Hugging Face's logo

Nablaaa
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
Nablaaa commited on
Commit
df896b7
·
verified ·
1 Parent(s): ce0f3cd

test other yaml configs

Browse files
Files changed (29) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-1000056.onnx +3 -0
  3. SnowballTarget/SnowballTarget-1000056.pt +3 -0
  4. SnowballTarget/SnowballTarget-649960.onnx +3 -0
  5. SnowballTarget/SnowballTarget-649960.pt +3 -0
  6. SnowballTarget/SnowballTarget-699960.onnx +3 -0
  7. SnowballTarget/SnowballTarget-699960.pt +3 -0
  8. SnowballTarget/SnowballTarget-749984.onnx +3 -0
  9. SnowballTarget/SnowballTarget-749984.pt +3 -0
  10. SnowballTarget/SnowballTarget-799944.onnx +3 -0
  11. SnowballTarget/SnowballTarget-799944.pt +3 -0
  12. SnowballTarget/SnowballTarget-812288.onnx +3 -0
  13. SnowballTarget/SnowballTarget-812288.pt +3 -0
  14. SnowballTarget/SnowballTarget-849944.onnx +3 -0
  15. SnowballTarget/SnowballTarget-849944.pt +3 -0
  16. SnowballTarget/SnowballTarget-899944.onnx +3 -0
  17. SnowballTarget/SnowballTarget-899944.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.1731661923.2768e6f224c9.29032.0 +3 -0
  24. SnowballTarget/events.out.tfevents.1731662611.2768e6f224c9.31996.0 +3 -0
  25. config.json +1 -1
  26. configuration.yaml +9 -9
  27. run_logs/Player-0.log +15 -15
  28. run_logs/timers.json +181 -181
  29. run_logs/training_status.json +60 -51
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0adad92ba1a720e27752f59151df1978ca8478e888c945a7a02f60efd2a6f96f
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29ba21f96d434ad071c872af999f8e888a496444085866bc7ad43e57ce98ba36
3
  size 650646
SnowballTarget/SnowballTarget-1000056.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29ba21f96d434ad071c872af999f8e888a496444085866bc7ad43e57ce98ba36
3
+ size 650646
SnowballTarget/SnowballTarget-1000056.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9acd5ccc6e5df4086ac2101d17f6ea331cee975ce9b055b47301e6c5f2031d0e
3
+ size 3850022
SnowballTarget/SnowballTarget-649960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8225a9de0b465d64b5b8f9cee82610e3e51b1ae26167c869eec50c39a3f7059
3
+ size 650646
SnowballTarget/SnowballTarget-649960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5962da160a79a22cdb8f730381598a10212d9122bdc02c39af628b20c628de90
3
+ size 3849883
SnowballTarget/SnowballTarget-699960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a7d41b0898e7d3c8f1a78ddf840fce03cd29003ca8e0d396b8d0c01ee329717
3
+ size 650646
SnowballTarget/SnowballTarget-699960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:095a13f77c206a316f6f65da6278d6b1ade3bd0bd63c7340c340ccb9cf5cac8d
3
+ size 3849883
SnowballTarget/SnowballTarget-749984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dc6922a9b35b590197a579a086c0af0a37238e1ae4f77f65176871cfd0b9514
3
+ size 650646
SnowballTarget/SnowballTarget-749984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6960bd0dc4f5b70a221bf81928771cccf8ea07e5018f0efd9155b84e57b8d0a5
3
+ size 3849883
SnowballTarget/SnowballTarget-799944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd04f8146df05632b22c150732ba2dbe3c625b439dfb56c4c7d31cf980de361b
3
+ size 650646
SnowballTarget/SnowballTarget-799944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1bb9f448a4eef3470e92357641a1b3651d78560b0badb17358c332b3da13ff7
3
+ size 3849883
SnowballTarget/SnowballTarget-812288.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3893ee13b2d77da9858a8b4701a16d5f4bda8d5c81c2da5118b38b81171941d8
3
+ size 650646
SnowballTarget/SnowballTarget-812288.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9aac7a70acb85c1658d761935240f1044b5217775b04e724bf794d72b921b03
3
+ size 3849883
SnowballTarget/SnowballTarget-849944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c93e4a10260c18854894247c476797daf2e6961f8067534af4dacc2a3e86bf1
3
+ size 650646
SnowballTarget/SnowballTarget-849944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:990b6e35ec5a60681b3b30d0f161be1eceababd7f3683bf16df5789a89d2e976
3
+ size 3849883
SnowballTarget/SnowballTarget-899944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6830a97dd708dbb9a85c3aede849e55215171f22cfddd222764976b08b478fe
3
+ size 650646
SnowballTarget/SnowballTarget-899944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be434a7386bdeca4b74dac16a9b2ecb04de3ffa0509f0b5d4220cdd7a31b7b20
3
+ size 3849883
SnowballTarget/SnowballTarget-949968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e923894c65e0e9aa36e18788ee0378f2eed861b747d11dd28e37de32a0134aba
3
+ size 650646
SnowballTarget/SnowballTarget-949968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed6a4ec9986ff43e5f725215c56268276f3f8d2d9bdc5cd2d07ccdcda2272295
3
+ size 3849883
SnowballTarget/SnowballTarget-999992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29ba21f96d434ad071c872af999f8e888a496444085866bc7ad43e57ce98ba36
3
+ size 650646
SnowballTarget/SnowballTarget-999992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b9edf54e0c641d74d8b1aa2f1aedf0a6f890a7b463edbb97ac802783af2d95c
3
+ size 3849883
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf67a98209ffa1db3d5f19aa95911d991cbf7b6cf0959f2488a73c71247a793a
3
  size 3849058
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:324b2bb3f850f681e88a9752e511759be8e021ba8cee88a65f50b7a02fc2bbf8
3
  size 3849058
SnowballTarget/events.out.tfevents.1731661923.2768e6f224c9.29032.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd0987c659237d282f5493abe620b7eade88a0c60bb7328840e166d44e85353d
3
+ size 26620
SnowballTarget/events.out.tfevents.1731662611.2768e6f224c9.31996.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b888d9ed61348307ebe1a6a3127eea987c89fd8d63b147e9a518180816dffcc5
3
+ size 16470
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": 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": "SnowballTarget3", "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": 256, "buffer_size": 8192, "learning_rate": 3e-05, "beta": 0.02, "epsilon": 0.15, "lambd": 0.98, "num_epoch": 5, "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": 1.022, "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": "SnowballTarget3", "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
@@ -3,13 +3,13 @@ behaviors:
3
  SnowballTarget:
4
  trainer_type: ppo
5
  hyperparameters:
6
- batch_size: 128
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
@@ -26,7 +26,7 @@ behaviors:
26
  reward_signals:
27
  extrinsic:
28
  gamma: 0.99
29
- strength: 1.0
30
  network_settings:
31
  normalize: false
32
  hidden_units: 128
@@ -69,7 +69,7 @@ checkpoint_settings:
69
  run_id: SnowballTarget3
70
  initialize_from: null
71
  load_model: false
72
- resume: false
73
  force: false
74
  train_model: false
75
  inference: false
 
3
  SnowballTarget:
4
  trainer_type: ppo
5
  hyperparameters:
6
+ batch_size: 256
7
+ buffer_size: 8192
8
+ learning_rate: 3.0e-05
9
+ beta: 0.02
10
+ epsilon: 0.15
11
+ lambd: 0.98
12
+ num_epoch: 5
13
  shared_critic: false
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
 
26
  reward_signals:
27
  extrinsic:
28
  gamma: 0.99
29
+ strength: 1.022
30
  network_settings:
31
  normalize: false
32
  hidden_units: 128
 
69
  run_id: SnowballTarget3
70
  initialize_from: null
71
  load_model: false
72
+ resume: true
73
  force: false
74
  train_model: false
75
  inference: false
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 0.090 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: 0.711357 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]: 14734 frames, [16.0 KB-32.0 KB]: 249 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
@@ -166,22 +166,22 @@ Memory Statistics:
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
- Peak main deferred allocation count 40
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]: 10822 frames, [8.0 MB-16.0 MB]: 4162 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
- Peak Allocated memory 10.0 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
- Peak usage frame count: [16.0 MB-32.0 MB]: 14984 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
- Peak Allocated memory 17.6 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]: 14376 frames, [64.0 KB-128.0 KB]: 608 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]: 14984 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]: 14984 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]: 14983 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]: 14984 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]: 14984 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 0.139 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: 0.831029 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]: 5057 frames, [16.0 KB-32.0 KB]: 85 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 32
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]: 5143 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]: 5143 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
 
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]: 5072 frames, [64.0 KB-128.0 KB]: 71 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 65.6 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5143 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]: 5143 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]: 5142 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]: 5143 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]: 5143 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": 0.8140169382095337,
6
- "min": 0.8097283244132996,
7
- "max": 2.858764410018921,
8
- "count": 54
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8354.255859375,
12
- "min": 7731.2861328125,
13
- "max": 29245.16015625,
14
- "count": 54
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 539960.0,
18
- "min": 9952.0,
19
- "max": 539960.0,
20
- "count": 54
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 539960.0,
24
- "min": 9952.0,
25
- "max": 539960.0,
26
- "count": 54
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 13.846375465393066,
30
- "min": 0.37345069646835327,
31
- "max": 13.900613784790039,
32
- "count": 54
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2824.66064453125,
36
- "min": 72.44943237304688,
37
- "max": 2831.68505859375,
38
- "count": 54
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
- "count": 54
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 10945.0,
48
- "min": 8756.0,
49
  "max": 10945.0,
50
- "count": 54
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06835144121729422,
54
- "min": 0.05989573233811968,
55
- "max": 0.07579183326675311,
56
- "count": 54
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.3417572060864711,
60
- "min": 0.2395829293524787,
61
- "max": 0.3735196143962265,
62
- "count": 54
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.16497854584572363,
66
- "min": 0.1240604159059277,
67
- "max": 0.28862007277853347,
68
- "count": 54
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.8248927292286181,
72
- "min": 0.4962416636237108,
73
- "max": 1.4431003638926674,
74
- "count": 54
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 0.00013964645345120003,
78
- "min": 0.00013964645345120003,
79
- "max": 0.0002983764005411999,
80
- "count": 54
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 0.0006982322672560001,
84
- "min": 0.0005704658098448,
85
- "max": 0.001477032007656,
86
- "count": 54
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.14654880000000003,
90
- "min": 0.14654880000000003,
91
- "max": 0.1994588,
92
- "count": 54
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.7327440000000002,
96
- "min": 0.5901552000000001,
97
- "max": 0.992344,
98
- "count": 54
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
- "value": 0.00233278512,
102
- "min": 0.00233278512,
103
- "max": 0.00497299412,
104
- "count": 54
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.0116639256,
108
- "min": 0.00952874448,
109
- "max": 0.0246179656,
110
- "count": 54
111
- },
112
- "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 27.29090909090909,
114
- "min": 3.7954545454545454,
115
- "max": 27.613636363636363,
116
- "count": 54
117
- },
118
- "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1501.0,
120
- "min": 167.0,
121
- "max": 1507.0,
122
- "count": 54
123
- },
124
- "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 27.29090909090909,
126
- "min": 3.7954545454545454,
127
- "max": 27.613636363636363,
128
- "count": 54
129
- },
130
- "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1501.0,
132
- "min": 167.0,
133
- "max": 1507.0,
134
- "count": 54
135
- },
136
- "SnowballTarget.IsTraining.mean": {
137
- "value": 1.0,
138
- "min": 1.0,
139
- "max": 1.0,
140
- "count": 54
141
- },
142
- "SnowballTarget.IsTraining.sum": {
143
- "value": 1.0,
144
- "min": 1.0,
145
- "max": 1.0,
146
- "count": 54
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1731659827",
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 ./config/ppo/SnowballTarget3.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget3 --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": "2.5.0+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1731661039"
160
  },
161
- "total": 1211.559063652,
162
  "count": 1,
163
- "self": 0.5863407859997096,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.05506386800061591,
167
  "count": 1,
168
- "self": 0.05506386800061591
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 1210.9176589979998,
172
  "count": 1,
173
- "self": 1.4887348180291156,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 2.69649940599993,
177
  "count": 1,
178
- "self": 2.69649940599993
179
  },
180
  "TrainerController.advance": {
181
- "total": 1206.7314791489707,
182
- "count": 49947,
183
- "self": 0.6823276700042697,
184
  "children": {
185
  "env_step": {
186
- "total": 1206.0491514789665,
187
- "count": 49947,
188
- "self": 737.1471806450636,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 468.1690363379348,
192
- "count": 49947,
193
- "self": 3.8320324700207493,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 464.33700386791406,
197
- "count": 49947,
198
- "self": 464.33700386791406
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.7329344959680384,
204
- "count": 49946,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 1208.074729278087,
209
- "count": 49946,
210
  "is_parallel": true,
211
- "self": 640.0176559572346,
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": 0.0031243229996107402,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.000868049997734488,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0022562730018762522,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0022562730018762522
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.062033584999880986,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006183189998409944,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0003636130004451843,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0003636130004451843
244
  },
245
  "communicator.exchange": {
246
- "total": 0.059257386999888695,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.059257386999888695
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0017942659997061128,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.000363535997166764,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0014307300025393488,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0014307300025393488
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 568.0570733208524,
271
- "count": 49945,
272
  "is_parallel": true,
273
- "self": 26.529494731926206,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 13.714483265988747,
277
- "count": 49945,
278
  "is_parallel": true,
279
- "self": 13.714483265988747
280
  },
281
  "communicator.exchange": {
282
- "total": 442.40394648782694,
283
- "count": 49945,
284
  "is_parallel": true,
285
- "self": 442.40394648782694
286
  },
287
  "steps_from_proto": {
288
- "total": 85.4091488351105,
289
- "count": 49945,
290
  "is_parallel": true,
291
- "self": 15.943040161207136,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 69.46610867390336,
295
- "count": 499450,
296
  "is_parallel": true,
297
- "self": 69.46610867390336
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 4.186000023764791e-05,
313
  "count": 1,
314
- "self": 4.186000023764791e-05,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 1191.8636701597643,
324
- "count": 1856394,
325
  "is_parallel": true,
326
- "self": 40.378412104681956,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 650.2180409470811,
330
- "count": 1856394,
331
  "is_parallel": true,
332
- "self": 648.546378143079,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 1.6716628040021533,
336
- "count": 10,
337
  "is_parallel": true,
338
- "self": 1.6716628040021533
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 501.2672171080012,
344
- "count": 249,
345
  "is_parallel": true,
346
- "self": 154.72115953702723,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 346.54605757097397,
350
- "count": 12696,
351
  "is_parallel": true,
352
- "self": 346.54605757097397
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.0009037649997480912,
364
  "count": 1,
365
- "self": 2.32619995585992e-05,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.000880503000189492,
369
  "count": 1,
370
- "self": 0.000880503000189492
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.8138673901557922,
6
+ "min": 0.8005954027175903,
7
+ "max": 0.8235114812850952,
8
+ "count": 19
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 8361.673828125,
12
+ "min": 6552.91015625,
13
+ "max": 8427.986328125,
14
+ "count": 19
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 999992.0,
18
+ "min": 819976.0,
19
+ "max": 999992.0,
20
+ "count": 19
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 999992.0,
24
+ "min": 819976.0,
25
+ "max": 999992.0,
26
+ "count": 19
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 14.193025588989258,
30
+ "min": 14.180804252624512,
31
+ "max": 14.40643310546875,
32
+ "count": 19
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2909.5703125,
36
+ "min": 2146.55859375,
37
+ "max": 2930.494873046875,
38
+ "count": 19
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 19
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 10945.0,
48
+ "min": 6567.0,
49
  "max": 10945.0,
50
+ "count": 19
51
+ },
52
+ "SnowballTarget.Environment.CumulativeReward.mean": {
53
+ "value": 27.87272727272727,
54
+ "min": 26.745454545454546,
55
+ "max": 27.87272727272727,
56
+ "count": 19
57
+ },
58
+ "SnowballTarget.Environment.CumulativeReward.sum": {
59
+ "value": 1533.0,
60
+ "min": 894.0,
61
+ "max": 1533.0,
62
+ "count": 19
63
+ },
64
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
+ "value": 28.485926123098892,
66
+ "min": 27.33385359807448,
67
+ "max": 28.485926123098892,
68
+ "count": 19
69
+ },
70
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
+ "value": 1566.7259367704391,
72
+ "min": 913.6679664850235,
73
+ "max": 1566.7259367704391,
74
+ "count": 19
75
+ },
76
+ "SnowballTarget.IsTraining.mean": {
77
+ "value": 1.0,
78
+ "min": 1.0,
79
+ "max": 1.0,
80
+ "count": 19
81
+ },
82
+ "SnowballTarget.IsTraining.sum": {
83
+ "value": 1.0,
84
+ "min": 1.0,
85
+ "max": 1.0,
86
+ "count": 19
87
  },
88
  "SnowballTarget.Losses.PolicyLoss.mean": {
89
+ "value": 0.04594731732751384,
90
+ "min": 0.044273665204544906,
91
+ "max": 0.053823788311671124,
92
+ "count": 18
93
  },
94
  "SnowballTarget.Losses.PolicyLoss.sum": {
95
+ "value": 0.04594731732751384,
96
+ "min": 0.044273665204544906,
97
+ "max": 0.09959654017517702,
98
+ "count": 18
99
  },
100
  "SnowballTarget.Losses.ValueLoss.mean": {
101
+ "value": 0.24564173311898202,
102
+ "min": 0.23254177736885406,
103
+ "max": 0.3044277711002797,
104
+ "count": 18
105
  },
106
  "SnowballTarget.Losses.ValueLoss.sum": {
107
+ "value": 0.24564173311898202,
108
+ "min": 0.23254177736885406,
109
+ "max": 0.6088555422005594,
110
+ "count": 18
111
  },
112
  "SnowballTarget.Policy.LearningRate.mean": {
113
+ "value": 2.2209925999999891e-07,
114
+ "min": 2.2209925999999891e-07,
115
+ "max": 5.254402485599999e-06,
116
+ "count": 18
117
  },
118
  "SnowballTarget.Policy.LearningRate.sum": {
119
+ "value": 2.2209925999999891e-07,
120
+ "min": 2.2209925999999891e-07,
121
+ "max": 1.0508804971199998e-05,
122
+ "count": 18
123
  },
124
  "SnowballTarget.Policy.Epsilon.mean": {
125
+ "value": 0.10036999999999997,
126
+ "min": 0.10036999999999997,
127
+ "max": 0.10875720000000003,
128
+ "count": 18
129
  },
130
  "SnowballTarget.Policy.Epsilon.sum": {
131
+ "value": 0.10036999999999997,
132
+ "min": 0.10036999999999997,
133
+ "max": 0.21751440000000005,
134
+ "count": 18
135
  },
136
  "SnowballTarget.Policy.Beta.mean": {
137
+ "value": 0.00015792599999999923,
138
+ "min": 0.00015792599999999923,
139
+ "max": 0.0035111285599999987,
140
+ "count": 18
141
  },
142
  "SnowballTarget.Policy.Beta.sum": {
143
+ "value": 0.00015792599999999923,
144
+ "min": 0.00015792599999999923,
145
+ "max": 0.007022257119999997,
146
+ "count": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1731662610",
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 ./config/ppo/SnowballTarget3.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget3 --no-graphics --resume",
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": "2.5.0+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1731663067"
160
  },
161
+ "total": 456.3888227039997,
162
  "count": 1,
163
+ "self": 0.7171841759991366,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.0854702910000924,
167
  "count": 1,
168
+ "self": 0.0854702910000924
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 455.5861682370005,
172
  "count": 1,
173
+ "self": 0.4975255839553938,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.162518302000535,
177
  "count": 1,
178
+ "self": 2.162518302000535
179
  },
180
  "TrainerController.advance": {
181
+ "total": 452.8023012030444,
182
+ "count": 17141,
183
+ "self": 0.24580430904461537,
184
  "children": {
185
  "env_step": {
186
+ "total": 452.5564968939998,
187
+ "count": 17141,
188
+ "self": 307.00740788777057,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 145.2975660201364,
192
+ "count": 17141,
193
+ "self": 1.3256831071548731,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 143.97188291298153,
197
+ "count": 17141,
198
+ "self": 143.97188291298153
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.251522986092823,
204
+ "count": 17141,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 454.5149997389226,
209
+ "count": 17141,
210
  "is_parallel": true,
211
+ "self": 258.6602134329305,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0021595989992420073,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0006339549991025706,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0015256440001394367,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0015256440001394367
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.03778493000027083,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006341050011542393,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0003842309997708071,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0003842309997708071
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03484560299966688,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03484560299966688
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0019209909996789065,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0003637410009105224,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.001557249998768384,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.001557249998768384
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 195.8547863059921,
271
+ "count": 17140,
272
  "is_parallel": true,
273
+ "self": 9.158067409049181,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 4.742068792984355,
277
+ "count": 17140,
278
  "is_parallel": true,
279
+ "self": 4.742068792984355
280
  },
281
  "communicator.exchange": {
282
+ "total": 152.02819800496036,
283
+ "count": 17140,
284
  "is_parallel": true,
285
+ "self": 152.02819800496036
286
  },
287
  "steps_from_proto": {
288
+ "total": 29.926452098998197,
289
+ "count": 17140,
290
  "is_parallel": true,
291
+ "self": 5.547426242139409,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 24.37902585685879,
295
+ "count": 171400,
296
  "is_parallel": true,
297
+ "self": 24.37902585685879
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 8.567599979869556e-05,
313
  "count": 1,
314
+ "self": 8.567599979869556e-05,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 445.006484520859,
324
+ "count": 905101,
325
  "is_parallel": true,
326
+ "self": 18.988185667437392,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 295.59006721842434,
330
+ "count": 905101,
331
  "is_parallel": true,
332
+ "self": 294.65669273542426,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 0.9333744830000796,
336
+ "count": 4,
337
  "is_parallel": true,
338
+ "self": 0.9333744830000796
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 130.42823163499725,
344
+ "count": 21,
345
  "is_parallel": true,
346
+ "self": 68.5583731740171,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 61.86985846098014,
350
+ "count": 3480,
351
  "is_parallel": true,
352
+ "self": 61.86985846098014
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.12373747200035723,
364
  "count": 1,
365
+ "self": 0.0019653560002552695,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.12177211600010196,
369
  "count": 1,
370
+ "self": 0.12177211600010196
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -2,96 +2,105 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 15.909090909090908,
8
- "creation_time": 1731659940.6960835,
9
  "auxillary_file_paths": [
10
- "results/SnowballTarget3/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
12
  },
13
  {
14
- "steps": 99960,
15
- "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 22.727272727272727,
17
- "creation_time": 1731660050.0319004,
18
  "auxillary_file_paths": [
19
- "results/SnowballTarget3/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
21
  },
22
  {
23
- "steps": 149984,
24
- "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 25.454545454545453,
26
- "creation_time": 1731660160.4481957,
27
  "auxillary_file_paths": [
28
- "results/SnowballTarget3/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
30
  },
31
  {
32
- "steps": 199984,
33
- "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 25.727272727272727,
35
- "creation_time": 1731660272.0411003,
36
  "auxillary_file_paths": [
37
- "results/SnowballTarget3/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
- "steps": 249944,
42
- "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-249944.onnx",
43
- "reward": 25.545454545454547,
44
- "creation_time": 1731660383.4888308,
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget3/SnowballTarget/SnowballTarget-249944.pt"
47
  ]
48
  },
49
  {
50
- "steps": 299968,
51
- "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-299968.onnx",
52
- "reward": 26.727272727272727,
53
- "creation_time": 1731660493.5284529,
54
  "auxillary_file_paths": [
55
- "results/SnowballTarget3/SnowballTarget/SnowballTarget-299968.pt"
56
  ]
57
  },
58
  {
59
- "steps": 349992,
60
- "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-349992.onnx",
61
- "reward": 27.454545454545453,
62
- "creation_time": 1731660605.708579,
63
  "auxillary_file_paths": [
64
- "results/SnowballTarget3/SnowballTarget/SnowballTarget-349992.pt"
65
  ]
66
  },
67
  {
68
- "steps": 399992,
69
- "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-399992.onnx",
70
- "reward": 26.545454545454547,
71
- "creation_time": 1731660714.2973912,
72
  "auxillary_file_paths": [
73
- "results/SnowballTarget3/SnowballTarget/SnowballTarget-399992.pt"
74
  ]
75
  },
76
  {
77
- "steps": 449952,
78
- "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-449952.onnx",
79
- "reward": 27.09090909090909,
80
- "creation_time": 1731660824.1089575,
81
  "auxillary_file_paths": [
82
- "results/SnowballTarget3/SnowballTarget/SnowballTarget-449952.pt"
83
  ]
84
  },
85
  {
86
- "steps": 499976,
87
- "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-499976.onnx",
88
- "reward": 28.0,
89
- "creation_time": 1731660932.8653169,
90
  "auxillary_file_paths": [
91
- "results/SnowballTarget3/SnowballTarget/SnowballTarget-499976.pt"
92
  ]
93
  }
94
- ]
 
 
 
 
 
 
 
 
 
95
  },
96
  "metadata": {
97
  "stats_format_version": "0.3.0",
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 649960,
6
+ "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-649960.onnx",
7
+ "reward": 27.09090909090909,
8
+ "creation_time": 1731662248.1402943,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget3/SnowballTarget/SnowballTarget-649960.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 699960,
15
+ "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-699960.onnx",
16
+ "reward": 26.636363636363637,
17
+ "creation_time": 1731662355.1198215,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget3/SnowballTarget/SnowballTarget-699960.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 749984,
24
+ "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-749984.onnx",
25
+ "reward": 26.772727272727273,
26
+ "creation_time": 1731662463.3866196,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget3/SnowballTarget/SnowballTarget-749984.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 799944,
33
+ "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-799944.onnx",
34
+ "reward": 27.272727272727273,
35
+ "creation_time": 1731662572.267128,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget3/SnowballTarget/SnowballTarget-799944.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 812288,
42
+ "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-812288.onnx",
43
+ "reward": null,
44
+ "creation_time": 1731662598.4305637,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget3/SnowballTarget/SnowballTarget-812288.pt"
47
  ]
48
  },
49
  {
50
+ "steps": 849944,
51
+ "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-849944.onnx",
52
+ "reward": 27.318181818181817,
53
+ "creation_time": 1731662701.2417543,
54
  "auxillary_file_paths": [
55
+ "results/SnowballTarget3/SnowballTarget/SnowballTarget-849944.pt"
56
  ]
57
  },
58
  {
59
+ "steps": 899944,
60
+ "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-899944.onnx",
61
+ "reward": 28.09090909090909,
62
+ "creation_time": 1731662824.8218458,
63
  "auxillary_file_paths": [
64
+ "results/SnowballTarget3/SnowballTarget/SnowballTarget-899944.pt"
65
  ]
66
  },
67
  {
68
+ "steps": 949968,
69
+ "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-949968.onnx",
70
+ "reward": 26.818181818181817,
71
+ "creation_time": 1731662942.8474967,
72
  "auxillary_file_paths": [
73
+ "results/SnowballTarget3/SnowballTarget/SnowballTarget-949968.pt"
74
  ]
75
  },
76
  {
77
+ "steps": 999992,
78
+ "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-999992.onnx",
79
+ "reward": 27.727272727272727,
80
+ "creation_time": 1731663066.163944,
81
  "auxillary_file_paths": [
82
+ "results/SnowballTarget3/SnowballTarget/SnowballTarget-999992.pt"
83
  ]
84
  },
85
  {
86
+ "steps": 1000056,
87
+ "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-1000056.onnx",
88
+ "reward": 27.727272727272727,
89
+ "creation_time": 1731663066.3091567,
90
  "auxillary_file_paths": [
91
+ "results/SnowballTarget3/SnowballTarget/SnowballTarget-1000056.pt"
92
  ]
93
  }
94
+ ],
95
+ "final_checkpoint": {
96
+ "steps": 1000056,
97
+ "file_path": "results/SnowballTarget3/SnowballTarget.onnx",
98
+ "reward": 27.727272727272727,
99
+ "creation_time": 1731663066.3091567,
100
+ "auxillary_file_paths": [
101
+ "results/SnowballTarget3/SnowballTarget/SnowballTarget-1000056.pt"
102
+ ]
103
+ }
104
  },
105
  "metadata": {
106
  "stats_format_version": "0.3.0",