Hugging Face's logo

kalmi901
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
kalmi901 commited on
Commit
6974206
•
1 Parent(s): 85034b1

First Push

Browse files
Files changed (29) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-1000120.onnx +3 -0
  3. SnowballTarget/SnowballTarget-1000120.pt +3 -0
  4. SnowballTarget/SnowballTarget-599976.onnx +3 -0
  5. SnowballTarget/SnowballTarget-599976.pt +3 -0
  6. SnowballTarget/SnowballTarget-649936.onnx +3 -0
  7. SnowballTarget/SnowballTarget-649936.pt +3 -0
  8. SnowballTarget/SnowballTarget-699960.onnx +3 -0
  9. SnowballTarget/SnowballTarget-699960.pt +3 -0
  10. SnowballTarget/SnowballTarget-749960.onnx +3 -0
  11. SnowballTarget/SnowballTarget-749960.pt +3 -0
  12. SnowballTarget/SnowballTarget-799984.onnx +3 -0
  13. SnowballTarget/SnowballTarget-799984.pt +3 -0
  14. SnowballTarget/SnowballTarget-849944.onnx +3 -0
  15. SnowballTarget/SnowballTarget-849944.pt +3 -0
  16. SnowballTarget/SnowballTarget-899968.onnx +3 -0
  17. SnowballTarget/SnowballTarget-899968.pt +3 -0
  18. SnowballTarget/SnowballTarget-949968.onnx +3 -0
  19. SnowballTarget/SnowballTarget-949968.pt +3 -0
  20. SnowballTarget/SnowballTarget-999992.onnx +3 -0
  21. SnowballTarget/SnowballTarget-999992.pt +3 -0
  22. SnowballTarget/checkpoint.pt +1 -1
  23. SnowballTarget/events.out.tfevents.1726854763.3b1d13dc9973.11826.0 +3 -0
  24. SnowballTarget/events.out.tfevents.1726854828.3b1d13dc9973.12158.0 +3 -0
  25. config.json +1 -1
  26. configuration.yaml +3 -3
  27. run_logs/Player-0.log +17 -17
  28. run_logs/timers.json +162 -162
  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 sha256:64740f3c72e1a9ed36516610a7d0105fda1a3244f3c0e79f5f3885ee1251efc7
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd964be09c868315fabf2f99032da4b277f93b78c27daa0d097d296b637d051a
3
  size 650646
SnowballTarget/SnowballTarget-1000120.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd964be09c868315fabf2f99032da4b277f93b78c27daa0d097d296b637d051a
3
+ size 650646
SnowballTarget/SnowballTarget-1000120.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3ca2b79e2dac1951ec2abe51f24dd78231f7f997dc3c742e5d7257774d83abc
3
+ size 3850214
SnowballTarget/SnowballTarget-599976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c69fa0e92d90f2a953f2819c854ad0fda9a4c6768a04855e2136f9a647d7c69
3
+ size 650646
SnowballTarget/SnowballTarget-599976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff2d4771245d3b79e9be5b2de56dd607cf0698a71bc2e2d8c24c084e82b459d3
3
+ size 3850075
SnowballTarget/SnowballTarget-649936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0c43df1e53f2c20a965d08ac1b226944e0e40dec39660f6b514d7d514e6ce06
3
+ size 650646
SnowballTarget/SnowballTarget-649936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:422d70c743048a58156f11992f3adcdbf9e62c93a3852e57ac44b6bd075fad0e
3
+ size 3850075
SnowballTarget/SnowballTarget-699960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bbe3e04313856f5ab70bca30a18440c5e7cbe780602cbe2a0787fd6034f5ba4
3
+ size 650646
SnowballTarget/SnowballTarget-699960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae6e0e026147e139ba6ca981a9946522df70ee04e32b19ecef992145af25055d
3
+ size 3850075
SnowballTarget/SnowballTarget-749960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e7cbda8023bacf2ffa568d62b2d06da789781775515c2adab7281772dee5f71
3
+ size 650646
SnowballTarget/SnowballTarget-749960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94a9b0d035f30bf59b5b7168deb6e4cbb93d6568145ed67d4726148fa329373c
3
+ size 3850075
SnowballTarget/SnowballTarget-799984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cde63e86efbe3eb8b99c939635911a2b36c93bfd206bf2add2771479a495343d
3
+ size 650646
SnowballTarget/SnowballTarget-799984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6a7e4cf7c4806b03eb5ad8141e42951618c327309ad19debf064f957679b023
3
+ size 3850075
SnowballTarget/SnowballTarget-849944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45ea3938a23a44961e7db6f0a04df43dee6a1499908cd5400437c46de43f4ef3
3
+ size 650646
SnowballTarget/SnowballTarget-849944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4846f0aa4a5d94286e8e2ecc40c032cc5e929ff8eade9abaf2a580f16dea1bc2
3
+ size 3850075
SnowballTarget/SnowballTarget-899968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b5b86484a8784c5844a209a13f5dfea3be2371226f5bd3f29b19a1a33dd71bd
3
+ size 650646
SnowballTarget/SnowballTarget-899968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb381c6dddc1ecaf7255891c11634d545eac8257a764b234392e3c37f6666fe5
3
+ size 3850075
SnowballTarget/SnowballTarget-949968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33e3e2cb352cb3830331f6310037dae2eab5d53681cbafc17010f1bb7468d2b2
3
+ size 650646
SnowballTarget/SnowballTarget-949968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b2d37076d066fe8b2a3334ba33378d99f8e7a805c7ec103a598cfc31e9eff5d
3
+ size 3850075
SnowballTarget/SnowballTarget-999992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd964be09c868315fabf2f99032da4b277f93b78c27daa0d097d296b637d051a
3
+ size 650646
SnowballTarget/SnowballTarget-999992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:191c0a256a5816d7a0198682bd2485e81a3321969a8bcb6ce6c490aa2a887943
3
+ size 3850075
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c5bb197e22e26aea241969cf4af3eaab540e8f7a42b93a3e9a2134342388ac8
3
  size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b4c8e5dede7e63c841cf8e0ea6a11031dc9e2e898c2fb29c77d8ba9cff310b2
3
  size 3849250
SnowballTarget/events.out.tfevents.1726854763.3b1d13dc9973.11826.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03d581e1a2b10ce6e5cafcb2a2b05470123e994cc94b090189d5c66215474ad7
3
+ size 1114
SnowballTarget/events.out.tfevents.1726854828.3b1d13dc9973.12158.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a07ace0294e2ad64e68e5ffa0f79a85578545562c695ed5bffe9702f60ce7535
3
+ size 71648
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": 8, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": 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": 8, "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, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -38,7 +38,7 @@ behaviors:
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
- max_steps: 200000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
@@ -69,8 +69,8 @@ checkpoint_settings:
69
  run_id: SnowballTarget1
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: 1000000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
 
69
  run_id: SnowballTarget1
70
  initialize_from: null
71
  load_model: false
72
+ resume: true
73
+ force: false
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 0.082 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: 0.646071 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]: 5368 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
54
  Initial Block Size 4.0 MB
55
  Current Block Size 4.0 MB
56
  Peak Allocated Bytes 2.0 MB
@@ -166,23 +166,23 @@ Memory Statistics:
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
- Peak main deferred allocation count 39
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
173
  Peak Allocated bytes 1.0 MB
174
  [ALLOC_DEFAULT_MAIN]
175
- Peak usage frame count: [4.0 MB-8.0 MB]: 5460 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
- Peak Allocated memory 6.6 MB
179
- Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
- Peak usage frame count: [16.0 MB-32.0 MB]: 5460 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
- Peak Allocated memory 17.8 MB
185
- Peak Large allocation bytes 16.0 MB
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
188
  Used Block Count 1
@@ -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]: 4670 frames, [64.0 KB-128.0 KB]: 790 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
- Peak Allocated memory 67.3 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
- Peak usage frame count: [32.0 KB-64.0 KB]: 5460 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]: 5460 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]: 5459 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]: 5460 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]: 5460 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 0.127 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: 0.881536 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]: 21457 frames, [16.0 KB-32.0 KB]: 363 frames, [2.0 MB-4.0 MB]: 1 frames
54
  Initial Block Size 4.0 MB
55
  Current Block Size 4.0 MB
56
  Peak Allocated Bytes 2.0 MB
 
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
+ Peak main deferred allocation count 41
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
173
  Peak Allocated bytes 1.0 MB
174
  [ALLOC_DEFAULT_MAIN]
175
+ Peak usage frame count: [16.0 MB-32.0 MB]: 21821 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 28.4 MB
179
+ Peak Large allocation bytes 16.0 MB
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [1.0 MB-2.0 MB]: 21821 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 1.4 MB
185
+ Peak Large allocation bytes 0 B
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
188
  Used Block Count 1
 
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]: 21447 frames, [64.0 KB-128.0 KB]: 374 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]: 21821 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]: 21821 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]: 21820 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]: 21821 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]: 21821 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -2,213 +2,213 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.8619441390037537,
6
- "min": 0.8619441390037537,
7
- "max": 2.8516571521759033,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8220.361328125,
12
- "min": 8220.361328125,
13
- "max": 29235.189453125,
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": 13.290427207946777,
30
- "min": 0.6305676698684692,
31
- "max": 13.290427207946777,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2591.63330078125,
36
- "min": 122.33012390136719,
37
- "max": 2694.414306640625,
38
- "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
- "count": 20
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 8756.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
- "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06588000833300398,
54
- "min": 0.06473739288308292,
55
- "max": 0.0748750726102919,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.2635200333320159,
60
- "min": 0.25894957153233167,
61
- "max": 0.36120528270240515,
62
- "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.19148161360884416,
66
- "min": 0.1495115998255,
67
- "max": 0.26746021234019496,
68
- "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.7659264544353767,
72
- "min": 0.598046399302,
73
- "max": 1.3373010617009748,
74
- "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 8.082097306000007e-06,
78
- "min": 8.082097306000007e-06,
79
- "max": 0.000291882002706,
80
- "count": 20
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 3.232838922400003e-05,
84
- "min": 3.232838922400003e-05,
85
- "max": 0.00138516003828,
86
- "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.10269400000000001,
90
- "min": 0.10269400000000001,
91
- "max": 0.197294,
92
- "count": 20
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.41077600000000003,
96
- "min": 0.41077600000000003,
97
- "max": 0.9617200000000001,
98
- "count": 20
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
- "value": 0.0001444306000000001,
102
- "min": 0.0001444306000000001,
103
- "max": 0.0048649706,
104
- "count": 20
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.0005777224000000004,
108
- "min": 0.0005777224000000004,
109
- "max": 0.023089828,
110
- "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.931818181818183,
114
- "min": 4.318181818181818,
115
- "max": 26.181818181818183,
116
- "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1141.0,
120
- "min": 190.0,
121
- "max": 1440.0,
122
- "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.931818181818183,
126
- "min": 4.318181818181818,
127
- "max": 26.181818181818183,
128
- "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1141.0,
132
- "min": 190.0,
133
- "max": 1440.0,
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": "1726853900",
152
  "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
153
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
154
  "mlagents_version": "1.1.0.dev0",
155
  "mlagents_envs_version": "1.1.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.4.1+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1726854507"
160
  },
161
- "total": 606.3211493260001,
162
  "count": 1,
163
- "self": 0.4336520009999276,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.05304578999994192,
167
  "count": 1,
168
- "self": 0.05304578999994192
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 605.8344515350002,
172
  "count": 1,
173
- "self": 0.6367364369789357,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 1.6643452430000707,
177
  "count": 1,
178
- "self": 1.6643452430000707
179
  },
180
  "TrainerController.advance": {
181
- "total": 603.4427088910211,
182
- "count": 18199,
183
- "self": 0.2875258400463281,
184
  "children": {
185
  "env_step": {
186
- "total": 603.1551830509748,
187
- "count": 18199,
188
- "self": 429.33385544599423,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 173.52477825698702,
192
- "count": 18199,
193
- "self": 1.4971410710024884,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 172.02763718598453,
197
- "count": 18199,
198
- "self": 172.02763718598453
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.29654934799350485,
204
- "count": 18199,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 604.5951128360109,
209
- "count": 18199,
210
  "is_parallel": true,
211
- "self": 385.3042974650091,
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": 0.0021467980000124953,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0006779030002235231,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0014688949997889722,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0014688949997889722
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.034837900999946214,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006608210001104453,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0004448709998996492,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0004448709998996492
244
  },
245
  "communicator.exchange": {
246
- "total": 0.031876500999942436,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.031876500999942436
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0018557079999936832,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0003528950001054909,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0015028129998881923,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0015028129998881923
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 219.29081537100183,
271
- "count": 18198,
272
  "is_parallel": true,
273
- "self": 10.241952031000665,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.261837061990946,
277
- "count": 18198,
278
  "is_parallel": true,
279
- "self": 5.261837061990946
280
  },
281
  "communicator.exchange": {
282
- "total": 171.07970117699938,
283
- "count": 18198,
284
  "is_parallel": true,
285
- "self": 171.07970117699938
286
  },
287
  "steps_from_proto": {
288
- "total": 32.70732510101084,
289
- "count": 18198,
290
  "is_parallel": true,
291
- "self": 6.309745509074219,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 26.39757959193662,
295
- "count": 181980,
296
  "is_parallel": true,
297
- "self": 26.39757959193662
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00012378200017337804,
313
  "count": 1,
314
- "self": 0.00012378200017337804,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 597.7480557482022,
324
- "count": 707034,
325
  "is_parallel": true,
326
- "self": 14.714106445086145,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 244.9419569211159,
330
- "count": 707034,
331
  "is_parallel": true,
332
- "self": 243.98783303911569,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 0.9541238820002036,
336
- "count": 4,
337
  "is_parallel": true,
338
- "self": 0.9541238820002036
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 338.09199238200017,
344
- "count": 90,
345
  "is_parallel": true,
346
- "self": 136.18059997000591,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 201.91139241199426,
350
- "count": 12224,
351
  "is_parallel": true,
352
- "self": 201.91139241199426
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.09053718199993455,
364
  "count": 1,
365
- "self": 0.0009107429996220162,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.08962643900031253,
369
  "count": 1,
370
- "self": 0.08962643900031253
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.5326029062271118,
6
+ "min": 0.5227048397064209,
7
+ "max": 0.9090038537979126,
8
+ "count": 80
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 5061.85791015625,
12
+ "min": 4967.78662109375,
13
+ "max": 9239.115234375,
14
+ "count": 80
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 999992.0,
18
+ "min": 209936.0,
19
+ "max": 999992.0,
20
+ "count": 80
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 999992.0,
24
+ "min": 209936.0,
25
+ "max": 999992.0,
26
+ "count": 80
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 14.173223495483398,
30
+ "min": 13.16577434539795,
31
+ "max": 14.405982971191406,
32
+ "count": 80
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2763.778564453125,
36
+ "min": 2567.235595703125,
37
+ "max": 2953.2265625,
38
+ "count": 80
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 80
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 8756.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 80
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.06899481696722004,
54
+ "min": 0.06391147776853091,
55
+ "max": 0.0725305397531723,
56
+ "count": 80
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.27597926786888016,
60
+ "min": 0.26089074859860645,
61
+ "max": 0.3626526987658615,
62
+ "count": 80
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.14936638727565021,
66
+ "min": 0.13474033800337243,
67
+ "max": 0.20730669712921718,
68
+ "count": 80
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.5974655491026009,
72
+ "min": 0.5846467292593682,
73
+ "max": 1.0152903094011196,
74
+ "count": 80
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 1.4028995324000038e-06,
78
+ "min": 1.4028995324000038e-06,
79
+ "max": 0.0002383428205524,
80
+ "count": 80
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 5.611598129600015e-06,
84
+ "min": 5.611598129600015e-06,
85
+ "max": 0.001176864107712,
86
+ "count": 80
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10046760000000002,
90
+ "min": 0.10046760000000002,
91
+ "max": 0.17944760000000004,
92
+ "count": 80
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.40187040000000007,
96
+ "min": 0.40187040000000007,
97
+ "max": 0.8922880000000001,
98
+ "count": 80
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 3.3333240000000065e-05,
102
+ "min": 3.3333240000000065e-05,
103
+ "max": 0.003974435239999999,
104
+ "count": 80
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.00013333296000000026,
108
+ "min": 0.00013333296000000026,
109
+ "max": 0.0196251712,
110
+ "count": 80
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 27.863636363636363,
114
+ "min": 25.10909090909091,
115
+ "max": 28.381818181818183,
116
+ "count": 80
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1226.0,
120
+ "min": 1108.0,
121
+ "max": 1561.0,
122
+ "count": 80
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 27.863636363636363,
126
+ "min": 25.10909090909091,
127
+ "max": 28.381818181818183,
128
+ "count": 80
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1226.0,
132
+ "min": 1108.0,
133
+ "max": 1561.0,
134
+ "count": 80
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 80
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 80
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1726854827",
152
  "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
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": "2.4.1+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1726857174"
160
  },
161
+ "total": 2346.2864499879997,
162
  "count": 1,
163
+ "self": 0.4358599130005132,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.07445213099981629,
167
  "count": 1,
168
+ "self": 0.07445213099981629
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 2345.7761379439994,
172
  "count": 1,
173
+ "self": 2.251796450945676,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.3781630909998057,
177
  "count": 1,
178
+ "self": 2.3781630909998057
179
  },
180
  "TrainerController.advance": {
181
+ "total": 2341.061490449054,
182
+ "count": 72736,
183
+ "self": 1.0147861170685246,
184
  "children": {
185
  "env_step": {
186
+ "total": 2340.0467043319854,
187
+ "count": 72736,
188
+ "self": 1657.531445365043,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 681.2458301628749,
192
+ "count": 72736,
193
+ "self": 5.593772210789666,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 675.6520579520852,
197
+ "count": 72736,
198
+ "self": 675.6520579520852
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 1.269428804067502,
204
+ "count": 72736,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 2341.6077854111395,
209
+ "count": 72736,
210
  "is_parallel": true,
211
+ "self": 1505.3031205361635,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0030896049997863884,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0008106050004244025,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.002278999999361986,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.002278999999361986
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.05363281099971573,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006811249995735125,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004004070001428772,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004004070001428772
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.04846765399997821,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.04846765399997821
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.004083625000021129,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0003947330001210503,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.003688891999900079,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.003688891999900079
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 836.304664874976,
271
+ "count": 72735,
272
  "is_parallel": true,
273
+ "self": 38.80943300871513,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 20.712948599077208,
277
+ "count": 72735,
278
  "is_parallel": true,
279
+ "self": 20.712948599077208
280
  },
281
  "communicator.exchange": {
282
+ "total": 651.1329285991415,
283
+ "count": 72735,
284
  "is_parallel": true,
285
+ "self": 651.1329285991415
286
  },
287
  "steps_from_proto": {
288
+ "total": 125.64935466804218,
289
+ "count": 72735,
290
  "is_parallel": true,
291
+ "self": 23.57902727997498,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 102.0703273880672,
295
+ "count": 727350,
296
  "is_parallel": true,
297
+ "self": 102.0703273880672
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.0001593429997228668,
313
  "count": 1,
314
+ "self": 0.0001593429997228668,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 2318.9619156790004,
324
+ "count": 2749667,
325
  "is_parallel": true,
326
+ "self": 57.1321107081294,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 954.4814090508658,
330
+ "count": 2749667,
331
  "is_parallel": true,
332
+ "self": 952.0762051158654,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 2.4052039350003724,
336
+ "count": 16,
337
  "is_parallel": true,
338
+ "self": 2.4052039350003724
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 1307.3483959200053,
344
+ "count": 363,
345
  "is_parallel": true,
346
+ "self": 508.36442521995286,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 798.9839707000524,
350
+ "count": 49360,
351
  "is_parallel": true,
352
+ "self": 798.9839707000524
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.08452861000023404,
364
  "count": 1,
365
+ "self": 0.001199008000185131,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.08332960200004891,
369
  "count": 1,
370
+ "self": 0.08332960200004891
371
  }
372
  }
373
  }
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": 16.636363636363637,
8
- "creation_time": 1726854054.1090393,
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": 23.454545454545453,
17
- "creation_time": 1726854206.9696994,
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": 25.90909090909091,
26
- "creation_time": 1726854358.0524492,
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": 25.727272727272727,
35
- "creation_time": 1726854506.537163,
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": 25.727272727272727,
44
- "creation_time": 1726854506.6551447,
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": 25.727272727272727,
54
- "creation_time": 1726854506.6551447,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 599976,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-599976.onnx",
7
+ "reward": 27.363636363636363,
8
+ "creation_time": 1726856006.905159,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-599976.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 649936,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-649936.onnx",
16
+ "reward": 29.272727272727273,
17
+ "creation_time": 1726856152.4313397,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-649936.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 699960,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-699960.onnx",
25
+ "reward": 27.181818181818183,
26
+ "creation_time": 1726856299.6574404,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-699960.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 749960,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-749960.onnx",
34
+ "reward": 27.454545454545453,
35
+ "creation_time": 1726856443.9366827,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-749960.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 799984,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-799984.onnx",
43
+ "reward": 27.545454545454547,
44
+ "creation_time": 1726856592.320008,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-799984.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 849944,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-849944.onnx",
52
+ "reward": 27.545454545454547,
53
+ "creation_time": 1726856737.807067,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-849944.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 899968,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-899968.onnx",
61
+ "reward": 27.818181818181817,
62
+ "creation_time": 1726856883.0487938,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-899968.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 949968,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-949968.onnx",
70
+ "reward": 28.09090909090909,
71
+ "creation_time": 1726857027.8179266,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-949968.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 999992,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-999992.onnx",
79
+ "reward": 28.636363636363637,
80
+ "creation_time": 1726857173.6627011,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-999992.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 1000120,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000120.onnx",
88
+ "reward": 28.636363636363637,
89
+ "creation_time": 1726857173.7741547,
90
+ "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000120.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 1000120,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 28.636363636363637,
99
+ "creation_time": 1726857173.7741547,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000120.pt"
102
  ]
103
  }
104
  },