Hugging Face's logo

HungChau
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
HungChau commited on
Commit
59c165b
•
1 Parent(s): ca18bde

500k steps

Browse files
Files changed (28) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-149984.onnx +1 -1
  3. SnowballTarget/SnowballTarget-149984.pt +1 -1
  4. SnowballTarget/SnowballTarget-199984.onnx +1 -1
  5. SnowballTarget/SnowballTarget-199984.pt +1 -1
  6. SnowballTarget/SnowballTarget-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-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 +1 -1
  21. SnowballTarget/SnowballTarget-99960.pt +1 -1
  22. SnowballTarget/checkpoint.pt +1 -1
  23. SnowballTarget/events.out.tfevents.1720126136.86362abe7b35.11687.0 +3 -0
  24. config.json +1 -1
  25. configuration.yaml +2 -2
  26. run_logs/Player-0.log +13 -16
  27. run_logs/timers.json +161 -161
  28. run_logs/training_status.json +69 -24
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd4a4e47f2b0f4344e09528c60d8c1201915b5061681440c00ad8d5c5fb7deb6
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b69b8ccc1e5d0cdae20c18f6b507cc9581d9b809dc386130ae54fb6d5c3672a0
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:baeef00a475a95b2ad343765ce1d2b1a48e57be5aa1edb74b1359859b853fe81
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b3ad5f7a8995737b58e14214bf1b5b3122ea1e07783a9652248d779851c2c62
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d676f03b83e5b6bfcd97f4cfe446a11864e349815353855d2be5b21c156c880f
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27748a13b9bc3ae21d01dee532c94bca9b3e65b70e614ff5a52ddc27b365f847
3
  size 3850075
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd4a4e47f2b0f4344e09528c60d8c1201915b5061681440c00ad8d5c5fb7deb6
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56070b8764e9d73b515695a89b1fbce30019d433c9d62fa4394e8969ff06bc76
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbd09cf93388ca55067197663987dfa753fcb19eb00bed8537e2dc0479a0f720
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e7f89e61a159a5290301bd1f54538645d3c7efc496c45398dbc9f596c0d9834
3
  size 3850075
SnowballTarget/SnowballTarget-249944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2f55c1423fdfdbc8531f9e2a1ea9b63780cebed9574ec9ed647bd164e3782b2
3
+ size 650646
SnowballTarget/SnowballTarget-249944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d9c52f5d97b8380c7c42e7ba19843e293a15f7932992170fc4723587d710f6e
3
+ size 3850075
SnowballTarget/SnowballTarget-299968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2f6f249585358f79036221e5ec7376a4d30e85f0d2a5e7721dfc7b5c53149c5
3
+ size 650646
SnowballTarget/SnowballTarget-299968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:451d1d8b47a91ac8ae225dff43a45526df2a9ebbac88033dfb322c198678f07c
3
+ size 3850075
SnowballTarget/SnowballTarget-349992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb6da15b0d4a0876ed21475a760da68ec21f9e9dafc10c8d95b74963eb9488e0
3
+ size 650646
SnowballTarget/SnowballTarget-349992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8d4a241cfae3078bf98bb79f3f1b36e981f6020354b78e30c09c6842170205a
3
+ size 3850075
SnowballTarget/SnowballTarget-399992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29bf3982308f78023b2c1ec8c11603b9dab7563309019b3c07f53c9a14ecdac8
3
+ size 650646
SnowballTarget/SnowballTarget-399992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab11234d6ac54298bcc466d98ae2a492df76621aa89f7b6e88358cefac9fac81
3
+ size 3850075
SnowballTarget/SnowballTarget-449952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b757ced9d4677ae1139bc344e30a746f23e6b4c921694036599919ed5fac1542
3
+ size 650646
SnowballTarget/SnowballTarget-449952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6849b27cfda85eb28f95f2e5ead09c5452b2f3154c1d23efe02ee62ed1d20e64
3
+ size 3850075
SnowballTarget/SnowballTarget-499976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b69b8ccc1e5d0cdae20c18f6b507cc9581d9b809dc386130ae54fb6d5c3672a0
3
+ size 650646
SnowballTarget/SnowballTarget-499976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:900e7b526d43c2dd953422ea20b6e438acb223f816cffd2978df0c6d60bc6610
3
+ size 3850075
SnowballTarget/SnowballTarget-500104.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b69b8ccc1e5d0cdae20c18f6b507cc9581d9b809dc386130ae54fb6d5c3672a0
3
+ size 650646
SnowballTarget/SnowballTarget-500104.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6214438ab2dbcbff23721cdcb73add6125ce70546662db7c985e2f1c14a379e3
3
+ size 3850075
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e0377232bf92e27f47b7d6facc5b40e6e1aadd79ba2e7eeace9988c6f546114
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2f7b0eab72c0d5bad14ae3f75dc07ac6d20f35bddd61b9cd0743b082f5a7ecb
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:913fc6d06aec0d2d727d0c4f82d104e4f4ae87124bda7e97cf3ca81c8c233dcb
3
  size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fc2bbf2c11ae60a1d28569127981db394c750da26d9e3c6cb98bb4277eb617c
3
  size 3850000
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f972a3a248579f38c0f4d72c2eb7e917239e8670c486696a9491d05785c0569d
3
  size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eca7bbe559a63824f22a11ea5c1019ef77e5c89ff841d21a4fd5d0570f508fee
3
  size 3849250
SnowballTarget/events.out.tfevents.1720126136.86362abe7b35.11687.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f39960e24472e6268ed08a8397ad1c0a1d2a33e227f7dc24fa41443943c05ab3
3
+ size 52865
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": 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, "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": 0.0003, "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": 500000, "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, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -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
@@ -70,7 +70,7 @@ checkpoint_settings:
70
  initialize_from: null
71
  load_model: false
72
  resume: false
73
- force: false
74
  train_model: false
75
  inference: false
76
  results_dir: results
 
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: true
 
70
  initialize_from: null
71
  load_model: false
72
  resume: false
73
+ force: true
74
  train_model: false
75
  inference: false
76
  results_dir: results
run_logs/Player-0.log CHANGED
@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
5
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
6
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
7
- Unable to load player prefs
8
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
9
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
- - Completed reload, in 0.141 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: 0.919493 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
@@ -175,13 +172,13 @@ Memory Statistics:
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
- Peak usage frame count: [4.0 MB-8.0 MB]: 5461 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.8 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
  Peak Allocated memory 17.8 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]: 4505 frames, [64.0 KB-128.0 KB]: 956 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 66.8 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 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 0.088 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: 0.703418 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]: 13415 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
 
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]: 11114 frames, [8.0 MB-16.0 MB]: 2529 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]: 13643 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]: 13328 frames, [64.0 KB-128.0 KB]: 315 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 66.0 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 13643 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]: 13643 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]: 13642 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]: 13643 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]: 13643 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": 0.9011333584785461,
6
- "min": 0.9011333584785461,
7
- "max": 2.863861322402954,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8604.021484375,
12
- "min": 8604.021484375,
13
- "max": 29360.306640625,
14
- "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 199984.0,
18
  "min": 9952.0,
19
- "max": 199984.0,
20
- "count": 20
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 199984.0,
24
  "min": 9952.0,
25
- "max": 199984.0,
26
- "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.843873023986816,
30
- "min": 0.4344838857650757,
31
- "max": 12.843873023986816,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2504.55517578125,
36
- "min": 84.28987121582031,
37
- "max": 2593.699462890625,
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": 0.07052967558468248,
54
- "min": 0.06062973385312801,
55
- "max": 0.07682464971417087,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.28211870233872993,
60
- "min": 0.24407442778978933,
61
- "max": 0.37819793416579783,
62
- "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.21678111165323677,
66
- "min": 0.15262091511805703,
67
- "max": 0.2951080462365758,
68
- "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.8671244466129471,
72
- "min": 0.6104836604722281,
73
- "max": 1.3845663596602047,
74
- "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 8.082097306000005e-06,
78
- "min": 8.082097306000005e-06,
79
- "max": 0.000291882002706,
80
- "count": 20
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 3.232838922400002e-05,
84
- "min": 3.232838922400002e-05,
85
- "max": 0.00138516003828,
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": 25.727272727272727,
114
- "min": 3.75,
115
- "max": 25.727272727272727,
116
- "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1132.0,
120
- "min": 165.0,
121
- "max": 1411.0,
122
- "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.727272727272727,
126
- "min": 3.75,
127
- "max": 25.727272727272727,
128
- "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1132.0,
132
- "min": 165.0,
133
- "max": 1411.0,
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": "1720125008",
152
  "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0",
155
  "mlagents_envs_version": "1.1.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.3.0+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1720125503"
160
  },
161
- "total": 494.9788190239999,
162
  "count": 1,
163
- "self": 0.48783703300000525,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.09652441599996564,
167
  "count": 1,
168
- "self": 0.09652441599996564
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 494.39445757499993,
172
  "count": 1,
173
- "self": 0.6268157710023843,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.3216414430000896,
177
  "count": 1,
178
- "self": 3.3216414430000896
179
  },
180
  "TrainerController.advance": {
181
- "total": 490.3513272139976,
182
- "count": 18201,
183
- "self": 0.3041475279912902,
184
  "children": {
185
  "env_step": {
186
- "total": 490.0471796860063,
187
- "count": 18201,
188
- "self": 321.7327709589922,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 168.00830214600478,
192
- "count": 18201,
193
- "self": 1.5806369170102244,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 166.42766522899456,
197
- "count": 18201,
198
- "self": 166.42766522899456
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.30610658100931687,
204
- "count": 18201,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 493.10292052299314,
209
- "count": 18201,
210
  "is_parallel": true,
211
- "self": 246.84124654200627,
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": 0.008025060999898415,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0056231240002944105,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.002401936999604004,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.002401936999604004
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.0414016569998239,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0007003600001098675,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00040631299998494796,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00040631299998494796
244
  },
245
  "communicator.exchange": {
246
- "total": 0.0381708739998885,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.0381708739998885
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0021241099998405844,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00042003999988082796,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0017040699999597564,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0017040699999597564
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 246.26167398098687,
271
- "count": 18200,
272
  "is_parallel": true,
273
- "self": 11.046602495013303,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.892424778960276,
277
- "count": 18200,
278
  "is_parallel": true,
279
- "self": 5.892424778960276
280
  },
281
  "communicator.exchange": {
282
- "total": 191.99821477299542,
283
- "count": 18200,
284
  "is_parallel": true,
285
- "self": 191.99821477299542
286
  },
287
  "steps_from_proto": {
288
- "total": 37.324431934017866,
289
- "count": 18200,
290
  "is_parallel": true,
291
- "self": 7.044783705030795,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 30.27964822898707,
295
- "count": 182000,
296
  "is_parallel": true,
297
- "self": 30.27964822898707
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00020039999981236178,
313
  "count": 1,
314
- "self": 0.00020039999981236178,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 483.97397674681633,
324
- "count": 719638,
325
  "is_parallel": true,
326
- "self": 16.78261704174861,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 268.33505444106913,
330
- "count": 719638,
331
  "is_parallel": true,
332
- "self": 267.3332967280692,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 1.0017577129999609,
336
- "count": 4,
337
  "is_parallel": true,
338
- "self": 1.0017577129999609
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 198.8563052639986,
344
- "count": 90,
345
  "is_parallel": true,
346
- "self": 64.60158270300008,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 134.25472256099852,
350
- "count": 4584,
351
  "is_parallel": true,
352
- "self": 134.25472256099852
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.09447274700005437,
364
  "count": 1,
365
- "self": 0.0010203560000263678,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.093452391000028,
369
  "count": 1,
370
- "self": 0.093452391000028
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.7275000214576721,
6
+ "min": 0.7194790244102478,
7
+ "max": 2.8652455806732178,
8
+ "count": 50
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 7026.1953125,
12
+ "min": 6888.00732421875,
13
+ "max": 29374.498046875,
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": 13.84696102142334,
30
+ "min": 0.36392098665237427,
31
+ "max": 13.924683570861816,
32
+ "count": 50
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2838.626953125,
36
+ "min": 70.60066986083984,
37
+ "max": 2854.56005859375,
38
+ "count": 50
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 50
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 50
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.07238447250799486,
54
+ "min": 0.06183797203314802,
55
+ "max": 0.0743347274623446,
56
+ "count": 50
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.3619223625399743,
60
+ "min": 0.25228516041719484,
61
+ "max": 0.371673637311723,
62
+ "count": 50
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.16106045625957788,
66
+ "min": 0.1196251591192741,
67
+ "max": 0.28749285246811657,
68
+ "count": 50
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.8053022812978894,
72
+ "min": 0.4785006364770964,
73
+ "max": 1.4374642623405829,
74
+ "count": 50
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 3.0528989824000028e-06,
78
+ "min": 3.0528989824000028e-06,
79
+ "max": 0.00029675280108239997,
80
+ "count": 50
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 1.5264494912000015e-05,
84
+ "min": 1.5264494912000015e-05,
85
+ "max": 0.001454064015312,
86
+ "count": 50
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10101760000000001,
90
+ "min": 0.10101760000000001,
91
+ "max": 0.19891759999999997,
92
+ "count": 50
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.5050880000000001,
96
+ "min": 0.41199040000000003,
97
+ "max": 0.984688,
98
+ "count": 50
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 6.0778240000000044e-05,
102
+ "min": 6.0778240000000044e-05,
103
+ "max": 0.00494598824,
104
+ "count": 50
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.0003038912000000002,
108
+ "min": 0.0003038912000000002,
109
+ "max": 0.0242359312,
110
+ "count": 50
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 27.12727272727273,
114
+ "min": 3.4545454545454546,
115
+ "max": 27.490909090909092,
116
+ "count": 50
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1492.0,
120
+ "min": 152.0,
121
+ "max": 1512.0,
122
+ "count": 50
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 27.12727272727273,
126
+ "min": 3.4545454545454546,
127
+ "max": 27.490909090909092,
128
+ "count": 50
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1492.0,
132
+ "min": 152.0,
133
+ "max": 1512.0,
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": "1720126135",
152
  "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 --force",
154
  "mlagents_version": "1.1.0.dev0",
155
  "mlagents_envs_version": "1.1.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.3.0+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1720127344"
160
  },
161
+ "total": 1208.543196833,
162
  "count": 1,
163
+ "self": 0.4763191819997701,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.05647570100018129,
167
  "count": 1,
168
+ "self": 0.05647570100018129
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 1208.01040195,
172
  "count": 1,
173
+ "self": 1.5313657410360975,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.164688725999895,
177
  "count": 1,
178
+ "self": 2.164688725999895
179
  },
180
  "TrainerController.advance": {
181
+ "total": 1204.1999013829636,
182
+ "count": 45475,
183
+ "self": 0.7306241989845148,
184
  "children": {
185
  "env_step": {
186
+ "total": 1203.469277183979,
187
+ "count": 45475,
188
+ "self": 783.6745763400313,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 419.0318719929437,
192
+ "count": 45475,
193
+ "self": 3.9745484049221886,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 415.0573235880215,
197
+ "count": 45475,
198
+ "self": 415.0573235880215
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.7628288510040875,
204
+ "count": 45475,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 1204.587804190956,
209
+ "count": 45475,
210
  "is_parallel": true,
211
+ "self": 604.4370829810155,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.002409023000382149,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0008018330008781049,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.001607189999504044,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.001607189999504044
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.0926024650002546,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006516400003420131,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004552649998004199,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004552649998004199
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.08949468600030741,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.08949468600030741
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.002000873999804753,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0004349640007603739,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0015659099990443792,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0015659099990443792
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 600.1507212099405,
271
+ "count": 45474,
272
  "is_parallel": true,
273
+ "self": 26.91101500896275,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 14.54930129593913,
277
+ "count": 45474,
278
  "is_parallel": true,
279
+ "self": 14.54930129593913
280
  },
281
  "communicator.exchange": {
282
+ "total": 467.0953741240073,
283
+ "count": 45474,
284
  "is_parallel": true,
285
+ "self": 467.0953741240073
286
  },
287
  "steps_from_proto": {
288
+ "total": 91.59503078103126,
289
+ "count": 45474,
290
  "is_parallel": true,
291
+ "self": 17.562729008111546,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 74.03230177291971,
295
+ "count": 454740,
296
  "is_parallel": true,
297
+ "self": 74.03230177291971
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.00018398300016997382,
313
  "count": 1,
314
+ "self": 0.00018398300016997382,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 1188.9823670608157,
324
+ "count": 1749470,
325
  "is_parallel": true,
326
+ "self": 38.48850842071897,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 656.9798011880985,
330
+ "count": 1749470,
331
  "is_parallel": true,
332
+ "self": 654.7423406270982,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 2.237460561000262,
336
+ "count": 10,
337
  "is_parallel": true,
338
+ "self": 2.237460561000262
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 493.51405745199827,
344
+ "count": 227,
345
  "is_parallel": true,
346
+ "self": 154.49580333598442,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 339.01825411601385,
350
+ "count": 11571,
351
  "is_parallel": true,
352
+ "self": 339.01825411601385
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.1142621170001803,
364
  "count": 1,
365
+ "self": 0.0015201670003079926,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.1127419499998723,
369
  "count": 1,
370
+ "self": 0.1127419499998723
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -1,20 +1,11 @@
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
4
- {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 13.727272727272727,
8
- "creation_time": 1720125138.4171848,
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": 20.272727272727273,
17
- "creation_time": 1720125261.2116516,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
@@ -22,8 +13,8 @@
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 24.09090909090909,
26
- "creation_time": 1720125383.884589,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
@@ -31,29 +22,83 @@
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 26.0,
35
- "creation_time": 1720125503.1412559,
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": 26.0,
44
- "creation_time": 1720125503.2669232,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 26.0,
54
- "creation_time": 1720125503.2669232,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
 
 
 
 
 
 
 
 
 
4
  {
5
  "steps": 99960,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
7
+ "reward": 25.09090909090909,
8
+ "creation_time": 1720126382.0461097,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
11
  ]
 
13
  {
14
  "steps": 149984,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
16
+ "reward": 25.181818181818183,
17
+ "creation_time": 1720126506.9622428,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
20
  ]
 
22
  {
23
  "steps": 199984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
25
+ "reward": 26.636363636363637,
26
+ "creation_time": 1720126625.472967,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 249944,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.onnx",
34
+ "reward": 25.818181818181817,
35
+ "creation_time": 1720126744.6064053,
36
+ "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 299968,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
43
+ "reward": 27.272727272727273,
44
+ "creation_time": 1720126869.5179017,
45
+ "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 349992,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.onnx",
52
+ "reward": 27.0,
53
+ "creation_time": 1720126990.351025,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 399992,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.onnx",
61
+ "reward": 27.272727272727273,
62
+ "creation_time": 1720127106.2494328,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 449952,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.onnx",
70
+ "reward": 26.727272727272727,
71
+ "creation_time": 1720127224.6464312,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 499976,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.onnx",
79
+ "reward": 27.363636363636363,
80
+ "creation_time": 1720127343.903539,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 500104,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.onnx",
88
+ "reward": 27.363636363636363,
89
+ "creation_time": 1720127344.044839,
90
  "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 500104,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 27.363636363636363,
99
+ "creation_time": 1720127344.044839,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.pt"
102
  ]
103
  }
104
  },