "min": 0.49493937252783304,
61
- "max": 1.3717303807828942,
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": 25.75,
114
- "min": 3.8863636363636362,
115
- "max": 26.054545454545455,
116
- "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1133.0,
120
- "min": 171.0,
121
- "max": 1433.0,
122
- "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.75,
126
- "min": 3.8863636363636362,
127
- "max": 26.054545454545455,
128
- "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1133.0,
132
- "min": 171.0,
133
- "max": 1433.0,
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": "1754448757",
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": "1754449214"
160
  },
161
- "total": 456.937035743,
162
  "count": 1,
163
- "self": 0.4891850080000495,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.023609720999957062,
167
  "count": 1,
168
- "self": 0.023609720999957062
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 456.424241014,
172
  "count": 1,
173
- "self": 0.4301373400076045,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.4820336779998797,
177
  "count": 1,
178
- "self": 3.4820336779998797
179
  },
180
  "TrainerController.advance": {
181
- "total": 452.4285454079925,
182
- "count": 18192,
183
- "self": 0.4449020849979206,
184
  "children": {
185
  "env_step": {
186
- "total": 324.11776385300914,
187
- "count": 18192,
188
- "self": 249.39269874001025,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 74.47462456499306,
192
- "count": 18192,
193
- "self": 1.3585001599826683,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 73.1161244050104,
197
- "count": 18192,
198
- "self": 73.1161244050104
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.2504405480058267,
204
- "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 454.83355754000877,
209
- "count": 18192,
210
  "is_parallel": true,
211
- "self": 236.2475705060251,
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": 0.006069779999961611,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.004508330999897225,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0015614490000643855,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0015614490000643855
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.036356473000068945,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0005637979998027731,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00040063200003714883,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00040063200003714883
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03359538200015777,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03359538200015777
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0017966610000712535,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0003362809995905991,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0014603800004806544,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0014603800004806544
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 218.58598703398366,
271
- "count": 18191,
272
  "is_parallel": true,
273
- "self": 10.41881847095351,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.538089104997198,
277
- "count": 18191,
278
  "is_parallel": true,
279
- "self": 5.538089104997198
280
  },
281
  "communicator.exchange": {
282
- "total": 169.77627043101052,
283
- "count": 18191,
284
  "is_parallel": true,
285
- "self": 169.77627043101052
286
  },
287
  "steps_from_proto": {
288
- "total": 32.85280902702243,
289
- "count": 18191,
290
  "is_parallel": true,
291
- "self": 5.982666593999284,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 26.870142433023148,
295
- "count": 181910,
296
  "is_parallel": true,
297
- "self": 26.870142433023148
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 127.86587946998543,
311
- "count": 18192,
312
- "self": 0.5700468169827673,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 27.280328555001915,
316
- "count": 18192,
317
- "self": 26.804713067002012,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.47561548799990305,
321
- "count": 4,
322
- "self": 0.47561548799990305
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 100.01550409800075,
328
- "count": 90,
329
- "self": 41.29640787298604,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 58.71909622501471,
333
- "count": 4587,
334
- "self": 58.71909622501471
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 8.130000423989259e-07,
344
  "count": 1,
345
- "self": 8.130000423989259e-07
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.0835237750000033,
349
  "count": 1,
350
- "self": 0.0009112819998335908,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.0826124930001697,
354
  "count": 1,
355
- "self": 0.0826124930001697
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.9811392426490784,
6
+ "min": 0.9519923329353333,
7
+ "max": 0.9945018291473389,
8
+ "count": 3
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 9411.087890625,
12
+ "min": 700.1292724609375,
13
+ "max": 9717.9375,
14
+ "count": 3
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 499952.0,
18
+ "min": 479960.0,
19
+ "max": 499952.0,
20
+ "count": 3
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 499952.0,
24
+ "min": 479960.0,
25
+ "max": 499952.0,
26
+ "count": 3
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 118.75331115722656,
30
+ "min": 117.22108459472656,
31
+ "max": 118.75331115722656,
32
+ "count": 3
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 24225.67578125,
36
+ "min": 820.547607421875,
37
+ "max": 24225.67578125,
38
+ "count": 3
39
+ },
40
+ "SnowballTarget.IsTraining.mean": {
41
+ "value": 1.0,
42
+ "min": 1.0,
43
+ "max": 1.0,
44
+ "count": 3
45
+ },
46
+ "SnowballTarget.IsTraining.sum": {
47
+ "value": 1.0,
48
+ "min": 1.0,
49
+ "max": 1.0,
50
+ "count": 3
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.07010364909062856,
54
+ "min": 0.07010364909062856,
55
+ "max": 0.0752406652269094,
56
+ "count": 2
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.3505182454531428,
60
+ "min": 0.3009626609076376,
61
+ "max": 0.3505182454531428,
62
+ "count": 2
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 1.0401250626526628,
66
+ "min": 1.0401250626526628,
67
+ "max": 1.1791614168049658,
68
+ "count": 2
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 5.200625313263314,
72
+ "min": 4.716645667219863,
73
+ "max": 5.200625313263314,
74
+ "count": 2
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 1.0352989647999984e-06,
78
+ "min": 1.0352989647999984e-06,
79
+ "max": 3.0152969848000013e-06,
80
+ "count": 2
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 5.176494823999992e-06,
84
+ "min": 5.176494823999992e-06,
85
+ "max": 1.2061187939200005e-05,
86
+ "count": 2
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10103520000000002,
90
+ "min": 0.10103520000000002,
91
+ "max": 0.1030152,
92
+ "count": 2
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.5051760000000001,
96
+ "min": 0.4120608,
97
+ "max": 0.5051760000000001,
98
+ "count": 2
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 6.165647999999992e-05,
102
+ "min": 6.165647999999992e-05,
103
+ "max": 0.00016045848000000008,
104
+ "count": 2
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.0003082823999999996,
108
+ "min": 0.0003082823999999996,
109
+ "max": 0.0006418339200000003,
110
+ "count": 2
111
  },
112
  "SnowballTarget.Environment.EpisodeLength.mean": {
113
  "value": 199.0,
114
  "min": 199.0,
115
  "max": 199.0,
116
+ "count": 2
117
  },
118
  "SnowballTarget.Environment.EpisodeLength.sum": {
119
+ "value": 10945.0,
120
  "min": 8756.0,
121
  "max": 10945.0,
122
+ "count": 2
123
  },
124
  "SnowballTarget.Environment.CumulativeReward.mean": {
125
+ "value": 25.818181818181817,
126
+ "min": 25.636363636363637,
127
+ "max": 25.818181818181817,
128
+ "count": 2
129
  },
130
  "SnowballTarget.Environment.CumulativeReward.sum": {
131
+ "value": 1420.0,
132
+ "min": 1128.0,
133
+ "max": 1420.0,
134
+ "count": 2
135
  },
136
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
137
+ "value": 25.818181818181817,
138
+ "min": 25.636363636363637,
139
+ "max": 25.818181818181817,
140
+ "count": 2
141
  },
142
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
143
+ "value": 1420.0,
144
+ "min": 1128.0,
145
+ "max": 1420.0,
146
+ "count": 2
 
 
 
 
 
 
 
 
 
 
 
 
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1754451080",
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": "2.7.1+cu126",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1754451134"
160
  },
161
+ "total": 54.574341497000205,
162
  "count": 1,
163
+ "self": 0.47651181600031123,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.022783994999826973,
167
  "count": 1,
168
+ "self": 0.022783994999826973
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 54.07504568600007,
172
  "count": 1,
173
+ "self": 0.04649125301011736,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.255951511999683,
177
  "count": 1,
178
+ "self": 2.255951511999683
179
  },
180
  "TrainerController.advance": {
181
+ "total": 51.66140153299011,
182
+ "count": 1864,
183
+ "self": 0.04556924597454781,
184
  "children": {
185
  "env_step": {
186
+ "total": 35.19539097300412,
187
+ "count": 1864,
188
+ "self": 26.57316563000677,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 8.594578837008157,
192
+ "count": 1864,
193
+ "self": 0.14635792001445225,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 8.448220916993705,
197
+ "count": 1864,
198
+ "self": 8.448220916993705
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.027646505989196157,
204
+ "count": 1864,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 53.47082080098744,
209
+ "count": 1864,
210
  "is_parallel": true,
211
+ "self": 30.205245973983892,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.002046512000106304,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.000671051000153966,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0013754609999523382,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0013754609999523382
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.0355443829998876,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0005598339994321577,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0003971500000261585,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0003971500000261585
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03277499900013936,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03277499900013936
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0018124000002899265,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00034252600016770884,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0014698740001222177,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0014698740001222177
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 23.265574827003547,
271
+ "count": 1863,
272
  "is_parallel": true,
273
+ "self": 1.086245167006382,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 0.5792968029982148,
277
+ "count": 1863,
278
  "is_parallel": true,
279
+ "self": 0.5792968029982148
280
  },
281
  "communicator.exchange": {
282
+ "total": 18.181196178997652,
283
+ "count": 1863,
284
  "is_parallel": true,
285
+ "self": 18.181196178997652
286
  },
287
  "steps_from_proto": {
288
+ "total": 3.4188366780012984,
289
+ "count": 1863,
290
  "is_parallel": true,
291
+ "self": 0.6422251270219022,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 2.7766115509793963,
295
+ "count": 18630,
296
  "is_parallel": true,
297
+ "self": 2.7766115509793963
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 16.42044131401144,
311
+ "count": 1864,
312
+ "self": 0.0626499330014667,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 5.32722642500994,
316
+ "count": 1864,
317
+ "self": 5.188741588009634,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.13848483700030556,
321
+ "count": 1,
322
+ "self": 0.13848483700030556
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 11.030564956000035,
328
+ "count": 9,
329
+ "self": 4.442429172993798,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 6.588135783006237,
333
+ "count": 456,
334
+ "self": 6.588135783006237
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 1.0120002116309479e-06,
344
  "count": 1,
345
+ "self": 1.0120002116309479e-06
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.11120037599994248,
349
  "count": 1,
350
+ "self": 0.0010221789998468012,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.11017819700009568,
354
  "count": 1,
355
+ "self": 0.11017819700009568
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -2,58 +2,103 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 16.454545454545453,
8
- "creation_time": 1754448873.7854123,
9
  "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
12
  },
13
  {
14
- "steps": 99960,
15
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 24.454545454545453,
17
- "creation_time": 1754448986.3227324,
18
  "auxillary_file_paths": [
19
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
21
  },
22
  {
23
- "steps": 149984,
24
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 24.90909090909091,
26
- "creation_time": 1754449099.5068033,
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": 25.90909090909091,
35
- "creation_time": 1754449213.490398,
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": 25.90909090909091,
44
- "creation_time": 1754449213.585961,
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": 25.90909090909091,
54
- "creation_time": 1754449213.585961,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 149984,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
7
+ "reward": 21.181818181818183,
8
+ "creation_time": 1754450214.7086143,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 199984,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
16
+ "reward": 23.181818181818183,
17
+ "creation_time": 1754450341.2689095,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 249944,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.onnx",
25
+ "reward": 25.09090909090909,
26
+ "creation_time": 1754450470.2060246,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 299968,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
34
+ "reward": 25.545454545454547,
35
+ "creation_time": 1754450600.245744,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 349992,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.onnx",
43
+ "reward": 25.181818181818183,
44
+ "creation_time": 1754450726.2367063,
45
+ "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 399992,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.onnx",
52
+ "reward": 25.818181818181817,
53
+ "creation_time": 1754450852.0708408,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 449952,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.onnx",
61
+ "reward": 24.545454545454547,
62
+ "creation_time": 1754450980.471984,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 479512,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-479512.onnx",
70
+ "reward": 26.454545454545453,
71
+ "creation_time": 1754451054.014584,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-479512.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 499952,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499952.onnx",
79
+ "reward": 25.454545454545453,
80
+ "creation_time": 1754451134.127511,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-499952.pt"
83
  ]
84
  },
85
  {
86
+ "steps": 500016,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-500016.onnx",
88
+ "reward": 25.454545454545453,
89
+ "creation_time": 1754451134.2491248,
90
  "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-500016.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 500016,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 25.454545454545453,
99
+ "creation_time": 1754451134.2491248,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-500016.pt"
102
  ]
103
  }
104
  },