Hugging Face's logo

YuvanKumar
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
Ankit Kumar commited on
Commit
5d1ae11
·
1 Parent(s): 3be3d52

First Push

Browse files
Files changed (28) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-1000208.onnx +3 -0
  3. SnowballTarget/SnowballTarget-1000208.pt +3 -0
  4. SnowballTarget/SnowballTarget-599936.onnx +3 -0
  5. SnowballTarget/SnowballTarget-599936.pt +3 -0
  6. SnowballTarget/SnowballTarget-649960.onnx +3 -0
  7. SnowballTarget/SnowballTarget-649960.pt +3 -0
  8. SnowballTarget/SnowballTarget-699984.onnx +3 -0
  9. SnowballTarget/SnowballTarget-699984.pt +3 -0
  10. SnowballTarget/SnowballTarget-749984.onnx +3 -0
  11. SnowballTarget/SnowballTarget-749984.pt +3 -0
  12. SnowballTarget/SnowballTarget-799944.onnx +3 -0
  13. SnowballTarget/SnowballTarget-799944.pt +3 -0
  14. SnowballTarget/SnowballTarget-849968.onnx +3 -0
  15. SnowballTarget/SnowballTarget-849968.pt +3 -0
  16. SnowballTarget/SnowballTarget-899992.onnx +3 -0
  17. SnowballTarget/SnowballTarget-899992.pt +3 -0
  18. SnowballTarget/SnowballTarget-949992.onnx +3 -0
  19. SnowballTarget/SnowballTarget-949992.pt +3 -0
  20. SnowballTarget/SnowballTarget-999952.onnx +3 -0
  21. SnowballTarget/SnowballTarget-999952.pt +3 -0
  22. SnowballTarget/checkpoint.pt +2 -2
  23. SnowballTarget/events.out.tfevents.1697626676.7bcb63c51498.4974.0 +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 +65 -38
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8bbb0a75c84a251323450fb65e75ada92a136620d39b3218c10e1ecc00c9f3e0
3
  size 650645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc7b9f6cd4ad032a9f6681cb340935d558ceb3c9b9682d04919fc043e0f24e48
3
  size 650645
SnowballTarget/SnowballTarget-1000208.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc7b9f6cd4ad032a9f6681cb340935d558ceb3c9b9682d04919fc043e0f24e48
3
+ size 650645
SnowballTarget/SnowballTarget-1000208.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b86a9bc7daede65bf171c5046fb1c2e7b5343a93474fa0bf462ce7477a7ccd5
3
+ size 3848791
SnowballTarget/SnowballTarget-599936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d691f9f74796e21fa5542529b56ba2b2f599aec98b789c6db5803025d2fcec41
3
+ size 650645
SnowballTarget/SnowballTarget-599936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c785a14e79655a9baad4a525187981f78c19d3c4d6e4cb509fe8eee5249ad45f
3
+ size 3848654
SnowballTarget/SnowballTarget-649960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccb5737d2db590f47c8e839c5167741e7bd15acfd4b4c2be468ef29124b6066d
3
+ size 650645
SnowballTarget/SnowballTarget-649960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:009a3c6e46ce24eac4d3a97ac8ca422b83bdf571e674eddb7b89d8fcc67783f3
3
+ size 3848654
SnowballTarget/SnowballTarget-699984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:801a04c78b391c4d4389f711ef4cfaea3782ccb1767ad058340e738b4ea6ba13
3
+ size 650645
SnowballTarget/SnowballTarget-699984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbf18a59b1f99eb332b67dbe705613101ad60c5df3161a26505c1e2002c147d0
3
+ size 3848654
SnowballTarget/SnowballTarget-749984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c77158f3e2506aa4c6cfc08039b0dfc131493ffbf1bd912b1ddc56ec05e138b7
3
+ size 650645
SnowballTarget/SnowballTarget-749984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9ae9cac4c3e948cbc7a6c4b1c7b8d6136490225bbe21db32c62b3801057a149
3
+ size 3848654
SnowballTarget/SnowballTarget-799944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e288fe389bc29fe1ddb2542c1a9030b3c28f5c152a4d75830f2edd0fec9d52c0
3
+ size 650645
SnowballTarget/SnowballTarget-799944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cfc98763e56132e3b23547489c36c0c1a0f479e3d586611fff7c5744a4420b2
3
+ size 3848654
SnowballTarget/SnowballTarget-849968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a47dede2bc708b4d8f00893dafed62e561bda28208ab7a4baca6b4db0800d172
3
+ size 650645
SnowballTarget/SnowballTarget-849968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bf084638bbb180904c5e085320527ac9ce0379536a0b2b3a5bcd03dda10c21e
3
+ size 3848654
SnowballTarget/SnowballTarget-899992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:898508296973ae8026fdb615895fb6da2f5abbb7b9d41bdce9f2eac6ac7a60f5
3
+ size 650645
SnowballTarget/SnowballTarget-899992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ab4e560c9c4d3faf97776e363adfec9da04a82245765a8eaea1e1d27b06eee8
3
+ size 3848654
SnowballTarget/SnowballTarget-949992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc245e7b55d0dd8831d81a173b825e3790b0c12abbb919aa0ca20f0f2b00e4e0
3
+ size 650645
SnowballTarget/SnowballTarget-949992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8a4f9bf8a47fc863856270282e91bf1a50f85e01df8301f4c7c3ccf10594b32
3
+ size 3848654
SnowballTarget/SnowballTarget-999952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc7b9f6cd4ad032a9f6681cb340935d558ceb3c9b9682d04919fc043e0f24e48
3
+ size 650645
SnowballTarget/SnowballTarget-999952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:345a54edec8ef7829291cfea83ec66930ac115241def705ba055c13ca2d991ab
3
+ size 3848654
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e81a66d76dafdabb982dd0c615deee90eb3d553f6da66cdc16d3d6a2e0cdb471
3
- size 3848811
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34b104de3249403c5b36fca02e8a6ecc76f93925a65a531efa5011e33bef14f2
3
+ size 3847851
SnowballTarget/events.out.tfevents.1697626676.7bcb63c51498.4974.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:391c617ea7583773f09a93d69a4ac21f45196c886f72284b97f06e805fb89117
3
+ size 93544
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 264, "buffer_size": 2048, "learning_rate": 0.0004, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 4, "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": 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}, "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": 264, "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": 1000000, "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}, "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
@@ -5,11 +5,11 @@ behaviors:
5
  hyperparameters:
6
  batch_size: 264
7
  buffer_size: 2048
8
- learning_rate: 0.0004
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
12
- num_epoch: 4
13
  shared_critic: false
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
@@ -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: true
 
5
  hyperparameters:
6
  batch_size: 264
7
  buffer_size: 2048
8
+ learning_rate: 0.0003
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
12
+ num_epoch: 3
13
  shared_critic: false
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 1000000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
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 0.128 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: 0.756838 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]: 8063 frames, [16.0 KB-32.0 KB]: 136 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
@@ -169,19 +169,19 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 45
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]: 8200 frames
179
  Requested Block Size 16.0 MB
180
- Peak Block count 1
181
- Peak Allocated memory 7.4 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 8200 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
  Peak Allocated memory 17.8 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]: 6880 frames, [64.0 KB-128.0 KB]: 1320 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]: 8200 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]: 8200 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]: 8199 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]: 8200 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]: 8200 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 0.070 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: 0.550280 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]: 26827 frames, [16.0 KB-32.0 KB]: 454 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 41
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]: 11122 frames, [8.0 MB-16.0 MB]: 16160 frames
179
  Requested Block Size 16.0 MB
180
+ Peak Block count 2
181
+ Peak Allocated memory 14.5 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
+ Peak usage frame count: [16.0 MB-32.0 MB]: 27282 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
  Peak Allocated memory 17.8 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]: 25634 frames, [64.0 KB-128.0 KB]: 1648 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
+ Peak Allocated memory 67.7 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
+ Peak usage frame count: [32.0 KB-64.0 KB]: 27282 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]: 27282 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]: 27281 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]: 27282 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]: 27282 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
@@ -2,153 +2,153 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.8103706240653992,
6
- "min": 0.807844340801239,
7
- "max": 2.8515784740448,
8
- "count": 30
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8325.748046875,
12
- "min": 7735.56884765625,
13
- "max": 29203.015625,
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": 13.46130084991455,
30
- "min": 0.40719178318977356,
31
- "max": 13.49724006652832,
32
- "count": 30
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2746.10546875,
36
- "min": 78.99520874023438,
37
- "max": 2749.92041015625,
38
- "count": 30
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
- "count": 30
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
- "value": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
- "count": 30
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.050455696602148235,
54
- "min": 0.03958451389280526,
55
- "max": 0.05132645800586033,
56
- "count": 30
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.2522784830107412,
60
- "min": 0.15833805557122105,
61
- "max": 0.25396518236266274,
62
- "count": 30
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.19039288042113184,
66
- "min": 0.11913659021956846,
67
- "max": 0.2871275396086276,
68
- "count": 30
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.9519644021056592,
72
- "min": 0.47654636087827384,
73
- "max": 1.4356376980431378,
74
- "count": 30
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 7.0507649039999975e-06,
78
- "min": 7.0507649039999975e-06,
79
- "max": 0.000392784001804,
80
- "count": 30
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 3.525382451999999e-05,
84
- "min": 3.525382451999999e-05,
85
- "max": 0.0018979200255200002,
86
- "count": 30
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.10176266666666667,
90
- "min": 0.10176266666666667,
91
- "max": 0.198196,
92
- "count": 30
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.5088133333333333,
96
- "min": 0.42025066666666666,
97
- "max": 0.9744800000000001,
98
- "count": 30
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
- "value": 9.795706666666662e-05,
102
- "min": 9.795706666666662e-05,
103
- "max": 0.0049099804000000006,
104
- "count": 30
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.0004897853333333331,
108
- "min": 0.0004897853333333331,
109
- "max": 0.023726551999999998,
110
- "count": 30
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 26.036363636363635,
114
- "min": 3.340909090909091,
115
- "max": 26.75,
116
- "count": 30
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1432.0,
120
- "min": 147.0,
121
- "max": 1444.0,
122
- "count": 30
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 26.036363636363635,
126
- "min": 3.340909090909091,
127
- "max": 26.75,
128
- "count": 30
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1432.0,
132
- "min": 147.0,
133
- "max": 1444.0,
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": "1697616259",
152
  "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
153
  "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.1.0.dev0",
@@ -156,59 +156,59 @@
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.0.1+cu118",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1697616965"
160
  },
161
- "total": 706.6390929570002,
162
  "count": 1,
163
- "self": 0.4364265060003163,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.06732300900011978,
167
  "count": 1,
168
- "self": 0.06732300900011978
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 706.1353434419998,
172
  "count": 1,
173
- "self": 0.84929457697217,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 7.04299500299976,
177
  "count": 1,
178
- "self": 7.04299500299976
179
  },
180
  "TrainerController.advance": {
181
- "total": 698.1503826300273,
182
- "count": 27333,
183
- "self": 0.40815560900819037,
184
  "children": {
185
  "env_step": {
186
- "total": 697.7422270210191,
187
- "count": 27333,
188
- "self": 456.0188004540091,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 241.2230645270506,
192
- "count": 27333,
193
- "self": 2.159738381018542,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 239.06332614603207,
197
- "count": 27333,
198
- "self": 239.06332614603207
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.5003620399593274,
204
- "count": 27333,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 704.255705640041,
209
- "count": 27333,
210
  "is_parallel": true,
211
- "self": 341.37024536006993,
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": 0.006655250000221713,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.004301365000173973,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0023538850000477396,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0023538850000477396
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.051917810999839276,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0007285470001079375,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0004718549998870003,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0004718549998870003
244
  },
245
  "communicator.exchange": {
246
- "total": 0.048757182999906945,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.048757182999906945
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0019602259999373928,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00046687600024597486,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.001493349999691418,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.001493349999691418
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 362.8854602799711,
271
- "count": 27332,
272
  "is_parallel": true,
273
- "self": 16.130657274954956,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 8.320938625029157,
277
- "count": 27332,
278
  "is_parallel": true,
279
- "self": 8.320938625029157
280
  },
281
  "communicator.exchange": {
282
- "total": 285.7860269790258,
283
- "count": 27332,
284
  "is_parallel": true,
285
- "self": 285.7860269790258
286
  },
287
  "steps_from_proto": {
288
- "total": 52.64783740096118,
289
- "count": 27332,
290
  "is_parallel": true,
291
- "self": 9.919021880005857,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 42.72881552095532,
295
- "count": 273320,
296
  "is_parallel": true,
297
- "self": 42.72881552095532
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00047883100023682346,
313
  "count": 1,
314
- "self": 0.00047883100023682346,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 692.4570996939433,
324
- "count": 715583,
325
  "is_parallel": true,
326
- "self": 15.38329598588507,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 393.0956603900563,
330
- "count": 715583,
331
  "is_parallel": true,
332
- "self": 391.8519399300567,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 1.243720459999622,
336
- "count": 6,
337
  "is_parallel": true,
338
- "self": 1.243720459999622
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 283.9781433180019,
344
- "count": 136,
345
  "is_parallel": true,
346
- "self": 118.71959624499868,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 165.25854707300323,
350
- "count": 4352,
351
  "is_parallel": true,
352
- "self": 165.25854707300323
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.09219240100037496,
364
  "count": 1,
365
- "self": 0.0009243160002370132,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.09126808500013794,
369
  "count": 1,
370
- "self": 0.09126808500013794
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.734003484249115,
6
+ "min": 0.6146830916404724,
7
+ "max": 2.868138313293457,
8
+ "count": 100
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 7000.19140625,
12
+ "min": 5941.689453125,
13
+ "max": 29404.154296875,
14
+ "count": 100
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 999952.0,
18
  "min": 9952.0,
19
+ "max": 999952.0,
20
+ "count": 100
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 999952.0,
24
  "min": 9952.0,
25
+ "max": 999952.0,
26
+ "count": 100
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 14.036966323852539,
30
+ "min": 0.23821555078029633,
31
+ "max": 14.050886154174805,
32
+ "count": 100
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2737.20849609375,
36
+ "min": 46.21381759643555,
37
+ "max": 2866.380859375,
38
+ "count": 100
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 100
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 8756.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 100
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.04619872337487626,
54
+ "min": 0.035300275465609356,
55
+ "max": 0.05562673276085661,
56
+ "count": 100
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.18479489349950504,
60
+ "min": 0.15290963122727894,
61
+ "max": 0.27104018708875327,
62
+ "count": 100
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.17768584409107765,
66
+ "min": 0.10611372289713472,
67
+ "max": 0.276020464549462,
68
+ "count": 100
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.7107433763643106,
72
+ "min": 0.4244548915885389,
73
+ "max": 1.38010232274731,
74
+ "count": 100
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 1.3764995412000025e-06,
78
+ "min": 1.3764995412000025e-06,
79
+ "max": 0.00029837640054119997,
80
+ "count": 100
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 5.50599816480001e-06,
84
+ "min": 5.50599816480001e-06,
85
+ "max": 0.001477032007656,
86
+ "count": 100
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10045880000000001,
90
+ "min": 0.10045880000000001,
91
+ "max": 0.19945880000000002,
92
+ "count": 100
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.40183520000000006,
96
+ "min": 0.40183520000000006,
97
+ "max": 0.992344,
98
+ "count": 100
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 3.289412000000004e-05,
102
+ "min": 3.289412000000004e-05,
103
+ "max": 0.00497299412,
104
+ "count": 100
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.00013157648000000017,
108
+ "min": 0.00013157648000000017,
109
+ "max": 0.0246179656,
110
+ "count": 100
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 27.133333333333333,
114
+ "min": 3.0,
115
+ "max": 27.836363636363636,
116
+ "count": 100
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1221.0,
120
+ "min": 132.0,
121
+ "max": 1531.0,
122
+ "count": 100
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 27.133333333333333,
126
+ "min": 3.0,
127
+ "max": 27.836363636363636,
128
+ "count": 100
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1221.0,
132
+ "min": 132.0,
133
+ "max": 1531.0,
134
+ "count": 100
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 100
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 100
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1697626675",
152
  "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
153
  "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.1.0.dev0",
 
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.0.1+cu118",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1697628606"
160
  },
161
+ "total": 1930.654107932,
162
  "count": 1,
163
+ "self": 0.381629933999875,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.041146762999915154,
167
  "count": 1,
168
+ "self": 0.041146762999915154
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 1930.2313312350002,
172
  "count": 1,
173
+ "self": 3.3898680130298544,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 0.7172528490000332,
177
  "count": 1,
178
+ "self": 0.7172528490000332
179
  },
180
  "TrainerController.advance": {
181
+ "total": 1926.06418408897,
182
+ "count": 90937,
183
+ "self": 1.5875737980597933,
184
  "children": {
185
  "env_step": {
186
+ "total": 1924.4766102909102,
187
+ "count": 90937,
188
+ "self": 1468.4817784408601,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 454.4393810670467,
192
+ "count": 90937,
193
+ "self": 7.107732536081812,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 447.3316485309649,
197
+ "count": 90937,
198
+ "self": 447.3316485309649
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 1.55545078300338,
204
+ "count": 90937,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 1923.9537965631027,
209
+ "count": 90937,
210
  "is_parallel": true,
211
+ "self": 776.3636525121385,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.004727159000140091,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.003594310000380574,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.001132848999759517,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.001132848999759517
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.04420192199995654,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0005467000000862754,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00023382999984278285,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00023382999984278285
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.04167875300004198,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.04167875300004198
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0017426389999855019,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0004254120003679418,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.00131722699961756,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.00131722699961756
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 1147.5901440509642,
271
+ "count": 90936,
272
  "is_parallel": true,
273
+ "self": 48.29109200881703,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 27.289921783053842,
277
+ "count": 90936,
278
  "is_parallel": true,
279
+ "self": 27.289921783053842
280
  },
281
  "communicator.exchange": {
282
+ "total": 921.6075682481137,
283
+ "count": 90936,
284
  "is_parallel": true,
285
+ "self": 921.6075682481137
286
  },
287
  "steps_from_proto": {
288
+ "total": 150.40156201097966,
289
+ "count": 90936,
290
  "is_parallel": true,
291
+ "self": 29.358067190893053,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 121.04349482008661,
295
+ "count": 909360,
296
  "is_parallel": true,
297
+ "self": 121.04349482008661
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.00027570000020205043,
313
  "count": 1,
314
+ "self": 0.00027570000020205043,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 1911.2261498505563,
324
+ "count": 2320375,
325
  "is_parallel": true,
326
+ "self": 41.142332553843744,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 1127.2905629417155,
330
+ "count": 2320375,
331
  "is_parallel": true,
332
+ "self": 1124.7231795777154,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 2.5673833640000794,
336
+ "count": 20,
337
  "is_parallel": true,
338
+ "self": 2.5673833640000794
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 742.7932543549971,
344
+ "count": 454,
345
  "is_parallel": true,
346
+ "self": 262.95963818302357,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 479.8336161719735,
350
+ "count": 10893,
351
  "is_parallel": true,
352
+ "self": 479.8336161719735
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.05975058400008493,
364
  "count": 1,
365
+ "self": 0.00067960900014441,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.05907097499994052,
369
  "count": 1,
370
+ "self": 0.05907097499994052
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -2,76 +2,103 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 15.0,
8
- "creation_time": 1697616386.6159952,
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": 22.636363636363637,
17
- "creation_time": 1697616502.4894981,
18
  "auxillary_file_paths": [
19
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
21
  },
22
  {
23
- "steps": 149984,
24
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 25.363636363636363,
26
- "creation_time": 1697616618.4542053,
27
  "auxillary_file_paths": [
28
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
30
  },
31
  {
32
- "steps": 199984,
33
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 26.272727272727273,
35
- "creation_time": 1697616733.0661244,
36
  "auxillary_file_paths": [
37
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
- "steps": 249944,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.onnx",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
  "reward": 26.0,
44
- "creation_time": 1697616849.3572025,
 
 
 
 
 
 
 
 
 
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.pt"
47
  ]
48
  },
49
  {
50
- "steps": 299968,
51
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
52
- "reward": 26.363636363636363,
53
- "creation_time": 1697616965.1288385,
54
  "auxillary_file_paths": [
55
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.pt"
56
  ]
57
  },
58
  {
59
- "steps": 300608,
60
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-300608.onnx",
61
- "reward": 26.363636363636363,
62
- "creation_time": 1697616965.2930634,
63
  "auxillary_file_paths": [
64
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-300608.pt"
65
  ]
66
  }
67
  ],
68
  "final_checkpoint": {
69
- "steps": 300608,
70
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
71
- "reward": 26.363636363636363,
72
- "creation_time": 1697616965.2930634,
73
  "auxillary_file_paths": [
74
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-300608.pt"
75
  ]
76
  }
77
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 599936,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-599936.onnx",
7
+ "reward": 28.0,
8
+ "creation_time": 1697627834.1841924,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-599936.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 649960,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-649960.onnx",
16
+ "reward": 27.272727272727273,
17
+ "creation_time": 1697627930.8565145,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-649960.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 699984,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-699984.onnx",
25
+ "reward": 26.90909090909091,
26
+ "creation_time": 1697628028.4171784,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-699984.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 749984,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-749984.onnx",
34
+ "reward": 27.272727272727273,
35
+ "creation_time": 1697628123.1278749,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-749984.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 799944,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-799944.onnx",
43
+ "reward": 26.545454545454547,
44
+ "creation_time": 1697628218.715837,
45
+ "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-799944.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 849968,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-849968.onnx",
52
+ "reward": 27.181818181818183,
53
+ "creation_time": 1697628317.089699,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-849968.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 899992,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-899992.onnx",
61
  "reward": 26.0,
62
+ "creation_time": 1697628413.8366878,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-899992.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 949992,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-949992.onnx",
70
+ "reward": 27.545454545454547,
71
+ "creation_time": 1697628510.8287146,
72
  "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-949992.pt"
74
  ]
75
  },
76
  {
77
+ "steps": 999952,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-999952.onnx",
79
+ "reward": 28.636363636363637,
80
+ "creation_time": 1697628606.0808067,
81
  "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-999952.pt"
83
  ]
84
  },
85
  {
86
+ "steps": 1000208,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000208.onnx",
88
+ "reward": 28.636363636363637,
89
+ "creation_time": 1697628606.177273,
90
  "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000208.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 1000208,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 28.636363636363637,
99
+ "creation_time": 1697628606.177273,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000208.pt"
102
  ]
103
  }
104
  },