Hugging Face's logo

hartman23
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
hartman23 commited on
Commit
13cf853
·
verified ·
1 Parent(s): b91e46f

Second Push

Browse files
Files changed (20) hide show
  1. SnowballTarget.onnx +2 -2
  2. SnowballTarget/SnowballTarget-0.onnx +3 -0
  3. SnowballTarget/SnowballTarget-0.pt +3 -0
  4. SnowballTarget/SnowballTarget-149984.onnx +2 -2
  5. SnowballTarget/SnowballTarget-149984.pt +2 -2
  6. SnowballTarget/SnowballTarget-199984.onnx +2 -2
  7. SnowballTarget/SnowballTarget-199984.pt +2 -2
  8. SnowballTarget/SnowballTarget-200112.onnx +2 -2
  9. SnowballTarget/SnowballTarget-200112.pt +2 -2
  10. SnowballTarget/SnowballTarget-49936.onnx +2 -2
  11. SnowballTarget/SnowballTarget-49936.pt +2 -2
  12. SnowballTarget/SnowballTarget-99960.onnx +2 -2
  13. SnowballTarget/SnowballTarget-99960.pt +2 -2
  14. SnowballTarget/checkpoint.pt +2 -2
  15. SnowballTarget/events.out.tfevents.1734561809.7c714cd12d50.42528.0 +3 -0
  16. config.json +1 -1
  17. configuration.yaml +5 -5
  18. run_logs/Player-0.log +13 -13
  19. run_logs/timers.json +125 -125
  20. 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:ef4cce0f1261988d5cac69bc285d6fdac7ae51c7c425846326b9bd751ef4de37
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca67e88ceac60d29e082049aa638fa4217acb361d405023d35cbff856e3e5e23
3
+ size 1442973
SnowballTarget/SnowballTarget-0.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4800937e1329b486ba0bb00e913f0db4436f4fb1f21af001cc57932ed8b1fabe
3
+ size 1439175
SnowballTarget/SnowballTarget-0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4340f01390dfac13c70d56136b2f38f9376bc75f9595b3434dd2267fd5799a3
3
+ size 2869580
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc0ca6e4d3329f88df5cb981002a0e611c9e5bfd126b6ccfd4798a6bb60801f8
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c2b28b11a00f40752e9d2d0e158477070d0111f745015038795538bf818e4a1
3
+ size 1442973
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b4401f36df0f99ddbd32de2d1d07feb65dc26c146467f81a6de15386169f731
3
- size 3849115
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87ea5507362bdd3c5e3c8fde9ba86403544af43efa186b8ad1162693cdc71f04
3
+ size 8601214
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef4cce0f1261988d5cac69bc285d6fdac7ae51c7c425846326b9bd751ef4de37
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca67e88ceac60d29e082049aa638fa4217acb361d405023d35cbff856e3e5e23
3
+ size 1442973
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3e91fcb1bfd7af752ce94d396e065222ba623aa2f16385c7c9d98c8a9d8e2c0
3
- size 3849115
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3365a6ba892a73d04b595488c4bc9251e280ff1acb9af2035124d9cbfa64b1d5
3
+ size 8601214
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef4cce0f1261988d5cac69bc285d6fdac7ae51c7c425846326b9bd751ef4de37
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca67e88ceac60d29e082049aa638fa4217acb361d405023d35cbff856e3e5e23
3
+ size 1442973
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:574a4e4264bdbb8a5ef30933efd20c2754353ef975cfe6258b0619cd29d62d0f
3
- size 3849115
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e3967f3eec0c6c9bdf18b21e7100121f35924fa0548ac8c8685d5f0bb3d7d32
3
+ size 8601214
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f29ea5af690f83e115a177789706d184e2dcb9dea7c734e6e254a8a37b730f1
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2707b0415a3d404b8e7bacaee54f7de4796a44abfdcda6c04f53ecc37497577a
3
+ size 1442973
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c116192414105c850f1294eed0d5a9265f2ba924b7d8a72a5d2ae6538e9c711b
3
- size 3849040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be6022eda12358573e7f5a3914f9b8077c3302905c43c1122d47b6e9e18b80a9
3
+ size 8601091
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5dfa8fca7c07a07805577ed8b60dbd9d16027f7ca9303cbf43c5ed22b17e3a9
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcbef9eda439eb60b6048b3ded16e4081049ad4da1dcc6b175254c702d6631dd
3
+ size 1442973
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e08a5ae518e0c2eae78a8943cb2999a8a183dc78865266247a7976fa9623fc6d
3
- size 3849040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02927d0162a8516fe49e5ce407f0f1a5d9c23f1612629642b83fa8b2634c5031
3
+ size 8601091
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53a0b15fb7c35af6e05189c25ffda9c0013df9a92bfa7fdd603f4f76110abeeb
3
- size 3848290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4498ccee48ea55ad8f17b545932c551464e73b70496b7c31b44c97e967711cc4
3
+ size 8599861
SnowballTarget/events.out.tfevents.1734561809.7c714cd12d50.42528.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78cd122815b959b1d175ea6b14c6e78e12efcfa7886446302c00f062cb2b95a7
3
+ size 32993
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.99, "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": 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": "SnowballTarget2", "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": 0.003, "beta": 0.005, "epsilon": 0.3, "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": 5, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget6", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -7,8 +7,8 @@ behaviors:
7
  buffer_size: 2048
8
  learning_rate: 0.003
9
  beta: 0.005
10
- epsilon: 0.2
11
- lambd: 0.99
12
  num_epoch: 3
13
  shared_critic: false
14
  learning_rate_schedule: linear
@@ -18,7 +18,7 @@ behaviors:
18
  network_settings:
19
  normalize: false
20
  hidden_units: 256
21
- num_layers: 2
22
  vis_encode_type: simple
23
  memory: null
24
  goal_conditioning_type: hyper
@@ -66,11 +66,11 @@ engine_settings:
66
  no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
- run_id: SnowballTarget2
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
 
7
  buffer_size: 2048
8
  learning_rate: 0.003
9
  beta: 0.005
10
+ epsilon: 0.3
11
+ lambd: 0.95
12
  num_epoch: 3
13
  shared_critic: false
14
  learning_rate_schedule: linear
 
18
  network_settings:
19
  normalize: false
20
  hidden_units: 256
21
+ num_layers: 5
22
  vis_encode_type: simple
23
  memory: null
24
  goal_conditioning_type: hyper
 
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: true
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 0.099 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: 0.731097 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]: 5369 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
54
  Initial Block Size 4.0 MB
55
  Current Block Size 4.0 MB
56
  Peak Allocated Bytes 2.0 MB
@@ -166,19 +166,19 @@ Memory Statistics:
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
- Peak main deferred allocation count 36
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
173
  Peak Allocated bytes 1.0 MB
174
  [ALLOC_DEFAULT_MAIN]
175
- Peak usage frame count: [4.0 MB-8.0 MB]: 5461 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
  Peak Allocated memory 6.7 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
- Peak usage frame count: [16.0 MB-32.0 MB]: 5461 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]: 5027 frames, [64.0 KB-128.0 KB]: 434 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
- Peak Allocated memory 66.8 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
- Peak usage frame count: [32.0 KB-64.0 KB]: 5461 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]: 5461 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]: 5460 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]: 5461 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]: 5461 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 0.118 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: 0.795735 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]: 5374 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
54
  Initial Block Size 4.0 MB
55
  Current Block Size 4.0 MB
56
  Peak Allocated Bytes 2.0 MB
 
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
+ Peak main deferred allocation count 42
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
173
  Peak Allocated bytes 1.0 MB
174
  [ALLOC_DEFAULT_MAIN]
175
+ Peak usage frame count: [4.0 MB-8.0 MB]: 5466 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
  Peak Allocated memory 6.7 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5466 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]: 4342 frames, [64.0 KB-128.0 KB]: 1124 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 67.3 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5466 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]: 5466 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]: 5465 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]: 5466 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]: 5466 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
@@ -2,15 +2,15 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 1.1600804328918457,
6
- "min": 1.1600804328918457,
7
- "max": 2.866154193878174,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 11089.208984375,
12
- "min": 11089.208984375,
13
- "max": 29415.33984375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.877388954162598,
30
- "min": 0.4798322021961212,
31
- "max": 12.877388954162598,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2511.0908203125,
36
- "min": 93.08744812011719,
37
- "max": 2590.6220703125,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,87 +50,87 @@
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.07226741420393654,
54
- "min": 0.06207192843152477,
55
- "max": 0.08020605418035606,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.28906965681574615,
60
- "min": 0.2482877137260991,
61
- "max": 0.35459302726638847,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.44036250377950426,
66
- "min": 0.2503437679032704,
67
- "max": 0.5840809709009003,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 1.761450015118017,
72
- "min": 1.0013750716130816,
73
- "max": 2.797550805059134,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 8.130009729000006e-05,
78
- "min": 8.130009729000006e-05,
79
  "max": 0.0029188200027059994,
80
  "count": 20
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 0.0003252003891600002,
84
- "min": 0.0003252003891600002,
85
  "max": 0.013851600038280001,
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.10271000000000002,
90
- "min": 0.10271000000000002,
91
- "max": 0.19729400000000002,
92
  "count": 20
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.4108400000000001,
96
- "min": 0.4108400000000001,
97
- "max": 0.96172,
98
  "count": 20
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
- "value": 0.00014522900000000006,
102
- "min": 0.00014522900000000006,
103
  "max": 0.0048649706,
104
  "count": 20
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.0005809160000000002,
108
- "min": 0.0005809160000000002,
109
  "max": 0.023089828,
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 24.65909090909091,
114
- "min": 3.2045454545454546,
115
- "max": 25.09090909090909,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1085.0,
120
- "min": 141.0,
121
- "max": 1378.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 24.65909090909091,
126
- "min": 3.2045454545454546,
127
- "max": 25.09090909090909,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1085.0,
132
- "min": 141.0,
133
- "max": 1378.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
@@ -148,67 +148,67 @@
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1734556377",
152
  "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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=SnowballTarget2 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.5.1+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1734556935"
160
  },
161
- "total": 558.6190937129995,
162
  "count": 1,
163
- "self": 0.4901808479989995,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.06738271100039128,
167
  "count": 1,
168
- "self": 0.06738271100039128
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 558.0615301540001,
172
  "count": 1,
173
- "self": 0.8074708589847432,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 2.223583595000491,
177
  "count": 1,
178
- "self": 2.223583595000491
179
  },
180
  "TrainerController.advance": {
181
- "total": 554.9481329860155,
182
- "count": 18202,
183
- "self": 0.3886819680483313,
184
  "children": {
185
  "env_step": {
186
- "total": 554.5594510179671,
187
- "count": 18202,
188
- "self": 431.1749220889096,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 122.99731050302762,
192
- "count": 18202,
193
- "self": 1.9275531419771141,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 121.0697573610505,
197
- "count": 18202,
198
- "self": 121.0697573610505
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.38721842602990364,
204
- "count": 18202,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 556.2812152899623,
209
- "count": 18202,
210
  "is_parallel": true,
211
- "self": 257.88310522098345,
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": 0.0027627330000541406,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0009554819989716634,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0018072510010824772,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0018072510010824772
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.041688494000482024,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0008260449994850205,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00046136499986459967,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00046136499986459967
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03795821300082025,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03795821300082025
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0024428710003121523,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0004690200003096834,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.001973851000002469,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.001973851000002469
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 298.3981100689789,
271
- "count": 18201,
272
  "is_parallel": true,
273
- "self": 14.04851014788892,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 7.009006283052258,
277
- "count": 18201,
278
  "is_parallel": true,
279
- "self": 7.009006283052258
280
  },
281
  "communicator.exchange": {
282
- "total": 234.21097163205377,
283
- "count": 18201,
284
  "is_parallel": true,
285
- "self": 234.21097163205377
286
  },
287
  "steps_from_proto": {
288
- "total": 43.12962200598395,
289
- "count": 18201,
290
  "is_parallel": true,
291
- "self": 8.42452497706472,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 34.705097028919226,
295
- "count": 182010,
296
  "is_parallel": true,
297
- "self": 34.705097028919226
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.0001704380001683603,
313
  "count": 1,
314
- "self": 0.0001704380001683603,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 548.7020985289628,
324
- "count": 743052,
325
  "is_parallel": true,
326
- "self": 16.057937569507885,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 297.27185115245084,
330
- "count": 743052,
331
  "is_parallel": true,
332
- "self": 296.3035191914505,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 0.9683319610003309,
336
  "count": 4,
337
  "is_parallel": true,
338
- "self": 0.9683319610003309
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 235.37230980700406,
344
  "count": 90,
345
  "is_parallel": true,
346
- "self": 72.60989555098877,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 162.7624142560153,
350
  "count": 4587,
351
  "is_parallel": true,
352
- "self": 162.7624142560153
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.08217227599925536,
364
  "count": 1,
365
- "self": 0.0010850899998331442,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.08108718599942222,
369
  "count": 1,
370
- "self": 0.08108718599942222
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.9396764636039734,
6
+ "min": 0.9328323602676392,
7
+ "max": 2.835533618927002,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 9003.0400390625,
12
+ "min": 9003.0400390625,
13
+ "max": 29132.2734375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 12.420930862426758,
30
+ "min": 0.30448928475379944,
31
+ "max": 12.420930862426758,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2422.08154296875,
36
+ "min": 59.0709228515625,
37
+ "max": 2523.8857421875,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.0667450096955815,
54
+ "min": 0.0643873424590257,
55
+ "max": 0.07613985102313262,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.266980038782326,
60
+ "min": 0.2575493698361028,
61
+ "max": 0.38069925511566305,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.18022368450229076,
66
+ "min": 0.09609835992987248,
67
+ "max": 0.30526913211626167,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.720894738009163,
72
+ "min": 0.3843934397194899,
73
+ "max": 1.5263456605813084,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 8.082009730600007e-05,
78
+ "min": 8.082009730600007e-05,
79
  "max": 0.0029188200027059994,
80
  "count": 20
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 0.00032328038922400026,
84
+ "min": 0.00032328038922400026,
85
  "max": 0.013851600038280001,
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10538800000000001,
90
+ "min": 0.10538800000000001,
91
+ "max": 0.29458799999999996,
92
  "count": 20
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.42155200000000004,
96
+ "min": 0.42155200000000004,
97
+ "max": 1.42344,
98
  "count": 20
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 0.0001444306000000001,
102
+ "min": 0.0001444306000000001,
103
  "max": 0.0048649706,
104
  "count": 20
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.0005777224000000004,
108
+ "min": 0.0005777224000000004,
109
  "max": 0.023089828,
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 24.772727272727273,
114
+ "min": 2.772727272727273,
115
+ "max": 24.954545454545453,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1090.0,
120
+ "min": 122.0,
121
+ "max": 1334.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 24.772727272727273,
126
+ "min": 2.772727272727273,
127
+ "max": 24.954545454545453,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1090.0,
132
+ "min": 122.0,
133
+ "max": 1334.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1734561808",
152
  "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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=SnowballTarget6 --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": "2.5.1+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1734562439"
160
  },
161
+ "total": 630.1525164979994,
162
  "count": 1,
163
+ "self": 0.88209219700002,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.08057057099904341,
167
  "count": 1,
168
+ "self": 0.08057057099904341
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 629.1898537300003,
172
  "count": 1,
173
+ "self": 0.8146852400859643,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.2128651959992567,
177
  "count": 1,
178
+ "self": 2.2128651959992567
179
  },
180
  "TrainerController.advance": {
181
+ "total": 625.9671203839171,
182
+ "count": 18219,
183
+ "self": 0.3993069580701558,
184
  "children": {
185
  "env_step": {
186
+ "total": 625.5678134258469,
187
+ "count": 18219,
188
+ "self": 496.91452586006017,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 128.24817036493369,
192
+ "count": 18219,
193
+ "self": 2.0094329038365686,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 126.23873746109712,
197
+ "count": 18219,
198
+ "self": 126.23873746109712
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.4051172008530557,
204
+ "count": 18219,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 627.2540214290875,
209
+ "count": 18219,
210
  "is_parallel": true,
211
+ "self": 323.63135734108437,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0027559609989111777,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0007963979969645152,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0019595630019466626,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0019595630019466626
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.04244096000002173,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0007532430008723168,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00044428000001062173,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00044428000001062173
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03887668999959715,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03887668999959715
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.002366746999541647,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0004821170041395817,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.001884629995402065,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.001884629995402065
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 303.62266408800315,
271
+ "count": 18218,
272
  "is_parallel": true,
273
+ "self": 14.029078195988404,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 7.037806883961821,
277
+ "count": 18218,
278
  "is_parallel": true,
279
+ "self": 7.037806883961821
280
  },
281
  "communicator.exchange": {
282
+ "total": 238.70472706989676,
283
+ "count": 18218,
284
  "is_parallel": true,
285
+ "self": 238.70472706989676
286
  },
287
  "steps_from_proto": {
288
+ "total": 43.85105193815616,
289
+ "count": 18218,
290
  "is_parallel": true,
291
+ "self": 8.520708841708256,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 35.330343096447905,
295
+ "count": 182180,
296
  "is_parallel": true,
297
+ "self": 35.330343096447905
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.0001894509987323545,
313
  "count": 1,
314
+ "self": 0.0001894509987323545,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 619.7273823972318,
324
+ "count": 748058,
325
  "is_parallel": true,
326
+ "self": 16.304826081483043,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 313.98528438775793,
330
+ "count": 748058,
331
  "is_parallel": true,
332
+ "self": 312.6801092737569,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 1.305175114001031,
336
  "count": 4,
337
  "is_parallel": true,
338
+ "self": 1.305175114001031
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 289.4372719279909,
344
  "count": 90,
345
  "is_parallel": true,
346
+ "self": 66.57187288802197,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 222.8653990399689,
350
  "count": 4587,
351
  "is_parallel": true,
352
+ "self": 222.8653990399689
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.1949934589993063,
364
  "count": 1,
365
+ "self": 0.004870779999691877,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.19012267899961444,
369
  "count": 1,
370
+ "self": 0.19012267899961444
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -3,57 +3,57 @@
3
  "checkpoints": [
4
  {
5
  "steps": 49936,
6
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 10.181818181818182,
8
- "creation_time": 1734556516.3561795,
9
  "auxillary_file_paths": [
10
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
12
  },
13
  {
14
  "steps": 99960,
15
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 19.545454545454547,
17
- "creation_time": 1734556656.9587693,
18
  "auxillary_file_paths": [
19
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
21
  },
22
  {
23
  "steps": 149984,
24
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 23.181818181818183,
26
- "creation_time": 1734556794.4471014,
27
  "auxillary_file_paths": [
28
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
30
  },
31
  {
32
  "steps": 199984,
33
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 23.727272727272727,
35
- "creation_time": 1734556935.3367863,
36
  "auxillary_file_paths": [
37
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
  "steps": 200112,
42
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 23.727272727272727,
44
- "creation_time": 1734556935.4434266,
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
  "steps": 200112,
52
- "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
53
- "reward": 23.727272727272727,
54
- "creation_time": 1734556935.4434266,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
3
  "checkpoints": [
4
  {
5
  "steps": 49936,
6
+ "file_path": "results/SnowballTarget6/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 15.727272727272727,
8
+ "creation_time": 1734561964.408665,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget6/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
12
  },
13
  {
14
  "steps": 99960,
15
+ "file_path": "results/SnowballTarget6/SnowballTarget/SnowballTarget-99960.onnx",
16
+ "reward": 21.90909090909091,
17
+ "creation_time": 1734562119.0415814,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget6/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
21
  },
22
  {
23
  "steps": 149984,
24
+ "file_path": "results/SnowballTarget6/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 23.545454545454547,
26
+ "creation_time": 1734562280.8939455,
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": 25.09090909090909,
35
+ "creation_time": 1734562438.006329,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget6/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
  "steps": 200112,
42
+ "file_path": "results/SnowballTarget6/SnowballTarget/SnowballTarget-200112.onnx",
43
+ "reward": 25.09090909090909,
44
+ "creation_time": 1734562438.238263,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget6/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
  "steps": 200112,
52
+ "file_path": "results/SnowballTarget6/SnowballTarget.onnx",
53
+ "reward": 25.09090909090909,
54
+ "creation_time": 1734562438.238263,
55
  "auxillary_file_paths": [
56
+ "results/SnowballTarget6/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },