Hugging Face's logo

sighmon
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
sighmon commited on
Commit
61e1b4a
·
verified ·
1 Parent(s): a3f849a

First Push

Browse files
Files changed (28) 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 +2 -2
  7. SnowballTarget/SnowballTarget-249944.pt +2 -2
  8. SnowballTarget/SnowballTarget-299968.onnx +2 -2
  9. SnowballTarget/SnowballTarget-299968.pt +2 -2
  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-499976.onnx +3 -0
  17. SnowballTarget/SnowballTarget-499976.pt +3 -0
  18. SnowballTarget/SnowballTarget-500104.onnx +3 -0
  19. SnowballTarget/SnowballTarget-500104.pt +3 -0
  20. SnowballTarget/SnowballTarget-99960.onnx +2 -2
  21. SnowballTarget/SnowballTarget-99960.pt +2 -2
  22. SnowballTarget/checkpoint.pt +2 -2
  23. SnowballTarget/events.out.tfevents.1738842722.a507baff72c6.15542.0 +3 -0
  24. config.json +1 -1
  25. configuration.yaml +3 -3
  26. run_logs/Player-0.log +14 -14
  27. run_logs/timers.json +160 -160
  28. run_logs/training_status.json +66 -39
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc917b2d0175837dc3783c86c3f43d325ef6cc62194f129bfb8be862d9c97628
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e2945eac7fea1a053f6d4f51b289f82afdec1079637ab1aa95ea22c6b9bcc08
3
+ size 657877
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:646d9d0ef2d58111eedcbf3ae48011b881c7bc2d0153f36034bfb2e87e61e429
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:056e5d91168051cd83c91f0d4f1acd6d028fe776a0c3dceb8f5bc6c0c6edaeb8
3
+ size 657877
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5a5005b3f1a5f54dfe33885d5e4d9e53b897aeba1ae9f47d56d13f3c0b6b9fc
3
- size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d64eebf1b2a5f977aaa784b44c8ebfff1522a07b1c1f7f747ee6598827e9f1ca
3
+ size 3872166
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:849bb86a7f8992f05d5e2615d0eac1c93607e81f295cb68b38dc8ba9a08fcd8a
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43888da3f75c1336e052e92c43a6583981ea767188a248cfdb4e0e60c869c5c3
3
+ size 657877
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e66fa665c6f1abfa8e3b9089b076643910f5490ad0121e8ac6e444006329577
3
- size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0174515f8d8336bb2362df3548a647805e50fca1d9656fab7c5c4b8e745bbaa1
3
+ size 3872166
SnowballTarget/SnowballTarget-249944.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b5e62ae72777bcc2678d3fc85fe7172076418007486080d55f1fd7eef6b50fb
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:267df14b395a8fdf1af38ecc98bc86ab7c29184097c52f40e8c09dd21c8e2471
3
+ size 657877
SnowballTarget/SnowballTarget-249944.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fccc76fee8534e22d9914e4fd7fd91c3297eb6b1afbce04e3a8b0ee5f2f4ab3c
3
- size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c15681b6e311ac72baf3c808232eea7fb744366546b069821bcf4bcc05ce29f
3
+ size 3872166
SnowballTarget/SnowballTarget-299968.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc917b2d0175837dc3783c86c3f43d325ef6cc62194f129bfb8be862d9c97628
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f73d78518739a0b06d0f98c2d6cc6eeefe1dc62862e06906c7623d6c8935fb1
3
+ size 657877
SnowballTarget/SnowballTarget-299968.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c9bb833033494255e15e9d184f7af3a0e0367f19b7e77faa8550763410aa44e
3
- size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b57ea055913e35183bf83205e31c4142490ac730f524f7035acdd09685f48e4
3
+ size 3872166
SnowballTarget/SnowballTarget-349992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87b97d7454e25131e929969b169fa7cd857e0b67477a42072b0405e9f9211108
3
+ size 657877
SnowballTarget/SnowballTarget-349992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21cd1a930bc32668dc954600d9ba8683e796969e6f8d249513a686b34297db9a
3
+ size 3872166
SnowballTarget/SnowballTarget-399992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a3e83861101eec9f493dc8a2f955f35a86829ecc5c518f109da9da1e5940500
3
+ size 657877
SnowballTarget/SnowballTarget-399992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b0df80fa3e45fd890df74aa3705e1ca3529f30ee8df36e080bbb9cb0ca3e077
3
+ size 3872166
SnowballTarget/SnowballTarget-449952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1c03506359dd15fedd13403b6fc115dabd92dff342b83f5298ee9da706884ca
3
+ size 657877
SnowballTarget/SnowballTarget-449952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:956a712318ab9f2e0aa93e3dbc4083e49a05ecf46d7755b48caf2d1285b45aad
3
+ size 3872166
SnowballTarget/SnowballTarget-499976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9578e725226bdd0bbbcb351b1f72b3b6e20b3a5d97908c7803f9e5241b97382d
3
+ size 657877
SnowballTarget/SnowballTarget-499976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5376dbe30653d15d18a0950cb7cc7242efbe3ea22d6cc49a704572eea5470ce8
3
+ size 3872166
SnowballTarget/SnowballTarget-500104.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e2945eac7fea1a053f6d4f51b289f82afdec1079637ab1aa95ea22c6b9bcc08
3
+ size 657877
SnowballTarget/SnowballTarget-500104.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f7a29585ca59badf6200504ca4f5de7f84275e36c956efffd719a28b08d8560
3
+ size 3872166
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0932b63401157ef8c63a28e8bb415be733e94a571e75caf0781dd367169bd642
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:704978017f3fe4b3e10ae198388648e553b7b789a0bb94cb7a8d292ab0127f44
3
+ size 657877
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f6ba0b890211f79928710ca8bf9fc69c7005f3de3702ef334a18f8f12f5b800
3
- size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:614c0d093d3c63663fedf58b2605cd8e4ea8ffb0be3d211bb4ee83219b2f21e0
3
+ size 3872061
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fdf9446f1e562c6b0d8b1fcf80547caa23822d671b5635003ee2c02d6e939f6b
3
- size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fa1fec08b7115972b8182ac71aae4266eb49b01efff33b3becca80bb230954c
3
+ size 3871011
SnowballTarget/events.out.tfevents.1738842722.a507baff72c6.15542.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f6c72f691abd6bd312df09e61b5a94e1f052b721967e3405c060a1f1b9245b2
3
+ size 42797
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0006, "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": 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": "SnowballTarget2", "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": 0.0006, "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": 0.99, "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": 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": "SnowballTarget4", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -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
@@ -38,7 +38,7 @@ behaviors:
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
@@ -66,7 +66,7 @@ engine_settings:
66
  no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
- run_id: SnowballTarget2
70
  initialize_from: null
71
  load_model: false
72
  resume: false
 
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
 
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
 
66
  no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
+ run_id: SnowballTarget4
70
  initialize_from: null
71
  load_model: false
72
  resume: false
run_logs/Player-0.log CHANGED
@@ -31,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
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)
@@ -42,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
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: 0.657948 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.
@@ -50,7 +50,7 @@ Memory Statistics:
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
@@ -166,19 +166,19 @@ Memory Statistics:
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
- Peak main deferred allocation count 41
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
@@ -210,13 +210,13 @@ Memory Statistics:
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]: 7544 frames, [64.0 KB-128.0 KB]: 655 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]: 8199 frames
220
  Requested Block Size 16.0 MB
221
  Peak Block count 1
222
  Peak Allocated memory 39.6 KB
@@ -228,13 +228,13 @@ Memory Statistics:
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
@@ -246,13 +246,13 @@ Memory Statistics:
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
 
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 0.096 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: 0.739171 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]: 13412 frames, [16.0 KB-32.0 KB]: 227 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 40
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]: 11052 frames, [8.0 MB-16.0 MB]: 2588 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 9.5 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 13640 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
  Peak Allocated memory 17.8 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]: 13382 frames, [64.0 KB-128.0 KB]: 258 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]: 13640 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]: 13640 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]: 13639 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]: 13640 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]: 13640 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": 0.7234710454940796,
6
- "min": 0.7211694121360779,
7
- "max": 2.8498573303222656,
8
- "count": 30
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 7448.85791015625,
12
- "min": 7241.0732421875,
13
- "max": 29091.34375,
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": 13.744291305541992,
30
- "min": 0.17775389552116394,
31
- "max": 13.925162315368652,
32
- "count": 30
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2803.83544921875,
36
- "min": 34.484256744384766,
37
- "max": 2854.658203125,
38
- "count": 30
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.07054175772303578,
42
- "min": 0.06297348507645188,
43
- "max": 0.07708247474967685,
44
- "count": 30
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.3527087886151789,
48
- "min": 0.25189394030580753,
49
- "max": 0.3654153714853558,
50
- "count": 30
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.18940478095821306,
54
- "min": 0.10031758798583064,
55
- "max": 0.2665141351959285,
56
- "count": 30
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.9470239047910652,
60
- "min": 0.40127035194332256,
61
- "max": 1.2888355453809104,
62
- "count": 30
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
- "value": 1.0576098237333326e-05,
66
- "min": 1.0576098237333326e-05,
67
- "max": 0.0005891760018039999,
68
- "count": 30
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
- "value": 5.288049118666663e-05,
72
- "min": 5.288049118666663e-05,
73
- "max": 0.0028468800255199997,
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": 26.672727272727272,
114
- "min": 2.8636363636363638,
115
- "max": 27.236363636363638,
116
- "count": 30
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1467.0,
120
- "min": 126.0,
121
- "max": 1498.0,
122
- "count": 30
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 26.672727272727272,
126
- "min": 2.8636363636363638,
127
- "max": 27.236363636363638,
128
- "count": 30
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1467.0,
132
- "min": 126.0,
133
- "max": 1498.0,
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": "1738841115",
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=SnowballTarget2 --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": "2.6.0+cu124",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1738841781"
160
  },
161
- "total": 666.8529377719999,
162
  "count": 1,
163
- "self": 0.755558695000218,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.021626193999964016,
167
  "count": 1,
168
- "self": 0.021626193999964016
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 666.0757528829997,
172
  "count": 1,
173
- "self": 0.6140667149784349,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 1.9851342710001063,
177
  "count": 1,
178
- "self": 1.9851342710001063
179
  },
180
  "TrainerController.advance": {
181
- "total": 663.3440004820209,
182
- "count": 27328,
183
- "self": 0.6185695410408698,
184
  "children": {
185
  "env_step": {
186
- "total": 472.5973576210047,
187
- "count": 27328,
188
- "self": 358.4394442549976,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 113.79617522099147,
192
- "count": 27328,
193
- "self": 2.0803244800029006,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 111.71585074098857,
197
- "count": 27328,
198
- "self": 111.71585074098857
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.361738145015579,
204
- "count": 27328,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 663.8068631400324,
209
- "count": 27328,
210
  "is_parallel": true,
211
- "self": 350.9226043930855,
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": 0.0021581409998816525,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0006682499993075908,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0014898910005740618,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0014898910005740618
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03621925500010548,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0005921619999753602,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0004401940000207105,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0004401940000207105
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03332988300007855,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03332988300007855
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0018570160000308533,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0003611639995142468,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0014958520005166065,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0014958520005166065
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 312.8842587469469,
271
- "count": 27327,
272
  "is_parallel": true,
273
- "self": 14.593478721860492,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 8.235549691996539,
277
- "count": 27327,
278
  "is_parallel": true,
279
- "self": 8.235549691996539
280
  },
281
  "communicator.exchange": {
282
- "total": 241.94320678205963,
283
- "count": 27327,
284
  "is_parallel": true,
285
- "self": 241.94320678205963
286
  },
287
  "steps_from_proto": {
288
- "total": 48.112023551030234,
289
- "count": 27327,
290
  "is_parallel": true,
291
- "self": 8.818129458982867,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 39.29389409204737,
295
- "count": 273270,
296
  "is_parallel": true,
297
- "self": 39.29389409204737
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 190.12807331997533,
311
- "count": 27328,
312
- "self": 0.7779899960366947,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 41.7558608249451,
316
- "count": 27328,
317
- "self": 40.93711971194466,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.8187411130004421,
321
- "count": 6,
322
- "self": 0.8187411130004421
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 147.59422249899353,
328
- "count": 136,
329
- "self": 58.50659884900074,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 89.08762364999279,
333
- "count": 6933,
334
- "self": 89.08762364999279
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 1.3280000530357938e-06,
344
  "count": 1,
345
- "self": 1.3280000530357938e-06
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.13255008700025428,
349
  "count": 1,
350
- "self": 0.0012406210003064189,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.13130946599994786,
354
  "count": 1,
355
- "self": 0.13130946599994786
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.778346061706543,
6
+ "min": 0.7760685086250305,
7
+ "max": 2.8323302268981934,
8
+ "count": 50
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 7465.8955078125,
12
+ "min": 7459.63916015625,
13
+ "max": 28912.427734375,
14
+ "count": 50
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 499976.0,
18
  "min": 9952.0,
19
+ "max": 499976.0,
20
+ "count": 50
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 499976.0,
24
  "min": 9952.0,
25
+ "max": 499976.0,
26
+ "count": 50
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 14.46053695678711,
30
+ "min": 0.36530283093452454,
31
+ "max": 14.469643592834473,
32
+ "count": 50
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2964.41015625,
36
+ "min": 70.8687515258789,
37
+ "max": 2966.27685546875,
38
+ "count": 50
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.06906648196608704,
42
+ "min": 0.058018910541546106,
43
+ "max": 0.0763130648651271,
44
+ "count": 50
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.3453324098304352,
48
+ "min": 0.24563687803011441,
49
+ "max": 0.37258500561766394,
50
+ "count": 50
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.15450777668578952,
54
+ "min": 0.11841040632148803,
55
+ "max": 0.2911285329683154,
56
+ "count": 50
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.7725388834289476,
60
+ "min": 0.4736416252859521,
61
+ "max": 1.455642664841577,
62
+ "count": 50
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
+ "value": 6.105698982400004e-06,
66
+ "min": 6.105698982400004e-06,
67
+ "max": 0.0005935056010824,
68
+ "count": 50
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
+ "value": 3.052849491200002e-05,
72
+ "min": 3.052849491200002e-05,
73
+ "max": 0.0029081280153119998,
74
+ "count": 50
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
+ "value": 0.10101760000000001,
78
+ "min": 0.10101760000000001,
79
+ "max": 0.19891759999999997,
80
+ "count": 50
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
+ "value": 0.5050880000000001,
84
+ "min": 0.41199040000000003,
85
+ "max": 0.984688,
86
+ "count": 50
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
+ "value": 6.0778240000000044e-05,
90
+ "min": 6.0778240000000044e-05,
91
+ "max": 0.00494598824,
92
+ "count": 50
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
+ "value": 0.0003038912000000002,
96
+ "min": 0.0003038912000000002,
97
+ "max": 0.0242359312,
98
+ "count": 50
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
+ "count": 50
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
  "value": 10945.0,
108
  "min": 8756.0,
109
  "max": 10945.0,
110
+ "count": 50
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 28.29090909090909,
114
+ "min": 3.8863636363636362,
115
+ "max": 28.64814814814815,
116
+ "count": 50
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1556.0,
120
+ "min": 171.0,
121
+ "max": 1568.0,
122
+ "count": 50
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 28.29090909090909,
126
+ "min": 3.8863636363636362,
127
+ "max": 28.64814814814815,
128
+ "count": 50
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1556.0,
132
+ "min": 171.0,
133
+ "max": 1568.0,
134
+ "count": 50
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 50
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 50
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1738842721",
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=SnowballTarget4 --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": "2.6.0+cu124",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1738843928"
160
  },
161
+ "total": 1207.0769785840002,
162
  "count": 1,
163
+ "self": 0.4925473890007197,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.021088758000132657,
167
  "count": 1,
168
+ "self": 0.021088758000132657
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 1206.5633424369994,
172
  "count": 1,
173
+ "self": 1.0259412320483534,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 1.9535205480001423,
177
  "count": 1,
178
+ "self": 1.9535205480001423
179
  },
180
  "TrainerController.advance": {
181
+ "total": 1203.4633720739512,
182
+ "count": 45464,
183
+ "self": 1.020297928023865,
184
  "children": {
185
  "env_step": {
186
+ "total": 818.2079761099676,
187
+ "count": 45464,
188
+ "self": 603.5839399959186,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 214.01058432204763,
192
+ "count": 45464,
193
+ "self": 3.3997262710645373,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 210.6108580509831,
197
+ "count": 45464,
198
+ "self": 210.6108580509831
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.6134517920013423,
204
+ "count": 45464,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 1203.0193285940236,
209
+ "count": 45464,
210
  "is_parallel": true,
211
+ "self": 674.9602680760827,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0022099800003161363,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0007236290007313073,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.001486350999584829,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.001486350999584829
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.035761382000146114,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0005477479999171919,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0003832249999504711,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0003832249999504711
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03308638099997552,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03308638099997552
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.001744028000302933,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0003583989996513992,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0013856290006515337,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0013856290006515337
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 528.0590605179409,
271
+ "count": 45463,
272
  "is_parallel": true,
273
+ "self": 24.55672441486513,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 13.932740382035263,
277
+ "count": 45463,
278
  "is_parallel": true,
279
+ "self": 13.932740382035263
280
  },
281
  "communicator.exchange": {
282
+ "total": 408.3952639410668,
283
+ "count": 45463,
284
  "is_parallel": true,
285
+ "self": 408.3952639410668
286
  },
287
  "steps_from_proto": {
288
+ "total": 81.17433177997373,
289
+ "count": 45463,
290
  "is_parallel": true,
291
+ "self": 14.825467513813692,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 66.34886426616004,
295
+ "count": 454630,
296
  "is_parallel": true,
297
+ "self": 66.34886426616004
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 384.2350980359597,
311
+ "count": 45464,
312
+ "self": 1.3410349658888663,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 124.30384383406499,
316
+ "count": 45464,
317
+ "self": 122.85314747306666,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 1.4506963609983359,
321
+ "count": 10,
322
+ "self": 1.4506963609983359
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 258.59021923600585,
328
+ "count": 227,
329
+ "self": 99.0990100999561,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 159.49120913604975,
333
+ "count": 11574,
334
+ "self": 159.49120913604975
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 8.309998520417139e-07,
344
  "count": 1,
345
+ "self": 8.309998520417139e-07
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.12050775199986674,
349
  "count": 1,
350
+ "self": 0.0009625279999454506,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.11954522399992129,
354
  "count": 1,
355
+ "self": 0.11954522399992129
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -1,77 +1,104 @@
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
4
- {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 17.545454545454547,
8
- "creation_time": 1738841224.822375,
9
- "auxillary_file_paths": [
10
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.pt"
11
- ]
12
- },
13
  {
14
  "steps": 99960,
15
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 23.272727272727273,
17
- "creation_time": 1738841334.5716143,
18
  "auxillary_file_paths": [
19
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
21
  },
22
  {
23
  "steps": 149984,
24
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 25.0,
26
- "creation_time": 1738841444.7629015,
27
  "auxillary_file_paths": [
28
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
30
  },
31
  {
32
  "steps": 199984,
33
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 26.0,
35
- "creation_time": 1738841554.4360917,
36
  "auxillary_file_paths": [
37
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
  "steps": 249944,
42
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-249944.onnx",
43
- "reward": 26.545454545454547,
44
- "creation_time": 1738841665.3302934,
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-249944.pt"
47
  ]
48
  },
49
  {
50
  "steps": 299968,
51
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-299968.onnx",
52
- "reward": 26.272727272727273,
53
- "creation_time": 1738841780.9258573,
54
  "auxillary_file_paths": [
55
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-299968.pt"
56
  ]
57
  },
58
  {
59
- "steps": 300608,
60
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-300608.onnx",
61
- "reward": 26.272727272727273,
62
- "creation_time": 1738841781.1539752,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  "auxillary_file_paths": [
64
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-300608.pt"
65
  ]
66
  }
67
  ],
68
  "final_checkpoint": {
69
- "steps": 300608,
70
- "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
71
- "reward": 26.272727272727273,
72
- "creation_time": 1738841781.1539752,
73
  "auxillary_file_paths": [
74
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-300608.pt"
75
  ]
76
  }
77
  },
 
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
 
 
 
 
 
 
 
 
 
4
  {
5
  "steps": 99960,
6
+ "file_path": "results/SnowballTarget4/SnowballTarget/SnowballTarget-99960.onnx",
7
+ "reward": 24.181818181818183,
8
+ "creation_time": 1738842960.956953,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget4/SnowballTarget/SnowballTarget-99960.pt"
11
  ]
12
  },
13
  {
14
  "steps": 149984,
15
+ "file_path": "results/SnowballTarget4/SnowballTarget/SnowballTarget-149984.onnx",
16
+ "reward": 24.818181818181817,
17
+ "creation_time": 1738843082.2325678,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget4/SnowballTarget/SnowballTarget-149984.pt"
20
  ]
21
  },
22
  {
23
  "steps": 199984,
24
+ "file_path": "results/SnowballTarget4/SnowballTarget/SnowballTarget-199984.onnx",
25
+ "reward": 27.727272727272727,
26
+ "creation_time": 1738843200.2727532,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget4/SnowballTarget/SnowballTarget-199984.pt"
29
  ]
30
  },
31
  {
32
  "steps": 249944,
33
+ "file_path": "results/SnowballTarget4/SnowballTarget/SnowballTarget-249944.onnx",
34
+ "reward": 26.272727272727273,
35
+ "creation_time": 1738843318.3953357,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget4/SnowballTarget/SnowballTarget-249944.pt"
38
  ]
39
  },
40
  {
41
  "steps": 299968,
42
+ "file_path": "results/SnowballTarget4/SnowballTarget/SnowballTarget-299968.onnx",
43
+ "reward": 27.0,
44
+ "creation_time": 1738843439.039213,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget4/SnowballTarget/SnowballTarget-299968.pt"
47
  ]
48
  },
49
  {
50
+ "steps": 349992,
51
+ "file_path": "results/SnowballTarget4/SnowballTarget/SnowballTarget-349992.onnx",
52
+ "reward": 28.545454545454547,
53
+ "creation_time": 1738843558.358035,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget4/SnowballTarget/SnowballTarget-349992.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 399992,
60
+ "file_path": "results/SnowballTarget4/SnowballTarget/SnowballTarget-399992.onnx",
61
+ "reward": 28.818181818181817,
62
+ "creation_time": 1738843684.1187868,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget4/SnowballTarget/SnowballTarget-399992.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 449952,
69
+ "file_path": "results/SnowballTarget4/SnowballTarget/SnowballTarget-449952.onnx",
70
+ "reward": 28.818181818181817,
71
+ "creation_time": 1738843807.1344843,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget4/SnowballTarget/SnowballTarget-449952.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 499976,
78
+ "file_path": "results/SnowballTarget4/SnowballTarget/SnowballTarget-499976.onnx",
79
+ "reward": 27.636363636363637,
80
+ "creation_time": 1738843928.339376,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget4/SnowballTarget/SnowballTarget-499976.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 500104,
87
+ "file_path": "results/SnowballTarget4/SnowballTarget/SnowballTarget-500104.onnx",
88
+ "reward": 27.636363636363637,
89
+ "creation_time": 1738843928.4804075,
90
  "auxillary_file_paths": [
91
+ "results/SnowballTarget4/SnowballTarget/SnowballTarget-500104.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 500104,
97
+ "file_path": "results/SnowballTarget4/SnowballTarget.onnx",
98
+ "reward": 27.636363636363637,
99
+ "creation_time": 1738843928.4804075,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget4/SnowballTarget/SnowballTarget-500104.pt"
102
  ]
103
  }
104
  },