Hugging Face's logo

hythyt
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
hythyt commited on
Commit
799b478
•
1 Parent(s): 18c0624

First Push

Browse files
Files changed (28) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-499976.onnx +3 -0
  3. SnowballTarget/SnowballTarget-499976.pt +3 -0
  4. SnowballTarget/SnowballTarget-549992.onnx +3 -0
  5. SnowballTarget/SnowballTarget-549992.pt +3 -0
  6. SnowballTarget/SnowballTarget-599936.onnx +3 -0
  7. SnowballTarget/SnowballTarget-599936.pt +3 -0
  8. SnowballTarget/SnowballTarget-649960.onnx +3 -0
  9. SnowballTarget/SnowballTarget-649960.pt +3 -0
  10. SnowballTarget/SnowballTarget-699984.onnx +3 -0
  11. SnowballTarget/SnowballTarget-699984.pt +3 -0
  12. SnowballTarget/SnowballTarget-749984.onnx +3 -0
  13. SnowballTarget/SnowballTarget-749984.pt +3 -0
  14. SnowballTarget/SnowballTarget-799944.onnx +3 -0
  15. SnowballTarget/SnowballTarget-799944.pt +3 -0
  16. SnowballTarget/SnowballTarget-849968.onnx +3 -0
  17. SnowballTarget/SnowballTarget-849968.pt +3 -0
  18. SnowballTarget/SnowballTarget-899992.onnx +3 -0
  19. SnowballTarget/SnowballTarget-899992.pt +3 -0
  20. SnowballTarget/SnowballTarget-900376.onnx +3 -0
  21. SnowballTarget/SnowballTarget-900376.pt +3 -0
  22. SnowballTarget/checkpoint.pt +1 -1
  23. SnowballTarget/events.out.tfevents.1708449723.4c12dffcb5cf.2586.0 +3 -0
  24. config.json +1 -1
  25. configuration.yaml +3 -3
  26. run_logs/Player-0.log +15 -15
  27. run_logs/timers.json +160 -160
  28. run_logs/training_status.json +53 -53
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:531668938c36bf5f46b1e9723fd2db199556688e4de01eecd75f50014f82d2e8
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8af432a0651bc1cf623516ce46db590240c37b47d4f02450686fbb8bd3a52b8c
3
  size 650646
SnowballTarget/SnowballTarget-499976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5ac66db8fc49934e083278c497014d62dbccea56fb9d704d49b430f7336baaf
3
+ size 650646
SnowballTarget/SnowballTarget-499976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e680837495393b7c578ca4face344f2386b72fafcf0f374e6f4c18f47f194eab
3
+ size 3850075
SnowballTarget/SnowballTarget-549992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00bad4456376234e69feea0558872fcc748acaf5a61952204e290d665a2bec3f
3
+ size 650646
SnowballTarget/SnowballTarget-549992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:107b154bb7c24f49680fe9baade6fce9606a0c06806d5c14462fc142f893a3ee
3
+ size 3850075
SnowballTarget/SnowballTarget-599936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a0611851b2222a28314b2f67c14454dcdb72976ff933210014a9d55b64e1255
3
+ size 650646
SnowballTarget/SnowballTarget-599936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7214d15f3b5f5c3e3bda68025ca02b4e50ee249c353093ce1084fd5019de2ef
3
+ size 3850075
SnowballTarget/SnowballTarget-649960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebc142c102fb0295cd085632fd1e5149c55018a17f4f58740482600dc23b638f
3
+ size 650646
SnowballTarget/SnowballTarget-649960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bf152bf7eaff2a3a59cb1aaf6acfbae532edcfc4d64857625eaecd455ee25e1
3
+ size 3850075
SnowballTarget/SnowballTarget-699984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:772a3a87dbfa00fd1e75d2993c12bf7a3cb8647f6ab95d4916df429f87b6942f
3
+ size 650646
SnowballTarget/SnowballTarget-699984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5438d21a805f6d839f2fa421ad83120b7764972d88eafd52b1e9b551bd373986
3
+ size 3850075
SnowballTarget/SnowballTarget-749984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f4f124482007b7ecc0107de3f29974eb4fa9f97c9934378c6f06960f5a46746
3
+ size 650646
SnowballTarget/SnowballTarget-749984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdfbaabc3757f58988e6d1019fbf8bccd8ab94b64d7da2967f82e2b094fb5658
3
+ size 3850075
SnowballTarget/SnowballTarget-799944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67898c6b9ce0df0812ca1e70eb30ec9f15cf0055727febe478cf467c54836b6a
3
+ size 650646
SnowballTarget/SnowballTarget-799944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbdca80522deceb0b23cea8b3803ce6d294f6d979558662a6de1398b34efbc22
3
+ size 3850075
SnowballTarget/SnowballTarget-849968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6ee681e17f09ab7e537e9e34cd6e01a1399be90f45741632767771e15f9ba66
3
+ size 650646
SnowballTarget/SnowballTarget-849968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f583fcc8f42a1b33c481669e70ba9d345ebf2fa7fd51ce1d125228d9d49b6952
3
+ size 3850075
SnowballTarget/SnowballTarget-899992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8af432a0651bc1cf623516ce46db590240c37b47d4f02450686fbb8bd3a52b8c
3
+ size 650646
SnowballTarget/SnowballTarget-899992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4122f5bcba8d893a6d3dbc44ab68d5dc40b6149f1f2c0e75b9e325551f008c7
3
+ size 3850075
SnowballTarget/SnowballTarget-900376.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8af432a0651bc1cf623516ce46db590240c37b47d4f02450686fbb8bd3a52b8c
3
+ size 650646
SnowballTarget/SnowballTarget-900376.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e76ec9becb3b79122961d06a5ea4c5684d2fda6d11abfd35018655ef92257e67
3
+ size 3850075
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e0e0bdc131eebf344379d3a61f6d92e20da1b9eca35a4b51d25c6027b526b8d
3
  size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f153ed7362783edabd1717c5b7035dedae244028edef95e4f2190698f90ef13b
3
  size 3849250
SnowballTarget/events.out.tfevents.1708449723.4c12dffcb5cf.2586.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:885290585db0f0e96098e82e6bc17d3e4c3def15ec7241a4db3d783d4dc05587
3
+ size 80977
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": 2000000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64", "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}
 
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": 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, "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}
configuration.yaml CHANGED
@@ -38,14 +38,14 @@ behaviors:
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
- max_steps: 2000000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
45
  self_play: null
46
  behavioral_cloning: null
47
  env_settings:
48
- env_path: /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64
49
  env_args: null
50
  base_port: 5005
51
  num_envs: 1
@@ -70,7 +70,7 @@ checkpoint_settings:
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
 
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
45
  self_play: null
46
  behavioral_cloning: null
47
  env_settings:
48
+ env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
49
  env_args: null
50
  base_port: 5005
51
  num_envs: 1
 
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
run_logs/Player-0.log CHANGED
@@ -34,7 +34,7 @@ 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 0.092 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 +45,7 @@ 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: 0.719196 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 +53,7 @@ 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]: 53652 frames, [16.0 KB-32.0 KB]: 909 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 +169,22 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 43
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
- Peak usage frame count: [4.0 MB-8.0 MB]: 10923 frames, [8.0 MB-16.0 MB]: 28736 frames, [16.0 MB-32.0 MB]: 14903 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 2
181
- Peak Allocated memory 24.5 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 54562 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.5 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
@@ -213,13 +213,13 @@ 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]: 53202 frames, [64.0 KB-128.0 KB]: 1360 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]: 54562 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
@@ -231,13 +231,13 @@ 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]: 54562 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]: 54561 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 +249,13 @@ 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]: 54562 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]: 54562 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  Peak Allocated memory 1.7 KB
 
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
+ - Completed reload, in 0.088 seconds
38
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
45
  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: 0.728513 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
  [ALLOC_TEMP_TLS] TLS Allocator
54
  StackAllocators :
55
  [ALLOC_TEMP_MAIN]
56
+ Peak usage frame count: [8.0 KB-16.0 KB]: 24156 frames, [16.0 KB-32.0 KB]: 409 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
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
+ Peak main deferred allocation count 44
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
+ Peak usage frame count: [4.0 MB-8.0 MB]: 11801 frames, [8.0 MB-16.0 MB]: 12765 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 2
181
+ Peak Allocated memory 13.8 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
+ Peak usage frame count: [16.0 MB-32.0 MB]: 24566 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
+ Peak Allocated memory 17.8 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
 
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]: 23349 frames, [64.0 KB-128.0 KB]: 1217 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
+ Peak Allocated memory 67.3 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
+ Peak usage frame count: [32.0 KB-64.0 KB]: 24566 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
 
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]: 24566 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]: 24565 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
  Used Block count 1
250
  Peak Allocated bytes 1.0 MB
251
  [ALLOC_TYPETREE_MAIN]
252
+ Peak usage frame count: [0-1.0 KB]: 24566 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]: 24566 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  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": 0.4676729142665863,
6
- "min": 0.4647047519683838,
7
- "max": 2.860957622528076,
8
- "count": 200
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 4820.3046875,
12
- "min": 4443.64892578125,
13
- "max": 29299.06640625,
14
- "count": 200
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 1999992.0,
18
  "min": 9952.0,
19
- "max": 1999992.0,
20
- "count": 200
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 1999992.0,
24
  "min": 9952.0,
25
- "max": 1999992.0,
26
- "count": 200
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 14.382729530334473,
30
- "min": 0.3005019724369049,
31
- "max": 14.529829025268555,
32
- "count": 200
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2948.45947265625,
36
- "min": 58.29738235473633,
37
- "max": 2953.619140625,
38
- "count": 200
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
- "count": 200
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
- "count": 200
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06954078151137247,
54
- "min": 0.05987668705290394,
55
- "max": 0.0779010560600927,
56
- "count": 200
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.34770390755686237,
60
- "min": 0.23950674821161577,
61
- "max": 0.38950528030046355,
62
- "count": 200
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.15490547938674104,
66
- "min": 0.10773771084552887,
67
- "max": 0.2927440986329434,
68
- "count": 200
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.7745273969337052,
72
- "min": 0.4309508433821155,
73
- "max": 1.290336033292845,
74
- "count": 200
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 7.032997656000039e-07,
78
- "min": 7.032997656000039e-07,
79
- "max": 0.00029918820027059994,
80
- "count": 200
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 3.5164988280000196e-06,
84
- "min": 3.5164988280000196e-06,
85
- "max": 0.0014885160038279998,
86
- "count": 200
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.10023440000000002,
90
- "min": 0.10023440000000002,
91
- "max": 0.1997294,
92
- "count": 200
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.5011720000000001,
96
- "min": 0.4029176,
97
- "max": 0.996172,
98
- "count": 200
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
- "value": 2.1696560000000067e-05,
102
- "min": 2.1696560000000067e-05,
103
- "max": 0.004986497059999999,
104
- "count": 200
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.00010848280000000034,
108
- "min": 0.00010848280000000034,
109
- "max": 0.024808982800000004,
110
- "count": 200
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 28.327272727272728,
114
- "min": 3.1136363636363638,
115
- "max": 28.68888888888889,
116
- "count": 200
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1558.0,
120
- "min": 137.0,
121
- "max": 1566.0,
122
- "count": 200
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 28.327272727272728,
126
- "min": 3.1136363636363638,
127
- "max": 28.68888888888889,
128
- "count": 200
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1558.0,
132
- "min": 137.0,
133
- "max": 1566.0,
134
- "count": 200
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 200
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 200
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1708250995",
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 /content/SnowballTarget.yaml --env=/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --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": "2.2.0+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1708255306"
160
  },
161
- "total": 4311.35360025,
162
  "count": 1,
163
- "self": 0.489965753999968,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.04945148699994206,
167
  "count": 1,
168
- "self": 0.04945148699994206
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 4310.814183009001,
172
  "count": 1,
173
- "self": 5.416347300897542,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.177165125999977,
177
  "count": 1,
178
- "self": 3.177165125999977
179
  },
180
  "TrainerController.advance": {
181
- "total": 4302.1299164341035,
182
- "count": 181871,
183
- "self": 2.7885790082082167,
184
  "children": {
185
  "env_step": {
186
- "total": 4299.341337425895,
187
- "count": 181871,
188
- "self": 2792.538878100863,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 1503.858034825993,
192
- "count": 181871,
193
- "self": 14.365423254102552,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 1489.4926115718904,
197
- "count": 181871,
198
- "self": 1489.4926115718904
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 2.9444244990396555,
204
- "count": 181871,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 4299.949203287,
209
- "count": 181871,
210
  "is_parallel": true,
211
- "self": 2105.834313281929,
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": 0.0054633480000347845,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.003968197000062901,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0014951509999718837,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0014951509999718837
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03804084800003693,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006361370001286559,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0004009770000266144,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0004009770000266144
244
  },
245
  "communicator.exchange": {
246
- "total": 0.034934837999912816,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.034934837999912816
250
  },
251
  "steps_from_proto": {
252
- "total": 0.002068895999968845,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0003935549997322596,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0016753410002365854,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0016753410002365854
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 2194.114890005071,
271
- "count": 181870,
272
  "is_parallel": true,
273
- "self": 104.23997799010476,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 51.85728597907166,
277
- "count": 181870,
278
  "is_parallel": true,
279
- "self": 51.85728597907166
280
  },
281
  "communicator.exchange": {
282
- "total": 1708.3360449078327,
283
- "count": 181870,
284
  "is_parallel": true,
285
- "self": 1708.3360449078327
286
  },
287
  "steps_from_proto": {
288
- "total": 329.681581128062,
289
- "count": 181870,
290
  "is_parallel": true,
291
- "self": 60.352540434002776,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 269.32904069405924,
295
- "count": 1818700,
296
  "is_parallel": true,
297
- "self": 269.32904069405924
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.0003272719995948137,
313
  "count": 1,
314
- "self": 0.0003272719995948137,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 4249.562116208759,
324
- "count": 6459827,
325
  "is_parallel": true,
326
- "self": 134.71285545272985,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 2332.078997726028,
330
- "count": 6459827,
331
  "is_parallel": true,
332
- "self": 2326.039195259027,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 6.039802467000527,
336
- "count": 40,
337
  "is_parallel": true,
338
- "self": 6.039802467000527
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 1782.7702630300018,
344
- "count": 909,
345
  "is_parallel": true,
346
- "self": 505.36145151994447,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 1277.4088115100574,
350
- "count": 46356,
351
  "is_parallel": true,
352
- "self": 1277.4088115100574
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.09042687600049248,
364
  "count": 1,
365
- "self": 0.0010059430005640024,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.08942093299992848,
369
  "count": 1,
370
- "self": 0.08942093299992848
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.5601517558097839,
6
+ "min": 0.5137851238250732,
7
+ "max": 2.8594589233398438,
8
+ "count": 90
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 5785.8076171875,
12
+ "min": 4877.3623046875,
13
+ "max": 29315.173828125,
14
+ "count": 90
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 899992.0,
18
  "min": 9952.0,
19
+ "max": 899992.0,
20
+ "count": 90
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 899992.0,
24
  "min": 9952.0,
25
+ "max": 899992.0,
26
+ "count": 90
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 14.026276588439941,
30
+ "min": 0.3239937126636505,
31
+ "max": 14.155049324035645,
32
+ "count": 90
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2875.38671875,
36
+ "min": 62.85477828979492,
37
+ "max": 2901.78515625,
38
+ "count": 90
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 90
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 90
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.06920327269472182,
54
+ "min": 0.05802497048445694,
55
+ "max": 0.07891666372169685,
56
+ "count": 90
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.3460163634736091,
60
+ "min": 0.23209988193782777,
61
+ "max": 0.3945833186084843,
62
+ "count": 90
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.16916274320261154,
66
+ "min": 0.10606509628340455,
67
+ "max": 0.2839184609698314,
68
+ "count": 90
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.8458137160130577,
72
+ "min": 0.4242603851336182,
73
+ "max": 1.4195923048491572,
74
+ "count": 90
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 1.5627661457777764e-06,
78
+ "min": 1.5627661457777764e-06,
79
+ "max": 0.0002981960006013333,
80
+ "count": 90
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 7.813830728888882e-06,
84
+ "min": 7.813830728888882e-06,
85
+ "max": 0.0014744800085066665,
86
+ "count": 90
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10052088888888888,
90
+ "min": 0.10052088888888888,
91
+ "max": 0.19939866666666672,
92
+ "count": 90
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.5026044444444444,
96
+ "min": 0.40648355555555554,
97
+ "max": 0.9914933333333332,
98
+ "count": 90
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 3.599235555555554e-05,
102
+ "min": 3.599235555555554e-05,
103
+ "max": 0.004969993466666666,
104
+ "count": 90
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.0001799617777777777,
108
+ "min": 0.0001799617777777777,
109
+ "max": 0.02457551733333333,
110
+ "count": 90
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 27.490909090909092,
114
+ "min": 3.227272727272727,
115
+ "max": 28.022727272727273,
116
+ "count": 90
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1512.0,
120
+ "min": 142.0,
121
+ "max": 1536.0,
122
+ "count": 90
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 27.490909090909092,
126
+ "min": 3.227272727272727,
127
+ "max": 28.022727272727273,
128
+ "count": 90
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1512.0,
132
+ "min": 142.0,
133
+ "max": 1536.0,
134
+ "count": 90
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 90
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 90
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1708449722",
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 /content/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": "2.2.0+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1708451846"
160
  },
161
+ "total": 2124.288374626,
162
  "count": 1,
163
+ "self": 0.48498972599963963,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.05082832000005055,
167
  "count": 1,
168
+ "self": 0.05082832000005055
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 2123.75255658,
172
  "count": 1,
173
+ "self": 2.9217817370126795,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.5906232009999712,
177
  "count": 1,
178
+ "self": 3.5906232009999712
179
  },
180
  "TrainerController.advance": {
181
+ "total": 2117.142485936987,
182
+ "count": 81884,
183
+ "self": 1.4324566069690263,
184
  "children": {
185
  "env_step": {
186
+ "total": 2115.710029330018,
187
+ "count": 81884,
188
+ "self": 1378.4128894129394,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 735.8304491690193,
192
+ "count": 81884,
193
+ "self": 7.095135940995192,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 728.7353132280241,
197
+ "count": 81884,
198
+ "self": 728.7353132280241
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 1.466690748059591,
204
+ "count": 81884,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 2118.054490967004,
209
+ "count": 81884,
210
  "is_parallel": true,
211
+ "self": 1038.412207756007,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.005791361999968103,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.003882118999740669,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.001909243000227434,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.001909243000227434
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.06741638900007274,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0021878979998746217,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00046122600008402515,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00046122600008402515
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.06259762700005922,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.06259762700005922
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0021696380000548743,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0005997080002089206,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0015699299998459537,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0015699299998459537
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 1079.6422832109968,
271
+ "count": 81883,
272
  "is_parallel": true,
273
+ "self": 51.19035017696319,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 26.557305570040057,
277
+ "count": 81883,
278
  "is_parallel": true,
279
+ "self": 26.557305570040057
280
  },
281
  "communicator.exchange": {
282
+ "total": 835.6340489199785,
283
+ "count": 81883,
284
  "is_parallel": true,
285
+ "self": 835.6340489199785
286
  },
287
  "steps_from_proto": {
288
+ "total": 166.26057854401517,
289
+ "count": 81883,
290
  "is_parallel": true,
291
+ "self": 31.60611159295877,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 134.6544669510564,
295
+ "count": 818830,
296
  "is_parallel": true,
297
+ "self": 134.6544669510564
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.0002615799999148294,
313
  "count": 1,
314
+ "self": 0.0002615799999148294,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 2090.1667035965816,
324
+ "count": 3209209,
325
  "is_parallel": true,
326
+ "self": 69.47002577047579,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 1152.89243171211,
330
+ "count": 3209209,
331
  "is_parallel": true,
332
+ "self": 1149.7660388131098,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 3.126392899000166,
336
+ "count": 18,
337
  "is_parallel": true,
338
+ "self": 3.126392899000166
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 867.8042461139958,
344
+ "count": 409,
345
  "is_parallel": true,
346
+ "self": 242.18361937897726,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 625.6206267350185,
350
+ "count": 20856,
351
  "is_parallel": true,
352
+ "self": 625.6206267350185
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.09740412500013917,
364
  "count": 1,
365
+ "self": 0.0010115459999724408,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.09639257900016673,
369
  "count": 1,
370
+ "self": 0.09639257900016673
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -2,103 +2,103 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 1599976,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1599976.onnx",
7
- "reward": 27.636363636363637,
8
- "creation_time": 1708254453.5691857,
9
  "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-1599976.pt"
11
  ]
12
  },
13
  {
14
- "steps": 1649992,
15
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1649992.onnx",
16
  "reward": 27.7,
17
- "creation_time": 1708254561.7073584,
18
  "auxillary_file_paths": [
19
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-1649992.pt"
20
  ]
21
  },
22
  {
23
- "steps": 1699936,
24
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1699936.onnx",
25
- "reward": 27.636363636363637,
26
- "creation_time": 1708254669.6805897,
27
  "auxillary_file_paths": [
28
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-1699936.pt"
29
  ]
30
  },
31
  {
32
- "steps": 1749960,
33
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1749960.onnx",
34
- "reward": 27.90909090909091,
35
- "creation_time": 1708254776.4041853,
36
  "auxillary_file_paths": [
37
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-1749960.pt"
38
  ]
39
  },
40
  {
41
- "steps": 1799984,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1799984.onnx",
43
- "reward": 27.90909090909091,
44
- "creation_time": 1708254884.3785455,
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-1799984.pt"
47
  ]
48
  },
49
  {
50
- "steps": 1849984,
51
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1849984.onnx",
52
- "reward": 28.272727272727273,
53
- "creation_time": 1708254989.5875938,
54
  "auxillary_file_paths": [
55
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-1849984.pt"
56
  ]
57
  },
58
  {
59
- "steps": 1899944,
60
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1899944.onnx",
61
- "reward": 27.181818181818183,
62
- "creation_time": 1708255095.6929421,
63
  "auxillary_file_paths": [
64
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-1899944.pt"
65
  ]
66
  },
67
  {
68
- "steps": 1949968,
69
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1949968.onnx",
70
- "reward": 28.0,
71
- "creation_time": 1708255201.7594125,
72
  "auxillary_file_paths": [
73
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-1949968.pt"
74
  ]
75
  },
76
  {
77
- "steps": 1999992,
78
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1999992.onnx",
79
- "reward": 28.272727272727273,
80
- "creation_time": 1708255306.2773032,
81
  "auxillary_file_paths": [
82
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-1999992.pt"
83
  ]
84
  },
85
  {
86
- "steps": 2000376,
87
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-2000376.onnx",
88
- "reward": 28.272727272727273,
89
- "creation_time": 1708255306.4143176,
90
  "auxillary_file_paths": [
91
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-2000376.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
- "steps": 2000376,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
- "reward": 28.272727272727273,
99
- "creation_time": 1708255306.4143176,
100
  "auxillary_file_paths": [
101
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-2000376.pt"
102
  ]
103
  }
104
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 499976,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.onnx",
7
+ "reward": 27.545454545454547,
8
+ "creation_time": 1708450944.9982712,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 549992,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-549992.onnx",
16
  "reward": 27.7,
17
+ "creation_time": 1708451062.5529194,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-549992.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 599936,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-599936.onnx",
25
+ "reward": 27.545454545454547,
26
+ "creation_time": 1708451172.757905,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-599936.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 649960,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-649960.onnx",
34
+ "reward": 27.363636363636363,
35
+ "creation_time": 1708451284.4438765,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-649960.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 699984,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-699984.onnx",
43
+ "reward": 26.454545454545453,
44
+ "creation_time": 1708451395.887994,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-699984.pt"
47
  ]
48
  },
49
  {
50
+ "steps": 749984,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-749984.onnx",
52
+ "reward": 28.454545454545453,
53
+ "creation_time": 1708451509.3620343,
54
  "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-749984.pt"
56
  ]
57
  },
58
  {
59
+ "steps": 799944,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-799944.onnx",
61
+ "reward": 27.09090909090909,
62
+ "creation_time": 1708451620.5442085,
63
  "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-799944.pt"
65
  ]
66
  },
67
  {
68
+ "steps": 849968,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-849968.onnx",
70
+ "reward": 26.818181818181817,
71
+ "creation_time": 1708451733.8320491,
72
  "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-849968.pt"
74
  ]
75
  },
76
  {
77
+ "steps": 899992,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-899992.onnx",
79
+ "reward": 28.0,
80
+ "creation_time": 1708451846.338857,
81
  "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-899992.pt"
83
  ]
84
  },
85
  {
86
+ "steps": 900376,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-900376.onnx",
88
+ "reward": 28.0,
89
+ "creation_time": 1708451846.487353,
90
  "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-900376.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 900376,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 28.0,
99
+ "creation_time": 1708451846.487353,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-900376.pt"
102
  ]
103
  }
104
  },