Hugging Face's logo

creogenus
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
 Metrics Community
creogenus commited on
Commit
c27659a
·
verified ·
1 Parent(s): 63a044e

Updated model

Browse files
Files changed (18) hide show
  1. SnowballTarget.onnx +2 -2
  2. SnowballTarget/SnowballTarget-149984.onnx +2 -2
  3. SnowballTarget/SnowballTarget-149984.pt +2 -2
  4. SnowballTarget/SnowballTarget-199984.onnx +2 -2
  5. SnowballTarget/SnowballTarget-199984.pt +2 -2
  6. SnowballTarget/SnowballTarget-200112.onnx +2 -2
  7. SnowballTarget/SnowballTarget-200112.pt +2 -2
  8. SnowballTarget/SnowballTarget-49936.onnx +2 -2
  9. SnowballTarget/SnowballTarget-49936.pt +2 -2
  10. SnowballTarget/SnowballTarget-99960.onnx +2 -2
  11. SnowballTarget/SnowballTarget-99960.pt +2 -2
  12. SnowballTarget/checkpoint.pt +2 -2
  13. SnowballTarget/events.out.tfevents.1740239025.919ddbd530b3.22548.0 +3 -0
  14. config.json +1 -1
  15. configuration.yaml +18 -5
  16. run_logs/Player-0.log +6 -9
  17. run_logs/timers.json +163 -115
  18. run_logs/training_status.json +24 -24
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5ac8e6bd76a5c001f1ccabc963dce49f7523cc0e1611686bb99fa5e455ed8bd
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83e33eda508e5c4859fdc6cc2646d006f92c277aeed20b5a9907f6520e582f72
3
+ size 1167766
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:671c019e13248f48dc9a05512b6e1e522be58c047ee82211153bf4023a770edb
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bbda5d58bb1dac7313e573bb25798ff6f50f9bec661bf8a64290dd61c8eb45d
3
+ size 1167766
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7e36c09cee167d5815cd9de1ff89f8431d0bf7774dce4e7c89fe2bcf40eb222
3
- size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1c4af87ec144f1792e096c0bb3482ea35d5440a5996c0dbe6fb7b5f92a149e8
3
+ size 7749367
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5ac8e6bd76a5c001f1ccabc963dce49f7523cc0e1611686bb99fa5e455ed8bd
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83e33eda508e5c4859fdc6cc2646d006f92c277aeed20b5a9907f6520e582f72
3
+ size 1167766
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35d16b86de4df95fd843c9d868e53f1ae3692bb819cf0fccff9435279bd3ba1e
3
- size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1850b47cccf5f09da2c5bfc78cdccd32fd8095a11a9523581284ae7b04643453
3
+ size 7749367
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5ac8e6bd76a5c001f1ccabc963dce49f7523cc0e1611686bb99fa5e455ed8bd
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83e33eda508e5c4859fdc6cc2646d006f92c277aeed20b5a9907f6520e582f72
3
+ size 1167766
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47ec5b1b6fa74954e61bb6c97a7cd25174f024b7e02fea82824504aaf7af6d83
3
- size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c865a1d2a8ea9ee23599d04ddc634f605c452fa706e57dda8f9d4adfc86907a9
3
+ size 7749367
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3644d33f4465e15cb36eaed3818353ea9cd20f1a7c68e651bae2b282614740f7
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32bdaef7bbc57a733a4d680193acdeddb98c26add05b9e236ffd47ce3d7a43a0
3
+ size 1167766
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1cc21b8e45912fb03260af51bfca2ae0d518e35a903d64f54d15a27a26eaade5
3
- size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bd4bdf584fd59168f63c068f3e5d0ae44fbaca243f6a4af023b79508056a083
3
+ size 7749272
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:241d782a453af90cb78b6722e3ca1bb241da976719a72807a775af5fd099326b
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:313cb5138195bb9cf2337fa8e0219a4251c4ff90710b1a51b687ca5e74cebb5f
3
+ size 1167766
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71badd1b4ecd47cc967c8bb22951de81035d756ddf2c6af8f290e80b3f9d6d81
3
- size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:493976e363f99a818d2c933be0b05a5c71f3598980eb5744afc4e0cc8135028d
3
+ size 7749272
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76efe72b6d9358aa35afee42d17f891f7b93ceace47fc8999f3478e0bafcd0f6
3
- size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:feffa12c4fea5151a1f8c33ef1e01347ecb39e3fd46a7f475d2debde5c8c7aff
3
+ size 7748322
SnowballTarget/events.out.tfevents.1740239025.919ddbd530b3.22548.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ccc704ebb2267b62e2edd508ef5fffcf3f24880849c6dc99892e79f23963eca
3
+ size 29419
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 196, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.15, "lambd": 0.95, "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": 384, "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}}, "curiosity": {"gamma": 0.99, "strength": 0.4, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0003, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "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}
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
@@ -17,7 +17,7 @@ behaviors:
17
  checkpoint_interval: 50000
18
  network_settings:
19
  normalize: false
20
- hidden_units: 256
21
  num_layers: 2
22
  vis_encode_type: simple
23
  memory: null
@@ -35,6 +35,19 @@ behaviors:
35
  memory: null
36
  goal_conditioning_type: hyper
37
  deterministic: false
 
 
 
 
 
 
 
 
 
 
 
 
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
@@ -66,7 +79,7 @@ engine_settings:
66
  no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
- run_id: SnowballTarget1
70
  initialize_from: null
71
  load_model: false
72
  resume: false
 
3
  SnowballTarget:
4
  trainer_type: ppo
5
  hyperparameters:
6
+ batch_size: 196
7
  buffer_size: 2048
8
  learning_rate: 0.0003
9
  beta: 0.005
10
+ epsilon: 0.15
11
  lambd: 0.95
12
+ num_epoch: 5
13
  shared_critic: false
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
 
17
  checkpoint_interval: 50000
18
  network_settings:
19
  normalize: false
20
+ hidden_units: 384
21
  num_layers: 2
22
  vis_encode_type: simple
23
  memory: null
 
35
  memory: null
36
  goal_conditioning_type: hyper
37
  deterministic: false
38
+ curiosity:
39
+ gamma: 0.99
40
+ strength: 0.4
41
+ network_settings:
42
+ normalize: false
43
+ hidden_units: 128
44
+ num_layers: 2
45
+ vis_encode_type: simple
46
+ memory: null
47
+ goal_conditioning_type: hyper
48
+ deterministic: false
49
+ learning_rate: 0.0003
50
+ encoding_size: null
51
  init_path: null
52
  keep_checkpoints: 10
53
  even_checkpoints: false
 
79
  no_graphics_monitor: false
80
  environment_parameters: null
81
  checkpoint_settings:
82
+ run_id: SnowballTarget3
83
  initialize_from: null
84
  load_model: false
85
  resume: false
run_logs/Player-0.log CHANGED
@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
5
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
6
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
7
- Unable to load player prefs
8
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
9
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ 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 0.089 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 +42,7 @@ 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: 0.969809 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.
@@ -169,7 +166,7 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 41
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
@@ -184,7 +181,7 @@ Memory Statistics:
184
  Peak usage frame count: [16.0 MB-32.0 MB]: 5458 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
@@ -213,10 +210,10 @@ 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]: 4211 frames, [64.0 KB-128.0 KB]: 1247 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 67.3 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
  Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
 
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
 
 
 
5
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
6
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
7
  Forcing GfxDevice: Null
 
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 0.083 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: 0.617912 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.
 
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
 
181
  Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.8 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]: 5276 frames, [64.0 KB-128.0 KB]: 182 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 66.3 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
  Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
run_logs/timers.json CHANGED
@@ -2,15 +2,15 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.8812531232833862,
6
- "min": 0.8812531232833862,
7
- "max": 2.8496854305267334,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8375.4296875,
12
- "min": 8375.4296875,
13
- "max": 29089.58984375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,77 +26,113 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.824972152709961,
30
- "min": 0.18623222410678864,
31
- "max": 12.824972152709961,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2500.86962890625,
36
- "min": 36.129051208496094,
37
- "max": 2598.50634765625,
 
 
 
 
 
 
 
 
 
 
 
 
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.07369358328401622,
42
- "min": 0.056957371319032404,
43
- "max": 0.07369358328401622,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.2947743331360649,
48
- "min": 0.2504801792071578,
49
- "max": 0.3673789270764888,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.18116920368344175,
54
- "min": 0.10388350203934618,
55
- "max": 0.31823076599953226,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.724676814733767,
60
- "min": 0.4155340081573847,
61
- "max": 1.4034993473221276,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
- "value": 8.082097306000005e-06,
66
- "min": 8.082097306000005e-06,
67
- "max": 0.000291882002706,
68
  "count": 20
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
- "value": 3.232838922400002e-05,
72
- "min": 3.232838922400002e-05,
73
  "max": 0.00138516003828,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
- "value": 0.10269400000000001,
78
- "min": 0.10269400000000001,
79
- "max": 0.19729400000000002,
80
  "count": 20
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
- "value": 0.41077600000000003,
84
- "min": 0.41077600000000003,
85
- "max": 0.96172,
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
- "value": 0.0001444306000000001,
90
- "min": 0.0001444306000000001,
91
- "max": 0.0048649706,
92
  "count": 20
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
- "value": 0.0005777224000000004,
96
- "min": 0.0005777224000000004,
97
  "max": 0.023089828,
98
  "count": 20
99
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
@@ -110,27 +146,39 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.522727272727273,
114
- "min": 2.8636363636363638,
115
- "max": 25.522727272727273,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1123.0,
120
- "min": 126.0,
121
- "max": 1380.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.522727272727273,
126
- "min": 2.8636363636363638,
127
- "max": 25.522727272727273,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1123.0,
132
- "min": 126.0,
133
- "max": 1380.0,
 
 
 
 
 
 
 
 
 
 
 
 
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
@@ -148,67 +196,67 @@
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1740234841",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.6.0+cu124",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1740235273"
160
  },
161
- "total": 432.052255328,
162
  "count": 1,
163
- "self": 0.4364587860000029,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.02317332899997382,
167
  "count": 1,
168
- "self": 0.02317332899997382
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 431.592623213,
172
  "count": 1,
173
- "self": 0.3430070690099001,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 2.885451229000182,
177
  "count": 1,
178
- "self": 2.885451229000182
179
  },
180
  "TrainerController.advance": {
181
- "total": 428.2764987159899,
182
  "count": 18192,
183
- "self": 0.3535795749864974,
184
  "children": {
185
  "env_step": {
186
- "total": 305.7601982899921,
187
  "count": 18192,
188
- "self": 232.87993763996315,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 72.6700397000177,
192
  "count": 18192,
193
- "self": 1.2808192160346152,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 71.38922048398308,
197
  "count": 18192,
198
- "self": 71.38922048398308
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.21022095001126218,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 430.04596713600176,
209
  "count": 18192,
210
  "is_parallel": true,
211
- "self": 226.328418657969,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
@@ -217,48 +265,48 @@
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
- "total": 0.005681076999962897,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.004110097999728168,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.001570979000234729,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.001570979000234729
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03514501799986647,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006580639997082471,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0004049140000006446,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0004049140000006446
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03207394400010344,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03207394400010344
250
  },
251
  "steps_from_proto": {
252
- "total": 0.002008096000054138,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00039107999964471674,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0016170160004094214,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0016170160004094214
262
  }
263
  }
264
  }
@@ -267,34 +315,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 203.71754847803277,
271
  "count": 18191,
272
  "is_parallel": true,
273
- "self": 9.943845452018195,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.561539801991103,
277
  "count": 18191,
278
  "is_parallel": true,
279
- "self": 5.561539801991103
280
  },
281
  "communicator.exchange": {
282
- "total": 155.91036471801294,
283
  "count": 18191,
284
  "is_parallel": true,
285
- "self": 155.91036471801294
286
  },
287
  "steps_from_proto": {
288
- "total": 32.30179850601053,
289
  "count": 18191,
290
  "is_parallel": true,
291
- "self": 5.80893985202988,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 26.492858653980647,
295
  "count": 181910,
296
  "is_parallel": true,
297
- "self": 26.492858653980647
298
  }
299
  }
300
  }
@@ -307,31 +355,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 122.16272085101127,
311
  "count": 18192,
312
- "self": 0.42055132999075795,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 26.992955690020153,
316
  "count": 18192,
317
- "self": 26.329588159019977,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.6633675310001763,
321
  "count": 4,
322
- "self": 0.6633675310001763
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 94.74921383100036,
328
  "count": 90,
329
- "self": 37.646985820003465,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 57.102228010996896,
333
- "count": 4587,
334
- "self": 57.102228010996896
335
  }
336
  }
337
  }
@@ -340,19 +388,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 1.032999989547534e-06,
344
  "count": 1,
345
- "self": 1.032999989547534e-06
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.0876651660000789,
349
  "count": 1,
350
- "self": 0.0008993810001811653,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.08676578499989773,
354
  "count": 1,
355
- "self": 0.08676578499989773
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.9212483167648315,
6
+ "min": 0.9212483167648315,
7
+ "max": 2.867960214614868,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 8755.5439453125,
12
+ "min": 8755.5439453125,
13
+ "max": 29276.138671875,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.047025680541992,
30
+ "min": 0.4108622372150421,
31
+ "max": 13.047025680541992,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2544.169921875,
36
+ "min": 79.707275390625,
37
+ "max": 2633.585693359375,
38
+ "count": 20
39
+ },
40
+ "SnowballTarget.Policy.CuriosityValueEstimate.mean": {
41
+ "value": 1.4923017024993896,
42
+ "min": 0.42835813760757446,
43
+ "max": 2.3067188262939453,
44
+ "count": 20
45
+ },
46
+ "SnowballTarget.Policy.CuriosityValueEstimate.sum": {
47
+ "value": 290.99884033203125,
48
+ "min": 83.10147857666016,
49
+ "max": 472.87738037109375,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.05358708580986951,
54
+ "min": 0.050163626572744265,
55
+ "max": 0.05840093715570137,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.21434834323947805,
60
+ "min": 0.20065450629097706,
61
+ "max": 0.28953316510887817,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.09344359091059729,
66
+ "min": 0.07468930684368719,
67
+ "max": 0.14716374164277857,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.37377436364238914,
72
+ "min": 0.29875722737474875,
73
+ "max": 0.7358187082138928,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 8.082097306000007e-06,
78
+ "min": 8.082097306000007e-06,
79
+ "max": 0.00029188200270599996,
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": 0.10134700000000002,
90
+ "min": 0.10134700000000002,
91
+ "max": 0.148647,
92
  "count": 20
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.4053880000000001,
96
+ "min": 0.4053880000000001,
97
+ "max": 0.73086,
98
  "count": 20
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 0.00014443060000000007,
102
+ "min": 0.00014443060000000007,
103
+ "max": 0.004864970599999999,
104
  "count": 20
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.0005777224000000003,
108
+ "min": 0.0005777224000000003,
109
  "max": 0.023089828,
110
  "count": 20
111
  },
112
+ "SnowballTarget.Losses.CuriosityForwardLoss.mean": {
113
+ "value": 0.036828366963362155,
114
+ "min": 0.03671931411055001,
115
+ "max": 0.11167120106518269,
116
+ "count": 20
117
+ },
118
+ "SnowballTarget.Losses.CuriosityForwardLoss.sum": {
119
+ "value": 0.14731346785344862,
120
+ "min": 0.1471481458707289,
121
+ "max": 0.44668480426073076,
122
+ "count": 20
123
+ },
124
+ "SnowballTarget.Losses.CuriosityInverseLoss.mean": {
125
+ "value": 0.7945268078283829,
126
+ "min": 0.7945268078283829,
127
+ "max": 2.7667143807627936,
128
+ "count": 20
129
+ },
130
+ "SnowballTarget.Losses.CuriosityInverseLoss.sum": {
131
+ "value": 3.1781072313135317,
132
+ "min": 3.1781072313135317,
133
+ "max": 12.65658032243902,
134
+ "count": 20
135
+ },
136
  "SnowballTarget.Environment.EpisodeLength.mean": {
137
  "value": 199.0,
138
  "min": 199.0,
 
146
  "count": 20
147
  },
148
  "SnowballTarget.Environment.CumulativeReward.mean": {
149
+ "value": 26.15909090909091,
150
+ "min": 3.5681818181818183,
151
+ "max": 26.15909090909091,
152
  "count": 20
153
  },
154
  "SnowballTarget.Environment.CumulativeReward.sum": {
155
+ "value": 1151.0,
156
+ "min": 157.0,
157
+ "max": 1409.0,
158
  "count": 20
159
  },
160
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
161
+ "value": 26.15909090909091,
162
+ "min": 3.5681818181818183,
163
+ "max": 26.15909090909091,
164
  "count": 20
165
  },
166
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
167
+ "value": 1151.0,
168
+ "min": 157.0,
169
+ "max": 1409.0,
170
+ "count": 20
171
+ },
172
+ "SnowballTarget.Policy.CuriosityReward.mean": {
173
+ "value": 3.007300841876052,
174
+ "min": 3.007300841876052,
175
+ "max": 5.480799111859365,
176
+ "count": 20
177
+ },
178
+ "SnowballTarget.Policy.CuriosityReward.sum": {
179
+ "value": 132.32123704254627,
180
+ "min": 132.32123704254627,
181
+ "max": 301.4439511522651,
182
  "count": 20
183
  },
184
  "SnowballTarget.IsTraining.mean": {
 
196
  },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1740239025",
200
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
201
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget3 --no-graphics",
202
  "mlagents_version": "1.2.0.dev0",
203
  "mlagents_envs_version": "1.2.0.dev0",
204
  "communication_protocol_version": "1.5.0",
205
  "pytorch_version": "2.6.0+cu124",
206
  "numpy_version": "1.23.5",
207
+ "end_time_seconds": "1740239574"
208
  },
209
+ "total": 549.5921344230001,
210
  "count": 1,
211
+ "self": 0.4287719890007793,
212
  "children": {
213
  "run_training.setup": {
214
+ "total": 0.019638693999695533,
215
  "count": 1,
216
+ "self": 0.019638693999695533
217
  },
218
  "TrainerController.start_learning": {
219
+ "total": 549.1437237399996,
220
  "count": 1,
221
+ "self": 0.34327860703251645,
222
  "children": {
223
  "TrainerController._reset_env": {
224
+ "total": 1.8911703900002976,
225
  "count": 1,
226
+ "self": 1.8911703900002976
227
  },
228
  "TrainerController.advance": {
229
+ "total": 546.7937669579669,
230
  "count": 18192,
231
+ "self": 0.37333067593954183,
232
  "children": {
233
  "env_step": {
234
+ "total": 301.67233247603235,
235
  "count": 18192,
236
+ "self": 230.5605755181441,
237
  "children": {
238
  "SubprocessEnvManager._take_step": {
239
+ "total": 70.90258636994713,
240
  "count": 18192,
241
+ "self": 1.2418399798962128,
242
  "children": {
243
  "TorchPolicy.evaluate": {
244
+ "total": 69.66074639005092,
245
  "count": 18192,
246
+ "self": 69.66074639005092
247
  }
248
  }
249
  },
250
  "workers": {
251
+ "total": 0.20917058794111654,
252
  "count": 18192,
253
  "self": 0.0,
254
  "children": {
255
  "worker_root": {
256
+ "total": 547.7082383329398,
257
  "count": 18192,
258
  "is_parallel": true,
259
+ "self": 344.88628337088994,
260
  "children": {
261
  "run_training.setup": {
262
  "total": 0.0,
 
265
  "self": 0.0,
266
  "children": {
267
  "steps_from_proto": {
268
+ "total": 0.0021596360002149595,
269
  "count": 1,
270
  "is_parallel": true,
271
+ "self": 0.0006937219995961641,
272
  "children": {
273
  "_process_rank_one_or_two_observation": {
274
+ "total": 0.0014659140006187954,
275
  "count": 10,
276
  "is_parallel": true,
277
+ "self": 0.0014659140006187954
278
  }
279
  }
280
  },
281
  "UnityEnvironment.step": {
282
+ "total": 0.04121166200002335,
283
  "count": 1,
284
  "is_parallel": true,
285
+ "self": 0.0005927939992034226,
286
  "children": {
287
  "UnityEnvironment._generate_step_input": {
288
+ "total": 0.000404823000280885,
289
  "count": 1,
290
  "is_parallel": true,
291
+ "self": 0.000404823000280885
292
  },
293
  "communicator.exchange": {
294
+ "total": 0.0383123430001433,
295
  "count": 1,
296
  "is_parallel": true,
297
+ "self": 0.0383123430001433
298
  },
299
  "steps_from_proto": {
300
+ "total": 0.001901702000395744,
301
  "count": 1,
302
  "is_parallel": true,
303
+ "self": 0.00036747600097442046,
304
  "children": {
305
  "_process_rank_one_or_two_observation": {
306
+ "total": 0.0015342259994213236,
307
  "count": 10,
308
  "is_parallel": true,
309
+ "self": 0.0015342259994213236
310
  }
311
  }
312
  }
 
315
  }
316
  },
317
  "UnityEnvironment.step": {
318
+ "total": 202.82195496204986,
319
  "count": 18191,
320
  "is_parallel": true,
321
+ "self": 9.701152280037604,
322
  "children": {
323
  "UnityEnvironment._generate_step_input": {
324
+ "total": 5.554603005948593,
325
  "count": 18191,
326
  "is_parallel": true,
327
+ "self": 5.554603005948593
328
  },
329
  "communicator.exchange": {
330
+ "total": 155.68612461098928,
331
  "count": 18191,
332
  "is_parallel": true,
333
+ "self": 155.68612461098928
334
  },
335
  "steps_from_proto": {
336
+ "total": 31.88007506507438,
337
  "count": 18191,
338
  "is_parallel": true,
339
+ "self": 5.624714032102929,
340
  "children": {
341
  "_process_rank_one_or_two_observation": {
342
+ "total": 26.25536103297145,
343
  "count": 181910,
344
  "is_parallel": true,
345
+ "self": 26.25536103297145
346
  }
347
  }
348
  }
 
355
  }
356
  },
357
  "trainer_advance": {
358
+ "total": 244.74810380599502,
359
  "count": 18192,
360
+ "self": 0.4115569980149303,
361
  "children": {
362
  "process_trajectory": {
363
+ "total": 38.8613563479812,
364
  "count": 18192,
365
+ "self": 38.34231229598117,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.5190440520000266,
369
  "count": 4,
370
+ "self": 0.5190440520000266
371
  }
372
  }
373
  },
374
  "_update_policy": {
375
+ "total": 205.47519045999888,
376
  "count": 90,
377
+ "self": 133.8213378710152,
378
  "children": {
379
  "TorchPPOOptimizer.update": {
380
+ "total": 71.65385258898368,
381
+ "count": 4945,
382
+ "self": 71.65385258898368
383
  }
384
  }
385
  }
 
388
  }
389
  },
390
  "trainer_threads": {
391
+ "total": 1.1580004866118543e-06,
392
  "count": 1,
393
+ "self": 1.1580004866118543e-06
394
  },
395
  "TrainerController._save_models": {
396
+ "total": 0.11550662699937675,
397
  "count": 1,
398
+ "self": 0.0014125859997875523,
399
  "children": {
400
  "RLTrainer._checkpoint": {
401
+ "total": 0.1140940409995892,
402
  "count": 1,
403
+ "self": 0.1140940409995892
404
  }
405
  }
406
  }
run_logs/training_status.json CHANGED
@@ -3,57 +3,57 @@
3
  "checkpoints": [
4
  {
5
  "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 13.363636363636363,
8
- "creation_time": 1740234950.157039,
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": 21.363636363636363,
17
- "creation_time": 1740235057.5298476,
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": 23.90909090909091,
26
- "creation_time": 1740235166.22663,
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": 24.818181818181817,
35
- "creation_time": 1740235272.6231928,
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": 24.818181818181817,
44
- "creation_time": 1740235272.7235959,
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": 24.818181818181817,
54
- "creation_time": 1740235272.7235959,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
3
  "checkpoints": [
4
  {
5
  "steps": 49936,
6
+ "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 15.272727272727273,
8
+ "creation_time": 1740239163.937057,
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": 22.636363636363637,
17
+ "creation_time": 1740239298.9327686,
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": 25.636363636363637,
26
+ "creation_time": 1740239436.9540567,
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": 25.636363636363637,
35
+ "creation_time": 1740239574.4253364,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget3/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
  "steps": 200112,
42
+ "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-200112.onnx",
43
+ "reward": 25.636363636363637,
44
+ "creation_time": 1740239574.5578046,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget3/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
  "steps": 200112,
52
+ "file_path": "results/SnowballTarget3/SnowballTarget.onnx",
53
+ "reward": 25.636363636363637,
54
+ "creation_time": 1740239574.5578046,
55
  "auxillary_file_paths": [
56
+ "results/SnowballTarget3/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },