Hugging Face's logo

whywynn
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
whywynn commited on
Commit
873cfe7
•
1 Parent(s): 0241bd4

First Push

Browse files
Files changed (28) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-499952.onnx +3 -0
  3. SnowballTarget/SnowballTarget-499952.pt +3 -0
  4. SnowballTarget/SnowballTarget-549976.onnx +3 -0
  5. SnowballTarget/SnowballTarget-549976.pt +3 -0
  6. SnowballTarget/SnowballTarget-599976.onnx +3 -0
  7. SnowballTarget/SnowballTarget-599976.pt +3 -0
  8. SnowballTarget/SnowballTarget-649936.onnx +3 -0
  9. SnowballTarget/SnowballTarget-649936.pt +3 -0
  10. SnowballTarget/SnowballTarget-699960.onnx +3 -0
  11. SnowballTarget/SnowballTarget-699960.pt +3 -0
  12. SnowballTarget/SnowballTarget-749960.onnx +3 -0
  13. SnowballTarget/SnowballTarget-749960.pt +3 -0
  14. SnowballTarget/SnowballTarget-799984.onnx +3 -0
  15. SnowballTarget/SnowballTarget-799984.pt +3 -0
  16. SnowballTarget/SnowballTarget-849944.onnx +3 -0
  17. SnowballTarget/SnowballTarget-849944.pt +3 -0
  18. SnowballTarget/SnowballTarget-899968.onnx +3 -0
  19. SnowballTarget/SnowballTarget-899968.pt +3 -0
  20. SnowballTarget/SnowballTarget-900288.onnx +3 -0
  21. SnowballTarget/SnowballTarget-900288.pt +3 -0
  22. SnowballTarget/checkpoint.pt +1 -1
  23. SnowballTarget/events.out.tfevents.1691789717.2e0f452bb9be.24090.0 +3 -0
  24. config.json +1 -1
  25. configuration.yaml +2 -2
  26. run_logs/Player-0.log +15 -18
  27. run_logs/timers.json +163 -163
  28. 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 sha256:458d5189465daaebb5de9c1f9e5f20cc8812089be72fab270936da4727a16458
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41a99857e918b9d3481a510debbf9f86768fd8f18340cadf248eff21b66fb3ea
3
  size 646532
SnowballTarget/SnowballTarget-499952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecefbae8a2e1b041e6af93711e48ab059ff1369b62638ad4173f014b4f99fbf9
3
+ size 646532
SnowballTarget/SnowballTarget-499952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1508ce0e4527273e19ebbd1a86b0fe6ee5cc8ae4191181f748b6927f7b3cf76
3
+ size 3843968
SnowballTarget/SnowballTarget-549976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60f9b3af818bc869e5e255abc288e8dab6b0d58427e4ed347e43e2e529c662d
3
+ size 646532
SnowballTarget/SnowballTarget-549976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:020d6a4f5fb8e47b4daa2983fd27a1c43adcc296d2d39c280d8982e5ce663a0a
3
+ size 3843968
SnowballTarget/SnowballTarget-599976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d64fd1e3cd7d0f83cd42a597eb1ef5453cf57316f9e5f5e6f2ab4e231531bce9
3
+ size 646532
SnowballTarget/SnowballTarget-599976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebc5acde1f5996cf450080e22516d563af186255f89ebf4db1c5e0af56527025
3
+ size 3843968
SnowballTarget/SnowballTarget-649936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2f65854a882be37192c73ed623af47756fb97e31a1577a814c3ea14fa64b9c6
3
+ size 646532
SnowballTarget/SnowballTarget-649936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c70308bd53025830d974e9c2bf5c6747ea9aff769d943352d57539226a740078
3
+ size 3843968
SnowballTarget/SnowballTarget-699960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c6d1f2921d99e64d1a838c5f5365f25de7a5bb8694a8d8fc40763f6105b46d7
3
+ size 646532
SnowballTarget/SnowballTarget-699960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b7bf9cf2002c294a2f6637c3cd2ddfaa8634b056f600b89bf01389cfda3b668
3
+ size 3843968
SnowballTarget/SnowballTarget-749960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:557895900392961b2fe2802443ec99b00e4c268f1681e94312b53e6e47e4ca0b
3
+ size 646532
SnowballTarget/SnowballTarget-749960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa67be71d8d664ad36b367c0d1ee9a7d8420ae55a3569dba8a05b4a7a5457dd1
3
+ size 3843968
SnowballTarget/SnowballTarget-799984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef17a8b6b74a4a47f272799746d8baa221ffdda739ef5dc234245723cf48f8b3
3
+ size 646532
SnowballTarget/SnowballTarget-799984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d760f4b75fc3f433919f181a49212ecfc63a774c95f3029c8c425bd2c52c485
3
+ size 3843968
SnowballTarget/SnowballTarget-849944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d735660a733a1203f3d998090b8031c16e7d6143314bd24eab73ead5c9632251
3
+ size 646532
SnowballTarget/SnowballTarget-849944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2e86112f0926bac9bd96dc2bc89585caf64d87a086d1190eee2eb044eb03c12
3
+ size 3843968
SnowballTarget/SnowballTarget-899968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41a99857e918b9d3481a510debbf9f86768fd8f18340cadf248eff21b66fb3ea
3
+ size 646532
SnowballTarget/SnowballTarget-899968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:442f4366b63d731bcf1cf70e357f440012a7394a56b564584083ba67ec96595e
3
+ size 3843968
SnowballTarget/SnowballTarget-900288.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41a99857e918b9d3481a510debbf9f86768fd8f18340cadf248eff21b66fb3ea
3
+ size 646532
SnowballTarget/SnowballTarget-900288.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01265761bc51018d6cace1a78cd6ed06c65d35af1a42e55f35eb729f92631aa7
3
+ size 3843968
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3425eb360ef138a6807c9d78a67810a9df705b776843b9abc5b00436ce396dbf
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01265761bc51018d6cace1a78cd6ed06c65d35af1a42e55f35eb729f92631aa7
3
  size 3843968
SnowballTarget/events.out.tfevents.1691789717.2e0f452bb9be.24090.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb9b98ce7f443b0a347e46fa407be3524f452a75055fd7caeb4c381b680eefcb
3
+ size 334633
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 3e-06, "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": 0.9, "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": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 3e-06, "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": 0.9, "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": 900000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -38,7 +38,7 @@ behaviors:
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
- max_steps: 200000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
@@ -67,7 +67,7 @@ checkpoint_settings:
67
  run_id: SnowballTarget1
68
  initialize_from: null
69
  load_model: false
70
- resume: false
71
  force: false
72
  train_model: false
73
  inference: false
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 900000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
 
67
  run_id: SnowballTarget1
68
  initialize_from: null
69
  load_model: false
70
+ resume: true
71
  force: false
72
  train_model: false
73
  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 0.129 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: 0.943126 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]: 5369 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
57
  Initial Block Size 4.0 MB
58
  Current Block Size 4.0 MB
59
  Peak Allocated Bytes 2.0 MB
@@ -169,22 +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: [16.0 MB-32.0 MB]: 5461 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 22.7 MB
182
  Peak Large allocation bytes 16.0 MB
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [1.0 MB-2.0 MB]: 5461 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
@@ -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]: 4977 frames, [64.0 KB-128.0 KB]: 484 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]: 5461 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]: 5461 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]: 5460 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]: 5461 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]: 5461 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 0.140 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: 0.901104 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]: 18784 frames, [16.0 KB-32.0 KB]: 318 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 45
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: [16.0 MB-32.0 MB]: 19103 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 28.5 MB
179
  Peak Large allocation bytes 16.0 MB
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [1.0 MB-2.0 MB]: 19103 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 1.8 MB
185
  Peak Large allocation bytes 0 B
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]: 16482 frames, [64.0 KB-128.0 KB]: 2621 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 66.8 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 19103 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]: 19103 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]: 19102 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]: 19103 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]: 19103 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -2,213 +2,213 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 2.8896782398223877,
6
- "min": 2.8896782398223877,
7
- "max": 2.890336751937866,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 27622.43359375,
12
- "min": 27433.9375,
13
- "max": 29818.41796875,
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": 0.15598002076148987,
30
- "min": 0.0047662751749157906,
31
- "max": 0.16870032250881195,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 30.416105270385742,
36
- "min": 0.9246573448181152,
37
- "max": 34.58356475830078,
38
- "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
- "count": 20
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
- "value": 8756.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
- "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06415645566948133,
54
- "min": 0.06399432363946735,
55
- "max": 0.07360126287676394,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.25662582267792533,
60
- "min": 0.2559772945578694,
61
- "max": 0.3616826339127204,
62
- "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.0472514656025405,
66
- "min": 0.03612691259888165,
67
- "max": 0.06508046232264343,
68
- "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.189005862410162,
72
- "min": 0.1445076503955266,
73
- "max": 0.26688022831199215,
74
- "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 8.091730600000007e-08,
78
- "min": 8.091730600000007e-08,
79
- "max": 2.918822706e-06,
80
- "count": 20
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 3.236692240000003e-07,
84
- "min": 3.236692240000003e-07,
85
- "max": 1.3851638279999999e-05,
86
- "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.10269400000000001,
90
- "min": 0.10269400000000001,
91
- "max": 0.19729400000000002,
92
- "count": 20
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.41077600000000003,
96
- "min": 0.41077600000000003,
97
- "max": 0.96172,
98
- "count": 20
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
- "value": 0.0001444306000000001,
102
- "min": 0.0001444306000000001,
103
- "max": 0.0048649706,
104
- "count": 20
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.0005777224000000004,
108
- "min": 0.0005777224000000004,
109
- "max": 0.023089828,
110
- "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 3.3181818181818183,
114
- "min": 2.3777777777777778,
115
- "max": 3.3181818181818183,
116
- "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 146.0,
120
- "min": 107.0,
121
- "max": 176.0,
122
- "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 3.3181818181818183,
126
- "min": 2.3777777777777778,
127
- "max": 3.3181818181818183,
128
- "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 146.0,
132
- "min": 107.0,
133
- "max": 176.0,
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": "1691785540",
152
  "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
153
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "0.31.0.dev0",
155
  "mlagents_envs_version": "0.31.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
- "end_time_seconds": "1691786061"
160
  },
161
- "total": 520.9244606269999,
162
  "count": 1,
163
- "self": 0.4931045139996968,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.06581045600000834,
167
  "count": 1,
168
- "self": 0.06581045600000834
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 520.3655456570002,
172
  "count": 1,
173
- "self": 0.6444751849940076,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 5.073664254999812,
177
  "count": 1,
178
- "self": 5.073664254999812
179
  },
180
  "TrainerController.advance": {
181
- "total": 514.4944833930062,
182
- "count": 18201,
183
- "self": 0.3376619700034098,
184
  "children": {
185
  "env_step": {
186
- "total": 514.1568214230028,
187
- "count": 18201,
188
- "self": 375.03920087500114,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 138.78077767699142,
192
- "count": 18201,
193
- "self": 2.055499486009012,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 136.7252781909824,
197
- "count": 18201,
198
- "self": 136.7252781909824
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.3368428710102762,
204
- "count": 18201,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 518.4026777910015,
209
- "count": 18201,
210
  "is_parallel": true,
211
- "self": 243.52079856098862,
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": 0.007281914000031975,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0049838659999750234,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0022980480000569514,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0022980480000569514
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.040112281999881816,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006382570002188004,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0003672420000384591,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0003672420000384591
244
  },
245
  "communicator.exchange": {
246
- "total": 0.036837975999787886,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.036837975999787886
250
  },
251
  "steps_from_proto": {
252
- "total": 0.00226880699983667,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00043515799984561454,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0018336489999910555,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0018336489999910555
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 274.8818792300128,
271
- "count": 18200,
272
  "is_parallel": true,
273
- "self": 11.577232592019072,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.9928607519805155,
277
- "count": 18200,
278
  "is_parallel": true,
279
- "self": 5.9928607519805155
280
  },
281
  "communicator.exchange": {
282
- "total": 216.49744649901754,
283
- "count": 18200,
284
  "is_parallel": true,
285
- "self": 216.49744649901754
286
  },
287
  "steps_from_proto": {
288
- "total": 40.8143393869957,
289
- "count": 18200,
290
  "is_parallel": true,
291
- "self": 7.838683240930322,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 32.975656146065376,
295
- "count": 182000,
296
  "is_parallel": true,
297
- "self": 32.975656146065376
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00012842900014220504,
313
  "count": 1,
314
- "self": 0.00012842900014220504,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 510.10041741493774,
324
- "count": 491033,
325
  "is_parallel": true,
326
- "self": 11.649732775948223,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 281.4376397579906,
330
- "count": 491033,
331
  "is_parallel": true,
332
- "self": 280.605716058991,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 0.831923698999617,
336
- "count": 4,
337
  "is_parallel": true,
338
- "self": 0.831923698999617
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 217.0130448809989,
344
- "count": 90,
345
  "is_parallel": true,
346
- "self": 87.36269089900338,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 129.65035398199552,
350
- "count": 4587,
351
  "is_parallel": true,
352
- "self": 129.65035398199552
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.1527943950000008,
364
  "count": 1,
365
- "self": 0.0009562760001244897,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.15183811899987631,
369
  "count": 1,
370
- "self": 0.15183811899987631
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 2.86368465423584,
6
+ "min": 2.86368465423584,
7
+ "max": 2.8896350860595703,
8
+ "count": 70
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 29452.99609375,
12
+ "min": 27148.046875,
13
+ "max": 29764.734375,
14
+ "count": 70
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 899968.0,
18
+ "min": 209936.0,
19
+ "max": 899968.0,
20
+ "count": 70
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 899968.0,
24
+ "min": 209936.0,
25
+ "max": 899968.0,
26
+ "count": 70
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 0.20816949009895325,
30
+ "min": 0.13810323178768158,
31
+ "max": 0.22446715831756592,
32
+ "count": 70
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 42.466575622558594,
36
+ "min": 26.930130004882812,
37
+ "max": 44.093170166015625,
38
+ "count": 70
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 70
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 70
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.07152454630243786,
54
+ "min": 0.06032311512236072,
55
+ "max": 0.07438520623832859,
56
+ "count": 70
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.3576227315121893,
60
+ "min": 0.2412924604894429,
61
+ "max": 0.37192603119164297,
62
+ "count": 70
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.05462366772048614,
66
+ "min": 0.035928833608826,
67
+ "max": 0.06355765520357617,
68
+ "count": 70
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.2731183386024307,
72
+ "min": 0.143715334435304,
73
+ "max": 0.3177882760178809,
74
+ "count": 70
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 1.6019469333333316e-08,
78
+ "min": 1.6019469333333316e-08,
79
+ "max": 2.3149428360000004e-06,
80
+ "count": 70
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 8.009734666666658e-08,
84
+ "min": 8.009734666666658e-08,
85
+ "max": 1.1409719679999999e-05,
86
+ "count": 70
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10053066666666668,
90
+ "min": 0.10053066666666668,
91
+ "max": 0.17716400000000002,
92
+ "count": 70
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.5026533333333334,
96
+ "min": 0.40652266666666664,
97
+ "max": 0.8803200000000001,
98
+ "count": 70
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 3.648026666666663e-05,
102
+ "min": 3.648026666666663e-05,
103
+ "max": 0.0038604836000000003,
104
+ "count": 70
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.00018240133333333316,
108
+ "min": 0.00018240133333333316,
109
+ "max": 0.019027968,
110
+ "count": 70
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 4.181818181818182,
114
+ "min": 2.6818181818181817,
115
+ "max": 5.054545454545455,
116
+ "count": 70
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 230.0,
120
+ "min": 118.0,
121
+ "max": 278.0,
122
+ "count": 70
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 4.181818181818182,
126
+ "min": 2.6818181818181817,
127
+ "max": 5.054545454545455,
128
+ "count": 70
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 230.0,
132
+ "min": 118.0,
133
+ "max": 278.0,
134
+ "count": 70
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 70
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 70
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1691789716",
152
  "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
154
  "mlagents_version": "0.31.0.dev0",
155
  "mlagents_envs_version": "0.31.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
+ "end_time_seconds": "1691791543"
160
  },
161
+ "total": 1827.0801377919997,
162
  "count": 1,
163
+ "self": 0.4342306569988068,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.06550851800056989,
167
  "count": 1,
168
+ "self": 0.06550851800056989
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 1826.5803986170004,
172
  "count": 1,
173
+ "self": 2.248516801940241,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 5.191542315999868,
177
  "count": 1,
178
+ "self": 5.191542315999868
179
  },
180
  "TrainerController.advance": {
181
+ "total": 1818.99052772506,
182
+ "count": 63674,
183
+ "self": 1.1208480139430321,
184
  "children": {
185
  "env_step": {
186
+ "total": 1817.869679711117,
187
+ "count": 63674,
188
+ "self": 1327.5544179470871,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 489.137316015901,
192
+ "count": 63674,
193
+ "self": 6.948076970018519,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 482.18923904588246,
197
+ "count": 63674,
198
+ "self": 482.18923904588246
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 1.1779457481288773,
204
+ "count": 63674,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 1820.362834624936,
209
+ "count": 63674,
210
  "is_parallel": true,
211
+ "self": 848.1124487679917,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0029990170005476102,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0006937140014997567,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0023053029990478535,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0023053029990478535
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.04061070199986716,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0007622849998369929,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004748560004372848,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004748560004372848
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03663902199969016,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03663902199969016
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0027345389999027248,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0007086479990903172,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0020258910008124076,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0020258910008124076
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 972.2503858569444,
271
+ "count": 63673,
272
  "is_parallel": true,
273
+ "self": 40.23167197309613,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 20.783129467002254,
277
+ "count": 63673,
278
  "is_parallel": true,
279
+ "self": 20.783129467002254
280
  },
281
  "communicator.exchange": {
282
+ "total": 766.8359551070089,
283
+ "count": 63673,
284
  "is_parallel": true,
285
+ "self": 766.8359551070089
286
  },
287
  "steps_from_proto": {
288
+ "total": 144.3996293098371,
289
+ "count": 63673,
290
  "is_parallel": true,
291
+ "self": 27.111744930974965,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 117.28788437886215,
295
+ "count": 636730,
296
  "is_parallel": true,
297
+ "self": 117.28788437886215
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.0002277430003232439,
313
  "count": 1,
314
+ "self": 0.0002277430003232439,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 1803.0946918022964,
324
+ "count": 1680449,
325
  "is_parallel": true,
326
+ "self": 39.56978513161266,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 987.1128867326761,
330
+ "count": 1680449,
331
  "is_parallel": true,
332
+ "self": 981.707200308676,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 5.405686424000123,
336
+ "count": 14,
337
  "is_parallel": true,
338
+ "self": 5.405686424000123
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 776.4120199380077,
344
+ "count": 318,
345
  "is_parallel": true,
346
+ "self": 311.6997565030133,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 464.7122634349944,
350
+ "count": 16212,
351
  "is_parallel": true,
352
+ "self": 464.7122634349944
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.14958403099990392,
364
  "count": 1,
365
+ "self": 0.0010529000001042732,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.14853113099979964,
369
  "count": 1,
370
+ "self": 0.14853113099979964
371
  }
372
  }
373
  }
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": 3.727272727272727,
8
- "creation_time": 1691785672.455665,
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": 3.090909090909091,
17
- "creation_time": 1691785801.9399114,
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": 3.090909090909091,
26
- "creation_time": 1691785931.6977835,
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": 3.4545454545454546,
35
- "creation_time": 1691786060.3424048,
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": 3.4545454545454546,
44
- "creation_time": 1691786060.532719,
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": 3.4545454545454546,
54
- "creation_time": 1691786060.532719,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 499952,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499952.onnx",
7
+ "reward": 4.0,
8
+ "creation_time": 1691790497.7808218,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-499952.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 549976,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-549976.onnx",
16
+ "reward": 3.0,
17
+ "creation_time": 1691790627.9956892,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-549976.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 599976,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-599976.onnx",
25
+ "reward": 4.0,
26
+ "creation_time": 1691790757.0515003,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-599976.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 649936,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-649936.onnx",
34
+ "reward": 3.272727272727273,
35
+ "creation_time": 1691790888.5311913,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-649936.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 699960,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-699960.onnx",
43
+ "reward": 3.3636363636363638,
44
+ "creation_time": 1691791019.6731496,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-699960.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 749960,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-749960.onnx",
52
+ "reward": 3.5454545454545454,
53
+ "creation_time": 1691791149.757476,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-749960.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 799984,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-799984.onnx",
61
+ "reward": 4.636363636363637,
62
+ "creation_time": 1691791283.8764565,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-799984.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 849944,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-849944.onnx",
70
+ "reward": 4.0,
71
+ "creation_time": 1691791413.8144617,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-849944.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 899968,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-899968.onnx",
79
+ "reward": 4.181818181818182,
80
+ "creation_time": 1691791542.7282896,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-899968.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 900288,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-900288.onnx",
88
+ "reward": 4.181818181818182,
89
+ "creation_time": 1691791542.9270914,
90
+ "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-900288.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 900288,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 4.181818181818182,
99
+ "creation_time": 1691791542.9270914,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-900288.pt"
102
  ]
103
  }
104
  },