Hugging Face's logo

ExusBurn
/
SnowBallTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
ExusBurn commited on
Commit
def0b2d
•
1 Parent(s): 6893471

First Push

Browse files
Files changed (28) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-219992.onnx +3 -0
  3. SnowballTarget/SnowballTarget-219992.pt +3 -0
  4. SnowballTarget/SnowballTarget-229952.onnx +3 -0
  5. SnowballTarget/SnowballTarget-229952.pt +3 -0
  6. SnowballTarget/SnowballTarget-239992.onnx +3 -0
  7. SnowballTarget/SnowballTarget-239992.pt +3 -0
  8. SnowballTarget/SnowballTarget-249944.onnx +3 -0
  9. SnowballTarget/SnowballTarget-249944.pt +3 -0
  10. SnowballTarget/SnowballTarget-259984.onnx +3 -0
  11. SnowballTarget/SnowballTarget-259984.pt +3 -0
  12. SnowballTarget/SnowballTarget-269936.onnx +3 -0
  13. SnowballTarget/SnowballTarget-269936.pt +3 -0
  14. SnowballTarget/SnowballTarget-279976.onnx +3 -0
  15. SnowballTarget/SnowballTarget-279976.pt +3 -0
  16. SnowballTarget/SnowballTarget-289992.onnx +3 -0
  17. SnowballTarget/SnowballTarget-289992.pt +3 -0
  18. SnowballTarget/SnowballTarget-299968.onnx +3 -0
  19. SnowballTarget/SnowballTarget-299968.pt +3 -0
  20. SnowballTarget/SnowballTarget-300608.onnx +3 -0
  21. SnowballTarget/SnowballTarget-300608.pt +3 -0
  22. SnowballTarget/checkpoint.pt +1 -1
  23. SnowballTarget/events.out.tfevents.1709622541.6d83d588a2e4.2030.0 +3 -0
  24. config.json +1 -1
  25. configuration.yaml +4 -4
  26. run_logs/Player-0.log +15 -15
  27. run_logs/timers.json +161 -161
  28. run_logs/training_status.json +54 -54
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d1f1cbb30c973680e22a931f03f4bcf38b642fbd0b7421f86f9bd8345c53db5
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c23b69809fba8f215b2340744654eea85e81764c20453eba15e7c2ee5e600f77
3
  size 650646
SnowballTarget/SnowballTarget-219992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:975008f144c64db8f74f46e18965e34b694af6f682f71fb1b94e699ae966f4ac
3
+ size 650646
SnowballTarget/SnowballTarget-219992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1791d33a81ef5f815b83eb59cf118fef4126059950ed24dd9cb118ee90c50312
3
+ size 3850075
SnowballTarget/SnowballTarget-229952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aea9e5d9b79468d3a0d6a1aff70b5e0a0d51ee72196ebeb02d1b22301b8c2dc
3
+ size 650646
SnowballTarget/SnowballTarget-229952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eee2c8913fd1d36f5fabbfa8abb6316059bc87883992e78faf70411b3dcd531c
3
+ size 3850075
SnowballTarget/SnowballTarget-239992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a04d7aabe0205143a742f70dddb31fafcdb3d51fdb661984e04b381b75dd8735
3
+ size 650646
SnowballTarget/SnowballTarget-239992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4586df19a45f1389066b68191baba0526b8be7b3379459f944fc944ee8323fac
3
+ size 3850075
SnowballTarget/SnowballTarget-249944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3611b8d0312e87ccdb44ee87b632097b9cc30b8a07e3ab6dfed85071953a318
3
+ size 650646
SnowballTarget/SnowballTarget-249944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a81bc525d532f15f92ca00679696c4636d1eb976720249774646e672064dfc7
3
+ size 3850075
SnowballTarget/SnowballTarget-259984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00bb1e047f8daa867c11fe879c9c5577cb1b6c361b272b427e25f1ae0ef3572c
3
+ size 650646
SnowballTarget/SnowballTarget-259984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b3123a6dc9a48f1f59e7705bee544a91f40f26e9ba2ea74256496d6cf6fe76d
3
+ size 3850075
SnowballTarget/SnowballTarget-269936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18ff3717b699565e7095810a2a963fe903ed045cf37430513bc469fc74a398ab
3
+ size 650646
SnowballTarget/SnowballTarget-269936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70d90cbf374d85bc543fe9fe9d0020edb93c27aa106f047948221742e05fa352
3
+ size 3850075
SnowballTarget/SnowballTarget-279976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c665d01ef9c3257b68bcf51540910610c3689beac92b2468109de8f880b7278a
3
+ size 650646
SnowballTarget/SnowballTarget-279976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44022a073ed6653e6991db1bc68efe60327ae96e03406cefc50c0f65ac48c5de
3
+ size 3850075
SnowballTarget/SnowballTarget-289992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ee354fecc41eb9f311ce0a730709fdac83881f365cd16eca3390523f79b327c
3
+ size 650646
SnowballTarget/SnowballTarget-289992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52e3c32e59ed848296e355a54e9b94671ef3843ec1f31de25ec90544b374f679
3
+ size 3850075
SnowballTarget/SnowballTarget-299968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c23b69809fba8f215b2340744654eea85e81764c20453eba15e7c2ee5e600f77
3
+ size 650646
SnowballTarget/SnowballTarget-299968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:474b5bbcfe363b3cd719dd07d3cbd860aa98f6127fd357935a0b46203c568b5a
3
+ size 3850075
SnowballTarget/SnowballTarget-300608.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c23b69809fba8f215b2340744654eea85e81764c20453eba15e7c2ee5e600f77
3
+ size 650646
SnowballTarget/SnowballTarget-300608.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc85f9091623b7b6512245675147d0b295e59aee8eddec17fa0455150962ac46
3
+ size 3850075
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ead65aae9b416a11279314ff2fec615690baadc3f660c7d3985a42bff4fd27f5
3
  size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e736298c9fa22544c0a843668ff82b1441592944f56b313a4591bd5a51a341eb
3
  size 3849250
SnowballTarget/events.out.tfevents.1709622541.6d83d588a2e4.2030.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf5f2e2a81d0b85bfcf3d68268253a6794946b79b31b551854004447883a0e73
3
+ size 41762
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": 1000, "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": 0.95, "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": 10000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0002, "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": 10000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 300000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -5,7 +5,7 @@ behaviors:
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
@@ -14,7 +14,7 @@ behaviors:
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
16
  epsilon_schedule: linear
17
- checkpoint_interval: 1000
18
  network_settings:
19
  normalize: false
20
  hidden_units: 256
@@ -25,7 +25,7 @@ behaviors:
25
  deterministic: false
26
  reward_signals:
27
  extrinsic:
28
- gamma: 0.95
29
  strength: 1.0
30
  network_settings:
31
  normalize: false
@@ -38,7 +38,7 @@ behaviors:
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
- max_steps: 10000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
 
5
  hyperparameters:
6
  batch_size: 128
7
  buffer_size: 2048
8
+ learning_rate: 0.0002
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
 
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
16
  epsilon_schedule: linear
17
+ checkpoint_interval: 10000
18
  network_settings:
19
  normalize: false
20
  hidden_units: 256
 
25
  deterministic: false
26
  reward_signals:
27
  extrinsic:
28
+ gamma: 0.99
29
  strength: 1.0
30
  network_settings:
31
  normalize: false
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 300000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
run_logs/Player-0.log CHANGED
@@ -34,7 +34,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
- - Completed reload, in 0.102 seconds
38
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -45,7 +45,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
45
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
46
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
47
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
48
- UnloadTime: 0.740509 ms
49
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
50
  requesting resize 84 x 84
51
  Setting up 1 worker threads for Enlighten.
@@ -53,7 +53,7 @@ Memory Statistics:
53
  [ALLOC_TEMP_TLS] TLS Allocator
54
  StackAllocators :
55
  [ALLOC_TEMP_MAIN]
56
- Peak usage frame count: [8.0 KB-16.0 KB]: 276 frames, [16.0 KB-32.0 KB]: 4 frames, [2.0 MB-4.0 MB]: 1 frames
57
  Initial Block Size 4.0 MB
58
  Current Block Size 4.0 MB
59
  Peak Allocated Bytes 2.0 MB
@@ -169,22 +169,22 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 36
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
- Peak usage frame count: [4.0 MB-8.0 MB]: 281 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 5.5 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 281 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.7 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
@@ -213,13 +213,13 @@ Memory Statistics:
213
  Used Block count 1
214
  Peak Allocated bytes 1.0 MB
215
  [ALLOC_GFX_MAIN]
216
- Peak usage frame count: [32.0 KB-64.0 KB]: 249 frames, [64.0 KB-128.0 KB]: 32 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 65.6 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 281 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
@@ -231,13 +231,13 @@ Memory Statistics:
231
  Used Block count 1
232
  Peak Allocated bytes 1.0 MB
233
  [ALLOC_CACHEOBJECTS_MAIN]
234
- Peak usage frame count: [0.5 MB-1.0 MB]: 281 frames
235
  Requested Block Size 4.0 MB
236
  Peak Block count 1
237
  Peak Allocated memory 0.6 MB
238
  Peak Large allocation bytes 0 B
239
  [ALLOC_CACHEOBJECTS_THREAD]
240
- Peak usage frame count: [0.5 MB-1.0 MB]: 280 frames, [2.0 MB-4.0 MB]: 1 frames
241
  Requested Block Size 4.0 MB
242
  Peak Block count 1
243
  Peak Allocated memory 2.2 MB
@@ -249,13 +249,13 @@ Memory Statistics:
249
  Used Block count 1
250
  Peak Allocated bytes 1.0 MB
251
  [ALLOC_TYPETREE_MAIN]
252
- Peak usage frame count: [0-1.0 KB]: 281 frames
253
  Requested Block Size 2.0 MB
254
  Peak Block count 1
255
  Peak Allocated memory 1.0 KB
256
  Peak Large allocation bytes 0 B
257
  [ALLOC_TYPETREE_THREAD]
258
- Peak usage frame count: [1.0 KB-2.0 KB]: 281 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  Peak Allocated memory 1.7 KB
 
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
+ - Completed reload, in 0.088 seconds
38
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
45
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
46
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
47
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
48
+ UnloadTime: 0.673522 ms
49
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
50
  requesting resize 84 x 84
51
  Setting up 1 worker threads for Enlighten.
 
53
  [ALLOC_TEMP_TLS] TLS Allocator
54
  StackAllocators :
55
  [ALLOC_TEMP_MAIN]
56
+ Peak usage frame count: [8.0 KB-16.0 KB]: 8063 frames, [16.0 KB-32.0 KB]: 136 frames, [2.0 MB-4.0 MB]: 1 frames
57
  Initial Block Size 4.0 MB
58
  Current Block Size 4.0 MB
59
  Peak Allocated Bytes 2.0 MB
 
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
+ Peak main deferred allocation count 44
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
+ Peak usage frame count: [4.0 MB-8.0 MB]: 8200 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
+ Peak Allocated memory 7.4 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
+ Peak usage frame count: [16.0 MB-32.0 MB]: 8200 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
+ Peak Allocated memory 17.8 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
 
213
  Used Block count 1
214
  Peak Allocated bytes 1.0 MB
215
  [ALLOC_GFX_MAIN]
216
+ Peak usage frame count: [32.0 KB-64.0 KB]: 7287 frames, [64.0 KB-128.0 KB]: 913 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
+ Peak Allocated memory 66.4 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
+ Peak usage frame count: [32.0 KB-64.0 KB]: 8200 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
 
231
  Used Block count 1
232
  Peak Allocated bytes 1.0 MB
233
  [ALLOC_CACHEOBJECTS_MAIN]
234
+ Peak usage frame count: [0.5 MB-1.0 MB]: 8200 frames
235
  Requested Block Size 4.0 MB
236
  Peak Block count 1
237
  Peak Allocated memory 0.6 MB
238
  Peak Large allocation bytes 0 B
239
  [ALLOC_CACHEOBJECTS_THREAD]
240
+ Peak usage frame count: [0.5 MB-1.0 MB]: 8199 frames, [2.0 MB-4.0 MB]: 1 frames
241
  Requested Block Size 4.0 MB
242
  Peak Block count 1
243
  Peak Allocated memory 2.2 MB
 
249
  Used Block count 1
250
  Peak Allocated bytes 1.0 MB
251
  [ALLOC_TYPETREE_MAIN]
252
+ Peak usage frame count: [0-1.0 KB]: 8200 frames
253
  Requested Block Size 2.0 MB
254
  Peak Block count 1
255
  Peak Allocated memory 1.0 KB
256
  Peak Large allocation bytes 0 B
257
  [ALLOC_TYPETREE_THREAD]
258
+ Peak usage frame count: [1.0 KB-2.0 KB]: 8200 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -2,153 +2,153 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 2.8677308559417725,
6
- "min": 2.8677308559417725,
7
- "max": 2.8677308559417725,
8
- "count": 1
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 29368.431640625,
12
- "min": 29368.431640625,
13
- "max": 29368.431640625,
14
- "count": 1
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 9952.0,
18
  "min": 9952.0,
19
- "max": 9952.0,
20
- "count": 1
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 9952.0,
24
  "min": 9952.0,
25
- "max": 9952.0,
26
- "count": 1
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 0.2532596290111542,
30
- "min": 0.2532596290111542,
31
- "max": 0.2532596290111542,
32
- "count": 1
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 49.13236618041992,
36
- "min": 49.13236618041992,
37
- "max": 49.13236618041992,
38
- "count": 1
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
- "count": 1
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
- "value": 8756.0,
48
  "min": 8756.0,
49
- "max": 8756.0,
50
- "count": 1
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.07315820297249137,
54
- "min": 0.07315820297249137,
55
- "max": 0.07315820297249137,
56
- "count": 1
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.2926328118899655,
60
- "min": 0.2926328118899655,
61
- "max": 0.2926328118899655,
62
- "count": 1
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.07041780591780301,
66
- "min": 0.07041780591780301,
67
- "max": 0.07041780591780301,
68
- "count": 1
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.28167122367121206,
72
- "min": 0.28167122367121206,
73
- "max": 0.28167122367121206,
74
- "count": 1
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 0.00013764005412,
78
- "min": 0.00013764005412,
79
- "max": 0.00013764005412,
80
- "count": 1
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 0.00055056021648,
84
- "min": 0.00055056021648,
85
- "max": 0.00055056021648,
86
- "count": 1
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.14588,
90
- "min": 0.14588,
91
- "max": 0.14588,
92
- "count": 1
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.58352,
96
- "min": 0.58352,
97
- "max": 0.58352,
98
- "count": 1
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
- "value": 0.002299412,
102
- "min": 0.002299412,
103
- "max": 0.002299412,
104
- "count": 1
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.009197648,
108
- "min": 0.009197648,
109
- "max": 0.009197648,
110
- "count": 1
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 3.8636363636363638,
114
- "min": 3.8636363636363638,
115
- "max": 3.8636363636363638,
116
- "count": 1
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 170.0,
120
- "min": 170.0,
121
- "max": 170.0,
122
- "count": 1
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 3.8636363636363638,
126
- "min": 3.8636363636363638,
127
- "max": 3.8636363636363638,
128
- "count": 1
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 170.0,
132
- "min": 170.0,
133
- "max": 170.0,
134
- "count": 1
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 1
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 1
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1709617195",
152
  "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
153
  "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.1.0.dev0",
@@ -156,59 +156,59 @@
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.2.1+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1709617223"
160
  },
161
- "total": 27.57146447699995,
162
  "count": 1,
163
- "self": 0.4331529969999792,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.048158802999978434,
167
  "count": 1,
168
- "self": 0.048158802999978434
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 27.090152676999992,
172
  "count": 1,
173
- "self": 0.04442979099951572,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.3047585260000005,
177
  "count": 1,
178
- "self": 3.3047585260000005
179
  },
180
  "TrainerController.advance": {
181
- "total": 23.648226612000485,
182
- "count": 934,
183
- "self": 0.014074654000182818,
184
  "children": {
185
  "env_step": {
186
- "total": 23.634151958000302,
187
- "count": 934,
188
- "self": 14.44931677600232,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 9.170867414998838,
192
- "count": 934,
193
- "self": 0.07365524600209028,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 9.097212168996748,
197
- "count": 934,
198
- "self": 9.097212168996748
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.01396776699914426,
204
- "count": 934,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 26.972609751999016,
209
- "count": 934,
210
  "is_parallel": true,
211
- "self": 15.702302971999416,
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": 0.005722280999975737,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.004081185999893933,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0016410950000818048,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0016410950000818048
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03551497199998721,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0007140140000956308,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00040842399994289735,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00040842399994289735
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03256494400000065,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03256494400000065
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0018275899999480316,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0003439189998744041,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0014836710000736275,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0014836710000736275
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 11.2703067799996,
271
- "count": 933,
272
  "is_parallel": true,
273
- "self": 0.5517644839968625,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 0.2776751849995662,
277
- "count": 933,
278
  "is_parallel": true,
279
- "self": 0.2776751849995662
280
  },
281
  "communicator.exchange": {
282
- "total": 8.71212897800251,
283
- "count": 933,
284
  "is_parallel": true,
285
- "self": 8.71212897800251
286
  },
287
  "steps_from_proto": {
288
- "total": 1.728738133000661,
289
- "count": 933,
290
  "is_parallel": true,
291
- "self": 0.320845887000587,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 1.407892246000074,
295
- "count": 9330,
296
  "is_parallel": true,
297
- "self": 1.407892246000074
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00024584599998433987,
313
  "count": 1,
314
- "self": 0.00024584599998433987,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 23.369707738001694,
324
- "count": 37710,
325
  "is_parallel": true,
326
- "self": 0.7340282049927964,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 14.37391572300885,
330
- "count": 37710,
331
  "is_parallel": true,
332
- "self": 12.675702439008887,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 1.6982132839999622,
336
- "count": 10,
337
  "is_parallel": true,
338
- "self": 1.6982132839999622
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 8.261763810000048,
344
- "count": 4,
345
  "is_parallel": true,
346
- "self": 2.438839995999615,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 5.822923814000433,
350
- "count": 201,
351
  "is_parallel": true,
352
- "self": 5.822923814000433
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.09249190200000612,
364
  "count": 1,
365
- "self": 0.0009783350000134305,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.09151356699999269,
369
  "count": 1,
370
- "self": 0.09151356699999269
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.8302021026611328,
6
+ "min": 0.8302021026611328,
7
+ "max": 2.8782455921173096,
8
+ "count": 30
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 8520.3642578125,
12
+ "min": 8240.2080078125,
13
+ "max": 29507.7734375,
14
+ "count": 30
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 299968.0,
18
  "min": 9952.0,
19
+ "max": 299968.0,
20
+ "count": 30
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 299968.0,
24
  "min": 9952.0,
25
+ "max": 299968.0,
26
+ "count": 30
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.184460639953613,
30
+ "min": 0.35725894570350647,
31
+ "max": 13.18896198272705,
32
+ "count": 30
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2689.6298828125,
36
+ "min": 69.30823516845703,
37
+ "max": 2696.407470703125,
38
+ "count": 30
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 30
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 10945.0,
48
  "min": 8756.0,
49
+ "max": 10945.0,
50
+ "count": 30
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.07016346581846901,
54
+ "min": 0.06261018357261883,
55
+ "max": 0.07606870673172286,
56
+ "count": 30
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.35081732909234503,
60
+ "min": 0.2504407342904753,
61
+ "max": 0.3803435336586143,
62
+ "count": 30
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.19849070842359579,
66
+ "min": 0.13108704224406909,
67
+ "max": 0.2855049737674349,
68
+ "count": 30
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.992453542117979,
72
+ "min": 0.5243481689762763,
73
+ "max": 1.3212304509737913,
74
+ "count": 30
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 3.5254315706666646e-06,
78
+ "min": 3.5254315706666646e-06,
79
+ "max": 0.00019639200180400005,
80
+ "count": 30
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 1.7627157853333323e-05,
84
+ "min": 1.7627157853333323e-05,
85
+ "max": 0.00094896002552,
86
+ "count": 30
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10176266666666667,
90
+ "min": 0.10176266666666667,
91
+ "max": 0.198196,
92
+ "count": 30
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.5088133333333333,
96
+ "min": 0.42025066666666666,
97
+ "max": 0.97448,
98
+ "count": 30
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 9.795706666666662e-05,
102
+ "min": 9.795706666666662e-05,
103
+ "max": 0.0049099804000000006,
104
+ "count": 30
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.0004897853333333331,
108
+ "min": 0.0004897853333333331,
109
+ "max": 0.023726551999999998,
110
+ "count": 30
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 25.6,
114
+ "min": 3.2954545454545454,
115
+ "max": 26.054545454545455,
116
+ "count": 30
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1408.0,
120
+ "min": 145.0,
121
+ "max": 1433.0,
122
+ "count": 30
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.6,
126
+ "min": 3.2954545454545454,
127
+ "max": 26.054545454545455,
128
+ "count": 30
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1408.0,
132
+ "min": 145.0,
133
+ "max": 1433.0,
134
+ "count": 30
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 30
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 30
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1709622540",
152
  "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
153
  "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.1.0.dev0",
 
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.2.1+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1709623177"
160
  },
161
+ "total": 636.9537627970001,
162
  "count": 1,
163
+ "self": 0.43438160400012293,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.04906087699998807,
167
  "count": 1,
168
+ "self": 0.04906087699998807
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 636.470320316,
172
  "count": 1,
173
+ "self": 0.8182911329979561,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.3064533680000068,
177
  "count": 1,
178
+ "self": 3.3064533680000068
179
  },
180
  "TrainerController.advance": {
181
+ "total": 632.2536601190021,
182
+ "count": 27332,
183
+ "self": 0.3724649230008481,
184
  "children": {
185
  "env_step": {
186
+ "total": 631.8811951960013,
187
+ "count": 27332,
188
+ "self": 405.44968545097475,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 226.02945619701836,
192
+ "count": 27332,
193
+ "self": 2.0867117090122633,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 223.9427444880061,
197
+ "count": 27332,
198
+ "self": 223.9427444880061
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.40205354800815485,
204
+ "count": 27332,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 634.910365822011,
209
+ "count": 27332,
210
  "is_parallel": true,
211
+ "self": 317.3698741610138,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.005236830000001191,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0036111739998432313,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.00162565600015796,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.00162565600015796
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.03809372499995334,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0007135779999316583,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00040767100000493883,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00040767100000493883
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03487212499999259,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03487212499999259
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0021003510000241477,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00046960100002024774,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0016307500000039,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0016307500000039
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 317.54049166099725,
271
+ "count": 27331,
272
  "is_parallel": true,
273
+ "self": 15.619649653011379,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 7.713544319001812,
277
+ "count": 27331,
278
  "is_parallel": true,
279
+ "self": 7.713544319001812
280
  },
281
  "communicator.exchange": {
282
+ "total": 245.71628289900127,
283
+ "count": 27331,
284
  "is_parallel": true,
285
+ "self": 245.71628289900127
286
  },
287
  "steps_from_proto": {
288
+ "total": 48.491014789982785,
289
+ "count": 27331,
290
  "is_parallel": true,
291
+ "self": 8.843670360015153,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 39.64734442996763,
295
+ "count": 273310,
296
  "is_parallel": true,
297
+ "self": 39.64734442996763
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.0004568059998746321,
313
  "count": 1,
314
+ "self": 0.0004568059998746321,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 624.5793353869763,
324
+ "count": 962887,
325
  "is_parallel": true,
326
+ "self": 20.048923227022442,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 345.28379113595355,
330
+ "count": 962887,
331
  "is_parallel": true,
332
+ "self": 340.95320233995335,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 4.3305887960002,
336
+ "count": 30,
337
  "is_parallel": true,
338
+ "self": 4.3305887960002
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 259.2466210240002,
344
+ "count": 136,
345
  "is_parallel": true,
346
+ "self": 76.02750755398978,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 183.21911347001043,
350
+ "count": 6933,
351
  "is_parallel": true,
352
+ "self": 183.21911347001043
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.09145889000001262,
364
  "count": 1,
365
+ "self": 0.0010628370000631548,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.09039605299994946,
369
  "count": 1,
370
+ "self": 0.09039605299994946
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -2,103 +2,103 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 1984,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1984.onnx",
7
- "reward": null,
8
- "creation_time": 1709617204.2843533,
9
  "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-1984.pt"
11
  ]
12
  },
13
  {
14
- "steps": 2968,
15
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-2968.onnx",
16
- "reward": 3.272727272727273,
17
- "creation_time": 1709617208.1503448,
18
  "auxillary_file_paths": [
19
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-2968.pt"
20
  ]
21
  },
22
  {
23
- "steps": 3992,
24
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-3992.onnx",
25
- "reward": 3.272727272727273,
26
- "creation_time": 1709617209.5688622,
27
  "auxillary_file_paths": [
28
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-3992.pt"
29
  ]
30
  },
31
  {
32
- "steps": 4976,
33
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-4976.onnx",
34
- "reward": 4.0,
35
- "creation_time": 1709617211.7535233,
36
  "auxillary_file_paths": [
37
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-4976.pt"
38
  ]
39
  },
40
  {
41
- "steps": 5936,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-5936.onnx",
43
- "reward": 4.0,
44
- "creation_time": 1709617214.489213,
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-5936.pt"
47
  ]
48
  },
49
  {
50
- "steps": 6984,
51
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-6984.onnx",
52
- "reward": 3.3636363636363638,
53
- "creation_time": 1709617217.1152039,
54
  "auxillary_file_paths": [
55
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-6984.pt"
56
  ]
57
  },
58
  {
59
- "steps": 7944,
60
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-7944.onnx",
61
- "reward": 3.3636363636363638,
62
- "creation_time": 1709617218.3590982,
63
  "auxillary_file_paths": [
64
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-7944.pt"
65
  ]
66
  },
67
  {
68
- "steps": 8992,
69
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-8992.onnx",
70
- "reward": 4.818181818181818,
71
- "creation_time": 1709617221.6392782,
72
  "auxillary_file_paths": [
73
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-8992.pt"
74
  ]
75
  },
76
  {
77
- "steps": 9952,
78
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-9952.onnx",
79
- "reward": 4.818181818181818,
80
- "creation_time": 1709617222.967461,
81
  "auxillary_file_paths": [
82
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-9952.pt"
83
  ]
84
  },
85
  {
86
- "steps": 10208,
87
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-10208.onnx",
88
- "reward": 4.818181818181818,
89
- "creation_time": 1709617223.0996897,
90
  "auxillary_file_paths": [
91
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-10208.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
- "steps": 10208,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
- "reward": 4.818181818181818,
99
- "creation_time": 1709617223.0996897,
100
  "auxillary_file_paths": [
101
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-10208.pt"
102
  ]
103
  }
104
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 219992,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-219992.onnx",
7
+ "reward": 24.3,
8
+ "creation_time": 1709623009.630262,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-219992.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 229952,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-229952.onnx",
16
+ "reward": 24.90909090909091,
17
+ "creation_time": 1709623028.8604286,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-229952.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 239992,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-239992.onnx",
25
+ "reward": 25.454545454545453,
26
+ "creation_time": 1709623050.564408,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-239992.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 249944,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.onnx",
34
+ "reward": 24.90909090909091,
35
+ "creation_time": 1709623070.6402118,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 259984,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-259984.onnx",
43
+ "reward": 26.818181818181817,
44
+ "creation_time": 1709623092.1867228,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-259984.pt"
47
  ]
48
  },
49
  {
50
+ "steps": 269936,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-269936.onnx",
52
+ "reward": 25.90909090909091,
53
+ "creation_time": 1709623113.0352645,
54
  "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-269936.pt"
56
  ]
57
  },
58
  {
59
+ "steps": 279976,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-279976.onnx",
61
+ "reward": 26.272727272727273,
62
+ "creation_time": 1709623134.16969,
63
  "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-279976.pt"
65
  ]
66
  },
67
  {
68
+ "steps": 289992,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-289992.onnx",
70
+ "reward": 25.454545454545453,
71
+ "creation_time": 1709623154.7998548,
72
  "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-289992.pt"
74
  ]
75
  },
76
  {
77
+ "steps": 299968,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
79
+ "reward": 25.363636363636363,
80
+ "creation_time": 1709623176.864819,
81
  "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.pt"
83
  ]
84
  },
85
  {
86
+ "steps": 300608,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-300608.onnx",
88
+ "reward": 25.363636363636363,
89
+ "creation_time": 1709623177.0242183,
90
  "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-300608.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 300608,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 25.363636363636363,
99
+ "creation_time": 1709623177.0242183,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-300608.pt"
102
  ]
103
  }
104
  },