Hugging Face's logo

DumbleDuck
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
DumbleDuck commited on
Commit
31ecbf3
·
verified ·
1 Parent(s): 360a3e2

First Push

Browse files
Files changed (20) 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-249880.onnx +3 -0
  7. SnowballTarget/SnowballTarget-249880.pt +3 -0
  8. SnowballTarget/SnowballTarget-250008.onnx +3 -0
  9. SnowballTarget/SnowballTarget-250008.pt +3 -0
  10. SnowballTarget/SnowballTarget-49952.onnx +3 -0
  11. SnowballTarget/SnowballTarget-49952.pt +3 -0
  12. SnowballTarget/SnowballTarget-99896.onnx +3 -0
  13. SnowballTarget/SnowballTarget-99896.pt +3 -0
  14. SnowballTarget/checkpoint.pt +2 -2
  15. SnowballTarget/events.out.tfevents.1745285894.95bbfa7064f3.23730.0 +3 -0
  16. config.json +1 -1
  17. configuration.yaml +6 -6
  18. run_logs/Player-0.log +13 -13
  19. run_logs/timers.json +178 -178
  20. run_logs/training_status.json +37 -28
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41988ac4e809092822a91436b20bbe4c5bb9bb61979d88da809c7206027b9d39
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1f144992fa93e9d1493a2775828ae83903b2f0c1746baf8268ec2128d234fea
3
+ size 657877
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d24e2cfecefb01b8134bdf63a539043eb0451611e6ddcdbcf5c80d3284d4874a
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ca45f75944c22b86a6d11b667c4035ad70d46bfd2740a59a61074d755b6cc96
3
+ size 657877
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e5e7077d91b0e8a557407f882444b81eaf01fe61d66e54392a6fc9e1813930c
3
- size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9b0c0725bcb684532c5d39038bf541b95a0d2623353e856b41489c19067ac75
3
+ size 3872166
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41988ac4e809092822a91436b20bbe4c5bb9bb61979d88da809c7206027b9d39
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb13cc2ae945ed01dcd099913f230b5e1327c919c7e14a8f3d078aa11f68b408
3
+ size 657877
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa48af93bfb2e4670d2afd60b32bb7d5ab95fe6529b42c5956f17b6d1f7936f9
3
- size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b995e5567c34f08fa05dc118ec216729bb28f9733a61242536db61a5a9fa4437
3
+ size 3872166
SnowballTarget/SnowballTarget-249880.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a92c0172e8fd35e600c30f877943900ff4fc738c50d579f6660d03d00af06f6
3
+ size 657877
SnowballTarget/SnowballTarget-249880.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:857f64f2c510ec5e84ef350751bb3515ecffc36b70a9fae37d032868784bf936
3
+ size 3872166
SnowballTarget/SnowballTarget-250008.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1f144992fa93e9d1493a2775828ae83903b2f0c1746baf8268ec2128d234fea
3
+ size 657877
SnowballTarget/SnowballTarget-250008.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dd3469a7e924798b7d20d85a6e0c52e758257823d4f2587a3e572bbdffa67c4
3
+ size 3872166
SnowballTarget/SnowballTarget-49952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3bba096a035916edb029fec71d4aa13a0651f3821448db49aee52914fb590e4
3
+ size 657877
SnowballTarget/SnowballTarget-49952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4ebe2f2c486cf074a87be01258322b81b4f58599edd810ed1943f4d28069bfe
3
+ size 3872061
SnowballTarget/SnowballTarget-99896.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdeeb5cedf6d4d583f4b0eafe8f0f52a64fffd49841f14863fbff6b8634c3e4f
3
+ size 657877
SnowballTarget/SnowballTarget-99896.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58432af635f9f7de616161535ff8abc4024aa233173d2c75aa48a8ff64b7db54
3
+ size 3872061
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6d78c572e92db984f6e2aad3bd9fdb6a9b62139b80a14cee3d4b52a27f7e383
3
- size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f80ba2f079c56148a339425e4fe1cab4e0a75aff95f88ac6710f99ab76660c6d
3
+ size 3871011
SnowballTarget/events.out.tfevents.1745285894.95bbfa7064f3.23730.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78c258fab246bb9605a699d204ef8aa4c4cf61a44a9c7075b25476ac9602dee7
3
+ size 27331
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0005, "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": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0008, "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": true, "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": 250000, "time_horizon": 128, "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": "SnowballTarget6", "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: 0.0005
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
@@ -16,7 +16,7 @@ behaviors:
16
  epsilon_schedule: linear
17
  checkpoint_interval: 50000
18
  network_settings:
19
- normalize: false
20
  hidden_units: 256
21
  num_layers: 2
22
  vis_encode_type: simple
@@ -38,8 +38,8 @@ behaviors:
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
- max_steps: 200000
42
- time_horizon: 64
43
  summary_freq: 10000
44
  threaded: false
45
  self_play: null
@@ -66,11 +66,11 @@ 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
73
- force: true
74
  train_model: false
75
  inference: false
76
  results_dir: results
 
5
  hyperparameters:
6
  batch_size: 128
7
  buffer_size: 2048
8
+ learning_rate: 0.0008
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
 
16
  epsilon_schedule: linear
17
  checkpoint_interval: 50000
18
  network_settings:
19
+ normalize: true
20
  hidden_units: 256
21
  num_layers: 2
22
  vis_encode_type: simple
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 250000
42
+ time_horizon: 128
43
  summary_freq: 10000
44
  threaded: false
45
  self_play: null
 
66
  no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
+ run_id: SnowballTarget6
70
  initialize_from: null
71
  load_model: false
72
  resume: false
73
+ force: false
74
  train_model: false
75
  inference: false
76
  results_dir: results
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 0.095 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: 0.619478 ms
46
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
47
  requesting resize 84 x 84
48
  Setting up 1 worker threads for Enlighten.
@@ -50,7 +50,7 @@ Memory Statistics:
50
  [ALLOC_TEMP_TLS] TLS Allocator
51
  StackAllocators :
52
  [ALLOC_TEMP_MAIN]
53
- Peak usage frame count: [8.0 KB-16.0 KB]: 5367 frames, [16.0 KB-32.0 KB]: 90 frames, [2.0 MB-4.0 MB]: 1 frames
54
  Initial Block Size 4.0 MB
55
  Current Block Size 4.0 MB
56
  Peak Allocated Bytes 2.0 MB
@@ -172,13 +172,13 @@ Memory Statistics:
172
  Used Block count 1
173
  Peak Allocated bytes 1.0 MB
174
  [ALLOC_DEFAULT_MAIN]
175
- Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
- Peak Allocated memory 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]: 5458 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
  Peak Allocated memory 17.8 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]: 4388 frames, [64.0 KB-128.0 KB]: 1070 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
- Peak Allocated memory 66.7 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
- Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
220
  Requested Block Size 16.0 MB
221
  Peak Block count 1
222
  Peak Allocated memory 39.6 KB
@@ -228,13 +228,13 @@ Memory Statistics:
228
  Used Block count 1
229
  Peak Allocated bytes 1.0 MB
230
  [ALLOC_CACHEOBJECTS_MAIN]
231
- Peak usage frame count: [0.5 MB-1.0 MB]: 5458 frames
232
  Requested Block Size 4.0 MB
233
  Peak Block count 1
234
  Peak Allocated memory 0.6 MB
235
  Peak Large allocation bytes 0 B
236
  [ALLOC_CACHEOBJECTS_THREAD]
237
- Peak usage frame count: [0.5 MB-1.0 MB]: 5457 frames, [2.0 MB-4.0 MB]: 1 frames
238
  Requested Block Size 4.0 MB
239
  Peak Block count 1
240
  Peak Allocated memory 2.2 MB
@@ -246,13 +246,13 @@ Memory Statistics:
246
  Used Block count 1
247
  Peak Allocated bytes 1.0 MB
248
  [ALLOC_TYPETREE_MAIN]
249
- Peak usage frame count: [0-1.0 KB]: 5458 frames
250
  Requested Block Size 2.0 MB
251
  Peak Block count 1
252
  Peak Allocated memory 1.0 KB
253
  Peak Large allocation bytes 0 B
254
  [ALLOC_TYPETREE_THREAD]
255
- Peak usage frame count: [1.0 KB-2.0 KB]: 5458 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
 
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.090 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
  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: 0.624021 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]: 6705 frames, [16.0 KB-32.0 KB]: 113 frames, [2.0 MB-4.0 MB]: 1 frames
54
  Initial Block Size 4.0 MB
55
  Current Block Size 4.0 MB
56
  Peak Allocated Bytes 2.0 MB
 
172
  Used Block count 1
173
  Peak Allocated bytes 1.0 MB
174
  [ALLOC_DEFAULT_MAIN]
175
+ Peak usage frame count: [4.0 MB-8.0 MB]: 6819 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 7.1 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 6819 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
  Peak Allocated memory 17.8 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]: 6593 frames, [64.0 KB-128.0 KB]: 226 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]: 6819 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]: 6819 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]: 6818 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]: 6819 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]: 6819 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": 0.8385888338088989,
6
- "min": 0.8385888338088989,
7
- "max": 2.851138114929199,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 7969.9482421875,
12
- "min": 7969.9482421875,
13
- "max": 29104.41796875,
14
- "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 199984.0,
18
  "min": 9952.0,
19
- "max": 199984.0,
20
- "count": 20
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 199984.0,
24
  "min": 9952.0,
25
- "max": 199984.0,
26
- "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 13.242030143737793,
30
- "min": 0.2582017779350281,
31
- "max": 13.242030143737793,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2582.19580078125,
36
- "min": 50.09114456176758,
37
- "max": 2693.198486328125,
38
- "count": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.06757358355218243,
42
- "min": 0.06585110651612208,
43
- "max": 0.07166822008861631,
44
- "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.2702943342087297,
48
- "min": 0.26980884679919565,
49
- "max": 0.35834110044308154,
50
- "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.17709490810247028,
54
- "min": 0.1298303642040849,
55
- "max": 0.2829548285580149,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.7083796324098811,
60
- "min": 0.5193214568163396,
61
- "max": 1.3213104301807925,
62
- "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
- "value": 1.347009730600001e-05,
66
- "min": 1.347009730600001e-05,
67
- "max": 0.00048647000270600005,
68
- "count": 20
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
- "value": 5.388038922400004e-05,
72
- "min": 5.388038922400004e-05,
73
- "max": 0.00230860003828,
74
- "count": 20
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
- "value": 0.10269400000000001,
78
- "min": 0.10269400000000001,
79
- "max": 0.19729400000000002,
80
- "count": 20
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
- "value": 0.41077600000000003,
84
- "min": 0.41077600000000003,
85
- "max": 0.96172,
86
- "count": 20
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
- "value": 0.0001444306000000001,
90
- "min": 0.0001444306000000001,
91
- "max": 0.0048649706,
92
- "count": 20
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
- "value": 0.0005777224000000004,
96
- "min": 0.0005777224000000004,
97
- "max": 0.023089828,
98
- "count": 20
99
- },
100
- "SnowballTarget.Environment.EpisodeLength.mean": {
101
- "value": 199.0,
102
- "min": 199.0,
103
- "max": 199.0,
104
- "count": 20
105
- },
106
- "SnowballTarget.Environment.EpisodeLength.sum": {
107
- "value": 8756.0,
108
- "min": 8756.0,
109
- "max": 10945.0,
110
- "count": 20
111
- },
112
- "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 26.318181818181817,
114
- "min": 3.7045454545454546,
115
- "max": 26.381818181818183,
116
- "count": 20
117
- },
118
- "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1158.0,
120
- "min": 163.0,
121
- "max": 1451.0,
122
- "count": 20
123
- },
124
- "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 26.318181818181817,
126
- "min": 3.7045454545454546,
127
- "max": 26.381818181818183,
128
- "count": 20
129
- },
130
- "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1158.0,
132
- "min": 163.0,
133
- "max": 1451.0,
134
- "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 20
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 20
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1745281709",
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 --force",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.6.0+cu124",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1745282165"
160
  },
161
- "total": 456.47453978800013,
162
  "count": 1,
163
- "self": 0.4745287640000697,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.0199177099998451,
167
  "count": 1,
168
- "self": 0.0199177099998451
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 455.9800933140002,
172
  "count": 1,
173
- "self": 0.38477020200048173,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 2.383765177999976,
177
  "count": 1,
178
- "self": 2.383765177999976
179
  },
180
  "TrainerController.advance": {
181
- "total": 453.11964366699976,
182
- "count": 18192,
183
- "self": 0.40181722197667114,
184
  "children": {
185
  "env_step": {
186
- "total": 320.88275024701557,
187
- "count": 18192,
188
- "self": 244.78299741999444,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 75.86871805001806,
192
- "count": 18192,
193
- "self": 1.3554315370313361,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 74.51328651298672,
197
- "count": 18192,
198
- "self": 74.51328651298672
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.2310347770030603,
204
- "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 454.48379826901146,
209
- "count": 18192,
210
  "is_parallel": true,
211
- "self": 239.48734262700782,
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": 0.002134976999968785,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0006189790003645612,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0015159979996042239,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0015159979996042239
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.058279932999994344,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0005481820001023152,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00038613199990322755,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00038613199990322755
244
  },
245
  "communicator.exchange": {
246
- "total": 0.05555932600009328,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.05555932600009328
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0017862929998955224,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00034172599976045603,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0014445670001350663,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0014445670001350663
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 214.99645564200364,
271
- "count": 18191,
272
  "is_parallel": true,
273
- "self": 10.04977074201679,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.516273121989116,
277
- "count": 18191,
278
  "is_parallel": true,
279
- "self": 5.516273121989116
280
  },
281
  "communicator.exchange": {
282
- "total": 166.75932848801858,
283
- "count": 18191,
284
  "is_parallel": true,
285
- "self": 166.75932848801858
286
  },
287
  "steps_from_proto": {
288
- "total": 32.67108328997915,
289
- "count": 18191,
290
  "is_parallel": true,
291
- "self": 5.8869245750140635,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 26.784158714965088,
295
- "count": 181910,
296
  "is_parallel": true,
297
- "self": 26.784158714965088
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 131.83507619800753,
311
- "count": 18192,
312
- "self": 0.485996823010737,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 28.115935144996683,
316
- "count": 18192,
317
- "self": 27.708985912996923,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.40694923199976074,
321
- "count": 4,
322
- "self": 0.40694923199976074
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 103.23314423000011,
328
- "count": 90,
329
- "self": 41.78955946299743,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 61.443584767002676,
333
- "count": 4587,
334
- "self": 61.443584767002676
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 9.339998996438226e-07,
344
  "count": 1,
345
- "self": 9.339998996438226e-07
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.09191333300009319,
349
  "count": 1,
350
- "self": 0.0010871020001559373,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.09082623099993725,
354
  "count": 1,
355
- "self": 0.09082623099993725
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 1.0005192756652832,
6
+ "min": 1.0005192756652832,
7
+ "max": 2.8310415744781494,
8
+ "count": 25
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 8804.5693359375,
12
+ "min": 8804.5693359375,
13
+ "max": 28940.94921875,
14
+ "count": 25
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 249880.0,
18
  "min": 9952.0,
19
+ "max": 249880.0,
20
+ "count": 25
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 249880.0,
24
  "min": 9952.0,
25
+ "max": 249880.0,
26
+ "count": 25
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.957201957702637,
30
+ "min": 0.414703905582428,
31
+ "max": 13.957201957702637,
32
+ "count": 25
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 1353.8486328125,
36
+ "min": 40.226280212402344,
37
+ "max": 1411.627685546875,
38
+ "count": 25
39
+ },
40
+ "SnowballTarget.Environment.EpisodeLength.mean": {
41
+ "value": 199.0,
42
+ "min": 199.0,
43
+ "max": 199.0,
44
+ "count": 25
45
+ },
46
+ "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 8756.0,
48
+ "min": 8756.0,
49
+ "max": 10945.0,
50
+ "count": 25
51
+ },
52
+ "SnowballTarget.Environment.CumulativeReward.mean": {
53
+ "value": 27.568181818181817,
54
+ "min": 4.681818181818182,
55
+ "max": 27.568181818181817,
56
+ "count": 25
57
+ },
58
+ "SnowballTarget.Environment.CumulativeReward.sum": {
59
+ "value": 1213.0,
60
+ "min": 206.0,
61
+ "max": 1515.0,
62
+ "count": 25
63
+ },
64
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
+ "value": 27.568181818181817,
66
+ "min": 4.681818181818182,
67
+ "max": 27.568181818181817,
68
+ "count": 25
69
+ },
70
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
+ "value": 1213.0,
72
+ "min": 206.0,
73
+ "max": 1515.0,
74
+ "count": 25
75
  },
76
  "SnowballTarget.Losses.PolicyLoss.mean": {
77
+ "value": 0.06210129925617081,
78
+ "min": 0.06210129925617081,
79
+ "max": 0.07561748272501956,
80
+ "count": 25
81
  },
82
  "SnowballTarget.Losses.PolicyLoss.sum": {
83
+ "value": 0.24840519702468325,
84
+ "min": 0.24840519702468325,
85
+ "max": 0.3780874136250978,
86
+ "count": 25
87
  },
88
  "SnowballTarget.Losses.ValueLoss.mean": {
89
+ "value": 0.16262870654463768,
90
+ "min": 0.13736278671844332,
91
+ "max": 0.2874898902487521,
92
+ "count": 25
93
  },
94
  "SnowballTarget.Losses.ValueLoss.sum": {
95
+ "value": 0.6505148261785507,
96
+ "min": 0.5921700890449917,
97
+ "max": 1.4112983188208414,
98
+ "count": 25
99
  },
100
  "SnowballTarget.Policy.LearningRate.mean": {
101
+ "value": 1.5040098120000011e-05,
102
+ "min": 1.5040098120000011e-05,
103
+ "max": 0.0007824000022000001,
104
+ "count": 25
105
  },
106
  "SnowballTarget.Policy.LearningRate.sum": {
107
+ "value": 6.0160392480000045e-05,
108
+ "min": 6.0160392480000045e-05,
109
+ "max": 0.0037536000308,
110
+ "count": 25
111
  },
112
  "SnowballTarget.Policy.Epsilon.mean": {
113
+ "value": 0.10188,
114
+ "min": 0.10188,
115
+ "max": 0.1978,
116
+ "count": 25
117
  },
118
  "SnowballTarget.Policy.Epsilon.sum": {
119
+ "value": 0.40752,
120
+ "min": 0.40752,
121
+ "max": 0.9692000000000001,
122
+ "count": 25
123
  },
124
  "SnowballTarget.Policy.Beta.mean": {
125
+ "value": 0.00010381200000000008,
126
+ "min": 0.00010381200000000008,
127
+ "max": 0.004890220000000001,
128
+ "count": 25
129
  },
130
  "SnowballTarget.Policy.Beta.sum": {
131
+ "value": 0.00041524800000000033,
132
+ "min": 0.00041524800000000033,
133
+ "max": 0.02346308,
134
+ "count": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 25
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 25
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1745285894",
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=SnowballTarget6 --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": "1745286442"
160
  },
161
+ "total": 548.207428613,
162
  "count": 1,
163
+ "self": 0.8045825750004951,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.020663676999902236,
167
  "count": 1,
168
+ "self": 0.020663676999902236
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 547.3821823609996,
172
  "count": 1,
173
+ "self": 0.4138622600439703,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.1674611489997915,
177
  "count": 1,
178
+ "self": 2.1674611489997915
179
  },
180
  "TrainerController.advance": {
181
+ "total": 544.6162616379552,
182
+ "count": 22728,
183
+ "self": 0.4284669310491154,
184
  "children": {
185
  "env_step": {
186
+ "total": 375.3740195359478,
187
+ "count": 22728,
188
+ "self": 275.75270871493376,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 99.37057520403687,
192
+ "count": 22728,
193
+ "self": 1.5869785651102575,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 97.78359663892661,
197
+ "count": 22728,
198
+ "self": 97.78359663892661
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.25073561697718105,
204
+ "count": 22728,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 545.300565538897,
209
+ "count": 22728,
210
  "is_parallel": true,
211
+ "self": 302.92732103581784,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.002240064000034181,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0006361899995681597,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0016038740004660212,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0016038740004660212
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.05354901500049891,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0005499720009538578,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00038391399993997766,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00038391399993997766
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.050935342000229866,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.050935342000229866
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0016797869993752101,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0003143739995721262,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.001365412999803084,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.001365412999803084
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 242.37324450307915,
271
+ "count": 22727,
272
  "is_parallel": true,
273
+ "self": 11.741168807054237,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 6.487960024999666,
277
+ "count": 22727,
278
  "is_parallel": true,
279
+ "self": 6.487960024999666
280
  },
281
  "communicator.exchange": {
282
+ "total": 186.05993160305934,
283
+ "count": 22727,
284
  "is_parallel": true,
285
+ "self": 186.05993160305934
286
  },
287
  "steps_from_proto": {
288
+ "total": 38.08418406796591,
289
+ "count": 22727,
290
  "is_parallel": true,
291
+ "self": 6.759363543805193,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 31.324820524160714,
295
+ "count": 227270,
296
  "is_parallel": true,
297
+ "self": 31.324820524160714
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 168.81377517095825,
311
+ "count": 22728,
312
+ "self": 0.49420756201379845,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 41.260879152942834,
316
+ "count": 22728,
317
+ "self": 40.4989085239431,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.7619706289997339,
321
+ "count": 5,
322
+ "self": 0.7619706289997339
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 127.05868845600162,
328
+ "count": 113,
329
+ "self": 48.77569470803155,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 78.28299374797007,
333
+ "count": 5763,
334
+ "self": 78.28299374797007
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 1.42800035973778e-06,
344
  "count": 1,
345
+ "self": 1.42800035973778e-06
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.18459588600035204,
349
  "count": 1,
350
+ "self": 0.0011665820002235705,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.18342930400012847,
354
  "count": 1,
355
+ "self": 0.18342930400012847
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -2,58 +2,67 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 16.90909090909091,
8
- "creation_time": 1745281817.7118633,
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": 21.181818181818183,
17
- "creation_time": 1745281936.4631653,
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": 26.272727272727273,
26
- "creation_time": 1745282052.0970256,
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": 26.09090909090909,
35
- "creation_time": 1745282165.235213,
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": 26.09090909090909,
44
- "creation_time": 1745282165.3395016,
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": 26.09090909090909,
54
- "creation_time": 1745282165.3395016,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 49952,
6
+ "file_path": "results/SnowballTarget6/SnowballTarget/SnowballTarget-49952.onnx",
7
+ "reward": 20.5,
8
+ "creation_time": 1745286003.8324952,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget6/SnowballTarget/SnowballTarget-49952.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 99896,
15
+ "file_path": "results/SnowballTarget6/SnowballTarget/SnowballTarget-99896.onnx",
16
+ "reward": null,
17
+ "creation_time": 1745286113.4412632,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget6/SnowballTarget/SnowballTarget-99896.pt"
20
  ]
21
  },
22
  {
23
  "steps": 149984,
24
+ "file_path": "results/SnowballTarget6/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": null,
26
+ "creation_time": 1745286223.824148,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget6/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
30
  },
31
  {
32
  "steps": 199984,
33
+ "file_path": "results/SnowballTarget6/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 26.5,
35
+ "creation_time": 1745286329.938911,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget6/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 249880,
42
+ "file_path": "results/SnowballTarget6/SnowballTarget/SnowballTarget-249880.onnx",
43
+ "reward": null,
44
+ "creation_time": 1745286441.2381437,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget6/SnowballTarget/SnowballTarget-249880.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 250008,
51
+ "file_path": "results/SnowballTarget6/SnowballTarget/SnowballTarget-250008.onnx",
52
+ "reward": null,
53
+ "creation_time": 1745286441.4467318,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget6/SnowballTarget/SnowballTarget-250008.pt"
56
  ]
57
  }
58
  ],
59
  "final_checkpoint": {
60
+ "steps": 250008,
61
+ "file_path": "results/SnowballTarget6/SnowballTarget.onnx",
62
+ "reward": null,
63
+ "creation_time": 1745286441.4467318,
64
  "auxillary_file_paths": [
65
+ "results/SnowballTarget6/SnowballTarget/SnowballTarget-250008.pt"
66
  ]
67
  }
68
  },