Hugging Face's logo

Zayneb17
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
Zayneb17 commited on
Commit
e6ee2c7
·
verified ·
1 Parent(s): 59eab51

First Push

Browse files
Files changed (29) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-1599976.onnx +3 -0
  3. SnowballTarget/SnowballTarget-1599976.pt +3 -0
  4. SnowballTarget/SnowballTarget-1649992.onnx +3 -0
  5. SnowballTarget/SnowballTarget-1649992.pt +3 -0
  6. SnowballTarget/SnowballTarget-1699936.onnx +3 -0
  7. SnowballTarget/SnowballTarget-1699936.pt +3 -0
  8. SnowballTarget/SnowballTarget-1749960.onnx +3 -0
  9. SnowballTarget/SnowballTarget-1749960.pt +3 -0
  10. SnowballTarget/SnowballTarget-1799984.onnx +3 -0
  11. SnowballTarget/SnowballTarget-1799984.pt +3 -0
  12. SnowballTarget/SnowballTarget-1849984.onnx +3 -0
  13. SnowballTarget/SnowballTarget-1849984.pt +3 -0
  14. SnowballTarget/SnowballTarget-1899944.onnx +3 -0
  15. SnowballTarget/SnowballTarget-1899944.pt +3 -0
  16. SnowballTarget/SnowballTarget-1949968.onnx +3 -0
  17. SnowballTarget/SnowballTarget-1949968.pt +3 -0
  18. SnowballTarget/SnowballTarget-1999992.onnx +3 -0
  19. SnowballTarget/SnowballTarget-1999992.pt +3 -0
  20. SnowballTarget/SnowballTarget-2000504.onnx +3 -0
  21. SnowballTarget/SnowballTarget-2000504.pt +3 -0
  22. SnowballTarget/SnowballTarget-217624.pt +3 -0
  23. SnowballTarget/checkpoint.pt +1 -1
  24. SnowballTarget/events.out.tfevents.1754699137.185baa4f270c.28548.0 +3 -0
  25. config.json +1 -1
  26. configuration.yaml +2 -2
  27. run_logs/Player-0.log +15 -15
  28. run_logs/timers.json +161 -161
  29. run_logs/training_status.json +74 -29
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8862b98860c783a978c4cc03d962ba2fee7921ddbe39244b538b46b923bcc747
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9841f941fb9a897027ff163a8a93ab602fe5b0319799162ca1826e6c20f3c4d
3
  size 650646
SnowballTarget/SnowballTarget-1599976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4afa243dab400cf18b0a02ab1730851ae951fc8788599eded3cd063ae08de3c
3
+ size 650646
SnowballTarget/SnowballTarget-1599976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:045e77ba001c8bddb0204f8a59626f1bd56adbbd1c63e25e04795d6f158b8439
3
+ size 3849745
SnowballTarget/SnowballTarget-1649992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e409d384b5008883387d82078736dc61a5b42cafb4119f556924f65b1fa1adb0
3
+ size 650646
SnowballTarget/SnowballTarget-1649992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5962eab85436ae2e6edef7db0de6b95031e3b7396acae12c36ff1142110a8baf
3
+ size 3849745
SnowballTarget/SnowballTarget-1699936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dc6b84631008bc4983497b11aef32e31471b8d989c8bc86be21c33a8f3f3e8c
3
+ size 650646
SnowballTarget/SnowballTarget-1699936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d86ceaf1c55400a5c2919c1a0e284c02d2ef099e28ef111648459a2456aeee0
3
+ size 3849745
SnowballTarget/SnowballTarget-1749960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90f0402ab2620fddbc41614e8a8bb413db78a19de397a4697c5bd32bd19db45f
3
+ size 650646
SnowballTarget/SnowballTarget-1749960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ccec63f0b00aaeb6e92a58ad5958162c7acff893b7c6c72370740b88650344e
3
+ size 3849745
SnowballTarget/SnowballTarget-1799984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3727cf0a8b6044853b43c8e1f754783f0abaf526e602e42017c0f7f47f15875c
3
+ size 650646
SnowballTarget/SnowballTarget-1799984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec939383e04fdd681b060514a749a3c2cf46b84e46cff9e3c92c0a3185be1775
3
+ size 3849745
SnowballTarget/SnowballTarget-1849984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46dbd23395e1943ba3bf6e55c2ae6d27ce38c18d9ed788a3372bc2f352cde2a3
3
+ size 650646
SnowballTarget/SnowballTarget-1849984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a9ee6de841dfac9f4966d3377d362198c2ed9a41859fcff967e3022327e3894
3
+ size 3849745
SnowballTarget/SnowballTarget-1899944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1372f7bd375f82d4269421b58f1d3725275eff99cfc6af06dcad62476de3a723
3
+ size 650646
SnowballTarget/SnowballTarget-1899944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec2e8aec58555209b5f7ba6d30a4f7c424561e72eb4ecaa873fd3af85874ac9d
3
+ size 3849745
SnowballTarget/SnowballTarget-1949968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f528307e35166efd1414a77e78ec1138c81cd9782524b790483f8da03cc26ca
3
+ size 650646
SnowballTarget/SnowballTarget-1949968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ea2e1dd4c836c7fa3e29ad17f90bcb94825c373e167e8c5db8e80d7b4ad76a1
3
+ size 3849745
SnowballTarget/SnowballTarget-1999992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9841f941fb9a897027ff163a8a93ab602fe5b0319799162ca1826e6c20f3c4d
3
+ size 650646
SnowballTarget/SnowballTarget-1999992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76a945c711c24e3b7dc90f01a13d29273390aa90b233e74a1add59e3a91310bc
3
+ size 3849745
SnowballTarget/SnowballTarget-2000504.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9841f941fb9a897027ff163a8a93ab602fe5b0319799162ca1826e6c20f3c4d
3
+ size 650646
SnowballTarget/SnowballTarget-2000504.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f3d170fcffe0b8f206433dc8bd796cff3aa1238d711ab3eebf848a803320fc0
3
+ size 3849745
SnowballTarget/SnowballTarget-217624.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7434a9ab64215f745b5db5cf72483332ee9de6ac8b1b6de76d8282edd36cdf9c
3
+ size 3849604
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8c3d21b17537d3ddfa0a37266da74366eda2f6ccfa10725d039414be7f5e779
3
  size 3848757
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:725d90a00ca11031fbcba22dee82ef5a590936d860a57fa20f51bdaeaedc14db
3
  size 3848757
SnowballTarget/events.out.tfevents.1754699137.185baa4f270c.28548.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fa45b051db7accb63c54bd6f5957980c66bab9ae51b68b8a317c85b9cafcac1
3
+ size 165292
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": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "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": 2000000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "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: false
@@ -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: 2000000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: false
 
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
@@ -31,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
- - Completed reload, in 0.143 seconds
35
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -42,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
42
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
43
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
44
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
45
- UnloadTime: 0.974204 ms
46
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
47
  requesting resize 84 x 84
48
  Setting up 1 worker threads for Enlighten.
@@ -50,7 +50,7 @@ Memory Statistics:
50
  [ALLOC_TEMP_TLS] TLS Allocator
51
  StackAllocators :
52
  [ALLOC_TEMP_MAIN]
53
- Peak usage frame count: [8.0 KB-16.0 KB]: 5367 frames, [16.0 KB-32.0 KB]: 90 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
@@ -172,16 +172,16 @@ Memory Statistics:
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]: 5458 frames
176
  Requested Block Size 16.0 MB
177
- Peak Block count 1
178
- Peak Allocated memory 7.0 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
- Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
- Peak Allocated memory 17.5 MB
185
  Peak Large allocation bytes 16.0 MB
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
@@ -210,13 +210,13 @@ Memory Statistics:
210
  Used Block count 1
211
  Peak Allocated bytes 1.0 MB
212
  [ALLOC_GFX_MAIN]
213
- Peak usage frame count: [32.0 KB-64.0 KB]: 2230 frames, [64.0 KB-128.0 KB]: 3228 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
- Peak Allocated memory 68.2 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
- Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
220
  Requested Block Size 16.0 MB
221
  Peak Block count 1
222
  Peak Allocated memory 39.6 KB
@@ -228,13 +228,13 @@ Memory Statistics:
228
  Used Block count 1
229
  Peak Allocated bytes 1.0 MB
230
  [ALLOC_CACHEOBJECTS_MAIN]
231
- Peak usage frame count: [0.5 MB-1.0 MB]: 5458 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]: 5457 frames, [2.0 MB-4.0 MB]: 1 frames
238
  Requested Block Size 4.0 MB
239
  Peak Block count 1
240
  Peak Allocated memory 2.2 MB
@@ -246,13 +246,13 @@ Memory Statistics:
246
  Used Block count 1
247
  Peak Allocated bytes 1.0 MB
248
  [ALLOC_TYPETREE_MAIN]
249
- Peak usage frame count: [0-1.0 KB]: 5458 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]: 5458 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
 
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.114 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: 0.928663 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]: 53650 frames, [16.0 KB-32.0 KB]: 909 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]: 10846 frames, [8.0 MB-16.0 MB]: 29904 frames, [16.0 MB-32.0 MB]: 13810 frames
176
  Requested Block Size 16.0 MB
177
+ Peak Block count 2
178
+ Peak Allocated memory 24.4 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 54560 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.7 MB
185
  Peak Large allocation bytes 16.0 MB
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
 
210
  Used Block count 1
211
  Peak Allocated bytes 1.0 MB
212
  [ALLOC_GFX_MAIN]
213
+ Peak usage frame count: [32.0 KB-64.0 KB]: 53247 frames, [64.0 KB-128.0 KB]: 1313 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 66.4 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 54560 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]: 54560 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]: 54559 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]: 54560 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]: 54560 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": 1.0315182209014893,
6
- "min": 0.9861311316490173,
7
- "max": 2.8433568477630615,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 9803.548828125,
12
- "min": 9718.7509765625,
13
- "max": 29024.986328125,
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": 11.093741416931152,
30
- "min": 0.4543501138687134,
31
- "max": 11.093741416931152,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2163.279541015625,
36
- "min": 88.1439208984375,
37
- "max": 2249.35107421875,
38
- "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.06087401443137958,
42
- "min": 0.06087401443137958,
43
- "max": 0.07543022676402995,
44
- "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.24349605772551833,
48
- "min": 0.24349605772551833,
49
- "max": 0.37715113382014975,
50
- "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.18950479353467625,
54
- "min": 0.1309527693505801,
55
- "max": 0.2796211578682357,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.758019174138705,
60
- "min": 0.5238110774023204,
61
- "max": 1.3758486868704067,
62
- "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
- "value": 8.082097306000005e-06,
66
- "min": 8.082097306000005e-06,
67
- "max": 0.000291882002706,
68
- "count": 20
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
- "value": 3.232838922400002e-05,
72
- "min": 3.232838922400002e-05,
73
- "max": 0.00138516003828,
74
- "count": 20
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
- "value": 0.10269400000000001,
78
- "min": 0.10269400000000001,
79
- "max": 0.19729400000000002,
80
- "count": 20
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
- "value": 0.41077600000000003,
84
- "min": 0.41077600000000003,
85
- "max": 0.96172,
86
- "count": 20
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
- "value": 0.0001444306000000001,
90
- "min": 0.0001444306000000001,
91
- "max": 0.0048649706,
92
- "count": 20
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
- "value": 0.0005777224000000004,
96
- "min": 0.0005777224000000004,
97
- "max": 0.023089828,
98
- "count": 20
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
- "count": 20
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
- "value": 8756.0,
108
  "min": 8756.0,
109
  "max": 10945.0,
110
- "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 21.886363636363637,
114
- "min": 3.659090909090909,
115
- "max": 21.886363636363637,
116
- "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 963.0,
120
- "min": 161.0,
121
- "max": 1203.0,
122
- "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 21.886363636363637,
126
- "min": 3.659090909090909,
127
- "max": 21.886363636363637,
128
- "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 963.0,
132
- "min": 161.0,
133
- "max": 1203.0,
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": "1754698374",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
- "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1754698985"
160
  },
161
- "total": 610.4160629050002,
162
  "count": 1,
163
- "self": 0.6815846070007865,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.02867158999970343,
167
  "count": 1,
168
- "self": 0.02867158999970343
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 609.7058067079997,
172
  "count": 1,
173
- "self": 0.6316897300257551,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 2.4595358830001715,
177
  "count": 1,
178
- "self": 2.4595358830001715
179
  },
180
  "TrainerController.advance": {
181
- "total": 606.5374873979736,
182
- "count": 18192,
183
- "self": 0.6202493079699707,
184
  "children": {
185
  "env_step": {
186
- "total": 430.27369343401415,
187
- "count": 18192,
188
- "self": 374.27404495995916,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 55.612286848987424,
192
- "count": 18192,
193
- "self": 1.8631844549690868,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 53.74910239401834,
197
- "count": 18192,
198
- "self": 53.74910239401834
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.38736162506756955,
204
- "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 607.6399782170297,
209
- "count": 18192,
210
  "is_parallel": true,
211
- "self": 279.85400680499833,
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": 0.003550990999883652,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0011950600001000566,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0023559309997835953,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0023559309997835953
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.04908839000017906,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0007688880000387144,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0005182740001146158,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0005182740001146158
244
  },
245
  "communicator.exchange": {
246
- "total": 0.04531309000003603,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.04531309000003603
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0024881379999897035,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00045906599962108885,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0020290720003686147,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0020290720003686147
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 327.78597141203136,
271
- "count": 18191,
272
  "is_parallel": true,
273
- "self": 15.118217826041928,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 7.992187652975645,
277
- "count": 18191,
278
  "is_parallel": true,
279
- "self": 7.992187652975645
280
  },
281
  "communicator.exchange": {
282
- "total": 259.63657296398196,
283
- "count": 18191,
284
  "is_parallel": true,
285
- "self": 259.63657296398196
286
  },
287
  "steps_from_proto": {
288
- "total": 45.038992969031824,
289
- "count": 18191,
290
  "is_parallel": true,
291
- "self": 8.634671352006535,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 36.40432161702529,
295
- "count": 181910,
296
  "is_parallel": true,
297
- "self": 36.40432161702529
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 175.64354465598944,
311
- "count": 18192,
312
- "self": 0.8180750449751031,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 31.154823918010607,
316
- "count": 18192,
317
- "self": 30.725105902010455,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.4297180160001517,
321
- "count": 4,
322
- "self": 0.4297180160001517
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 143.67064569300373,
328
- "count": 90,
329
- "self": 58.7345759180148,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 84.93606977498894,
333
- "count": 4587,
334
- "self": 84.93606977498894
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 1.2939999578520656e-06,
344
  "count": 1,
345
- "self": 1.2939999578520656e-06
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.07709240300027886,
349
  "count": 1,
350
- "self": 0.0011292070003037225,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.07596319599997514,
354
  "count": 1,
355
- "self": 0.07596319599997514
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.48494020104408264,
6
+ "min": 0.4389359652996063,
7
+ "max": 2.8448941707611084,
8
+ "count": 200
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 4992.9443359375,
12
+ "min": 4197.14599609375,
13
+ "max": 29040.6796875,
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": 14.192525863647461,
30
+ "min": 0.47541970014572144,
31
+ "max": 14.546624183654785,
32
+ "count": 200
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2909.4677734375,
36
+ "min": 92.2314224243164,
37
+ "max": 2976.600341796875,
38
+ "count": 200
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.066127688083889,
42
+ "min": 0.05954793449857379,
43
+ "max": 0.0798550780768981,
44
+ "count": 200
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.330638440419445,
48
+ "min": 0.23819173799429516,
49
+ "max": 0.3798116480408912,
50
+ "count": 200
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.1481990499239342,
54
+ "min": 0.12890622285651226,
55
+ "max": 0.3219272695189598,
56
+ "count": 200
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.740995249619671,
60
+ "min": 0.5160722804127955,
61
+ "max": 1.5637007294332281,
62
+ "count": 200
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
+ "value": 7.032997656000039e-07,
66
+ "min": 7.032997656000039e-07,
67
+ "max": 0.00029918820027059994,
68
+ "count": 200
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
+ "value": 3.5164988280000196e-06,
72
+ "min": 3.5164988280000196e-06,
73
+ "max": 0.0014885160038279998,
74
+ "count": 200
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
+ "value": 0.10023440000000002,
78
+ "min": 0.10023440000000002,
79
+ "max": 0.1997294,
80
+ "count": 200
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
+ "value": 0.5011720000000001,
84
+ "min": 0.4029176,
85
+ "max": 0.996172,
86
+ "count": 200
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
+ "value": 2.1696560000000067e-05,
90
+ "min": 2.1696560000000067e-05,
91
+ "max": 0.004986497059999999,
92
+ "count": 200
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
+ "value": 0.00010848280000000034,
96
+ "min": 0.00010848280000000034,
97
+ "max": 0.024808982800000004,
98
+ "count": 200
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
+ "count": 200
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
+ "value": 10945.0,
108
  "min": 8756.0,
109
  "max": 10945.0,
110
+ "count": 200
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 28.363636363636363,
114
+ "min": 4.068181818181818,
115
+ "max": 28.545454545454547,
116
+ "count": 200
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1560.0,
120
+ "min": 179.0,
121
+ "max": 1563.0,
122
+ "count": 200
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 28.363636363636363,
126
+ "min": 4.068181818181818,
127
+ "max": 28.545454545454547,
128
+ "count": 200
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1560.0,
132
+ "min": 179.0,
133
+ "max": 1563.0,
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": "1754699136",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1754705193"
160
  },
161
+ "total": 6057.009083854,
162
  "count": 1,
163
+ "self": 1.0899876410003344,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.04210754299992914,
167
  "count": 1,
168
+ "self": 0.04210754299992914
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 6055.876988669999,
172
  "count": 1,
173
+ "self": 6.029749486847322,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.068806665000011,
177
  "count": 1,
178
+ "self": 2.068806665000011
179
  },
180
  "TrainerController.advance": {
181
+ "total": 6047.651694401154,
182
+ "count": 181864,
183
+ "self": 6.389894466591613,
184
  "children": {
185
  "env_step": {
186
+ "total": 4226.218375478724,
187
+ "count": 181864,
188
+ "self": 3669.7648168563333,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 552.4364153810843,
192
+ "count": 181864,
193
+ "self": 18.211977415011006,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 534.2244379660733,
197
+ "count": 181864,
198
+ "self": 534.2244379660733
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 4.0171432413062576,
204
+ "count": 181864,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 6037.240575935578,
209
+ "count": 181864,
210
  "is_parallel": true,
211
+ "self": 2824.0741641150885,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.002369099000134156,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.000705273999756173,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.001663825000377983,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.001663825000377983
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.04726861500012092,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0007977440004651726,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0005030379998061107,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0005030379998061107
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.04348146599977554,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.04348146599977554
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0024863670000740967,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0005072769999969751,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0019790900000771217,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0019790900000771217
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 3213.1664118204894,
271
+ "count": 181863,
272
  "is_parallel": true,
273
+ "self": 150.78712598213588,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 78.341402653356,
277
+ "count": 181863,
278
  "is_parallel": true,
279
+ "self": 78.341402653356
280
  },
281
  "communicator.exchange": {
282
+ "total": 2537.1597086211486,
283
+ "count": 181863,
284
  "is_parallel": true,
285
+ "self": 2537.1597086211486
286
  },
287
  "steps_from_proto": {
288
+ "total": 446.8781745638489,
289
+ "count": 181863,
290
  "is_parallel": true,
291
+ "self": 84.53929674381061,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 362.3388778200383,
295
+ "count": 1818630,
296
  "is_parallel": true,
297
+ "self": 362.3388778200383
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 1815.0434244558382,
311
+ "count": 181864,
312
+ "self": 8.097857849059437,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 309.69932153977925,
316
+ "count": 181864,
317
+ "self": 306.21368697577645,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 3.485634564002794,
321
+ "count": 40,
322
+ "self": 3.485634564002794
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 1497.2462450669996,
328
+ "count": 909,
329
+ "self": 566.3734445209602,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 930.8728005460393,
333
+ "count": 46356,
334
+ "self": 930.8728005460393
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 1.710999640636146e-06,
344
  "count": 1,
345
+ "self": 1.710999640636146e-06
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.12673640599859937,
349
  "count": 1,
350
+ "self": 0.0030466929983958835,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.12368971300020348,
354
  "count": 1,
355
+ "self": 0.12368971300020348
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -2,58 +2,103 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 14.545454545454545,
8
- "creation_time": 1754698524.9046457,
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": 20.363636363636363,
17
- "creation_time": 1754698673.3261435,
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": 20.454545454545453,
26
- "creation_time": 1754698824.6664653,
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": 21.272727272727273,
35
- "creation_time": 1754698984.3105063,
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": 21.272727272727273,
44
- "creation_time": 1754698984.4010973,
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": 21.272727272727273,
54
- "creation_time": 1754698984.4010973,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 1599976,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1599976.onnx",
7
+ "reward": 27.181818181818183,
8
+ "creation_time": 1754703967.9482887,
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": 27.9,
17
+ "creation_time": 1754704120.4419851,
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": 27.272727272727273,
26
+ "creation_time": 1754704277.255187,
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": 28.09090909090909,
35
+ "creation_time": 1754704430.3281245,
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": 28.272727272727273,
44
+ "creation_time": 1754704582.933879,
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": 1754704732.0501177,
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": 28.454545454545453,
62
+ "creation_time": 1754704884.9548204,
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": 27.272727272727273,
71
+ "creation_time": 1754705037.7548316,
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": 29.727272727272727,
80
+ "creation_time": 1754705192.0096767,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-1999992.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 2000504,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-2000504.onnx",
88
+ "reward": 29.727272727272727,
89
+ "creation_time": 1754705192.2246587,
90
+ "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-2000504.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 2000504,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 29.727272727272727,
99
+ "creation_time": 1754705192.2246587,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-2000504.pt"
102
  ]
103
  }
104
  },