Hugging Face's logo

Weiming1122
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
 Metrics Community
Weiming1122 commited on
Commit
c21121d
·
1 Parent(s): 73daf80

First Push

Browse files
Files changed (18) hide show
  1. SnowballTarget.onnx +2 -2
  2. SnowballTarget/SnowballTarget-1499800.onnx +3 -0
  3. SnowballTarget/SnowballTarget-1499800.pt +3 -0
  4. SnowballTarget/SnowballTarget-1999800.onnx +3 -0
  5. SnowballTarget/SnowballTarget-1999800.pt +3 -0
  6. SnowballTarget/SnowballTarget-2002000.onnx +3 -0
  7. SnowballTarget/SnowballTarget-2002000.pt +3 -0
  8. SnowballTarget/SnowballTarget-499800.onnx +3 -0
  9. SnowballTarget/SnowballTarget-499800.pt +3 -0
  10. SnowballTarget/SnowballTarget-999800.onnx +3 -0
  11. SnowballTarget/SnowballTarget-999800.pt +3 -0
  12. SnowballTarget/checkpoint.pt +2 -2
  13. SnowballTarget/events.out.tfevents.1703744705.013cfbc1c1fd.1595.0 +3 -0
  14. config.json +1 -1
  15. configuration.yaml +6 -6
  16. run_logs/Player-0.log +16 -16
  17. run_logs/timers.json +176 -176
  18. run_logs/training_status.json +29 -29
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd2dba79d43f01bb26643190830efee007fb702a0e5577e9abccd72a5025af0d
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:950255ca55f381fa34c7b6f6969d854c8dfd3c67d1057a244172aa3a483c5d2f
3
+ size 914755
SnowballTarget/SnowballTarget-1499800.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab0ab123f2ee6001d41490673f6a059abe6d557053e48b5c3be79a292aeecfc5
3
+ size 914755
SnowballTarget/SnowballTarget-1499800.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad5df9418b592424eaef8b3e28c7895651312bc452bab7019c08e017c0d4c0cc
3
+ size 5434534
SnowballTarget/SnowballTarget-1999800.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:950255ca55f381fa34c7b6f6969d854c8dfd3c67d1057a244172aa3a483c5d2f
3
+ size 914755
SnowballTarget/SnowballTarget-1999800.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:062b9c9e85b5273a11e675b3b612c69b86167dc424f214a8354861383a904d02
3
+ size 5434534
SnowballTarget/SnowballTarget-2002000.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:950255ca55f381fa34c7b6f6969d854c8dfd3c67d1057a244172aa3a483c5d2f
3
+ size 914755
SnowballTarget/SnowballTarget-2002000.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc88f8fdd31501ff96b22ad439684b715929ff2a65d8c1a70f64e35115111875
3
+ size 5434534
SnowballTarget/SnowballTarget-499800.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdc33a117505eb9c78c9663f15872548706b4dbb4c1581d363bf2208cba6b0d1
3
+ size 914755
SnowballTarget/SnowballTarget-499800.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:733380eec82c2792c52ce3b1dcb462a8b6260a03d6061be4e59fe85a689daf81
3
+ size 5434379
SnowballTarget/SnowballTarget-999800.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0046cea82e73e5ef68f8448dd945ee494ee9e01c95fc70957331ed488438e87b
3
+ size 914755
SnowballTarget/SnowballTarget-999800.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a389de0c39d65553f78d55cdfb298348f56de65aeb92bb19a76c76f398af6671
3
+ size 5434379
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3f6c82ea38e791c21420195edddd70a81dfe6177856617535df342b3447ee84
3
- size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48b1acd7388f806368b8f40d6186b6b1bcb1b57acb6982cb5d6a206bda9ee726
3
+ size 5433378
SnowballTarget/events.out.tfevents.1703744705.013cfbc1c1fd.1595.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53e47c54ffe29c9d5ade86d4bad145cd26bf05b321dff0bc82189ef91f9ccbc7
3
+ size 39769
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": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 10240, "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": 500000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 3, "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": 2000000, "time_horizon": 256, "summary_freq": 50000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -4,7 +4,7 @@ behaviors:
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
@@ -14,11 +14,11 @@ behaviors:
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
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
23
  memory: null
24
  goal_conditioning_type: hyper
@@ -38,9 +38,9 @@ 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: true
45
  self_play: null
46
  behavioral_cloning: null
 
4
  trainer_type: ppo
5
  hyperparameters:
6
  batch_size: 128
7
+ buffer_size: 10240
8
  learning_rate: 0.0003
9
  beta: 0.005
10
  epsilon: 0.2
 
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
16
  epsilon_schedule: linear
17
+ checkpoint_interval: 500000
18
  network_settings:
19
  normalize: false
20
  hidden_units: 256
21
+ num_layers: 3
22
  vis_encode_type: simple
23
  memory: null
24
  goal_conditioning_type: hyper
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 2000000
42
+ time_horizon: 256
43
+ summary_freq: 50000
44
  threaded: true
45
  self_play: null
46
  behavioral_cloning: null
run_logs/Player-0.log CHANGED
@@ -34,7 +34,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
- - Completed reload, in 0.091 seconds
38
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -45,7 +45,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
45
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
46
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
47
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
48
- UnloadTime: 0.887692 ms
49
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
50
  requesting resize 84 x 84
51
  Setting up 1 worker threads for Enlighten.
@@ -53,7 +53,7 @@ Memory Statistics:
53
  [ALLOC_TEMP_TLS] TLS Allocator
54
  StackAllocators :
55
  [ALLOC_TEMP_MAIN]
56
- Peak usage frame count: [8.0 KB-16.0 KB]: 5368 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
57
  Initial Block Size 4.0 MB
58
  Current Block Size 4.0 MB
59
  Peak Allocated Bytes 2.0 MB
@@ -169,22 +169,22 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 40
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
- Peak usage frame count: [4.0 MB-8.0 MB]: 5460 frames
179
  Requested Block Size 16.0 MB
180
- Peak Block count 1
181
- Peak Allocated memory 6.6 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 5460 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.8 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
@@ -213,13 +213,13 @@ Memory Statistics:
213
  Used Block count 1
214
  Peak Allocated bytes 1.0 MB
215
  [ALLOC_GFX_MAIN]
216
- Peak usage frame count: [32.0 KB-64.0 KB]: 4535 frames, [64.0 KB-128.0 KB]: 925 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 67.7 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 5460 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
@@ -231,13 +231,13 @@ Memory Statistics:
231
  Used Block count 1
232
  Peak Allocated bytes 1.0 MB
233
  [ALLOC_CACHEOBJECTS_MAIN]
234
- Peak usage frame count: [0.5 MB-1.0 MB]: 5460 frames
235
  Requested Block Size 4.0 MB
236
  Peak Block count 1
237
  Peak Allocated memory 0.6 MB
238
  Peak Large allocation bytes 0 B
239
  [ALLOC_CACHEOBJECTS_THREAD]
240
- Peak usage frame count: [0.5 MB-1.0 MB]: 5459 frames, [2.0 MB-4.0 MB]: 1 frames
241
  Requested Block Size 4.0 MB
242
  Peak Block count 1
243
  Peak Allocated memory 2.2 MB
@@ -249,13 +249,13 @@ Memory Statistics:
249
  Used Block count 1
250
  Peak Allocated bytes 1.0 MB
251
  [ALLOC_TYPETREE_MAIN]
252
- Peak usage frame count: [0-1.0 KB]: 5460 frames
253
  Requested Block Size 2.0 MB
254
  Peak Block count 1
255
  Peak Allocated memory 1.0 KB
256
  Peak Large allocation bytes 0 B
257
  [ALLOC_TYPETREE_THREAD]
258
- Peak usage frame count: [1.0 KB-2.0 KB]: 5460 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  Peak Allocated memory 1.7 KB
 
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
+ - Completed reload, in 0.094 seconds
38
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
45
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
46
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
47
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
48
+ UnloadTime: 0.784973 ms
49
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
50
  requesting resize 84 x 84
51
  Setting up 1 worker threads for Enlighten.
 
53
  [ALLOC_TEMP_TLS] TLS Allocator
54
  StackAllocators :
55
  [ALLOC_TEMP_MAIN]
56
+ Peak usage frame count: [8.0 KB-16.0 KB]: 53690 frames, [16.0 KB-32.0 KB]: 910 frames, [2.0 MB-4.0 MB]: 1 frames
57
  Initial Block Size 4.0 MB
58
  Current Block Size 4.0 MB
59
  Peak Allocated Bytes 2.0 MB
 
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
+ Peak main deferred allocation count 45
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
+ Peak usage frame count: [4.0 MB-8.0 MB]: 12791 frames, [8.0 MB-16.0 MB]: 26996 frames, [16.0 MB-32.0 MB]: 14814 frames
179
  Requested Block Size 16.0 MB
180
+ Peak Block count 2
181
+ Peak Allocated memory 24.3 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
+ Peak usage frame count: [16.0 MB-32.0 MB]: 54601 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
  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]: 52658 frames, [64.0 KB-128.0 KB]: 1943 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
+ Peak Allocated memory 66.4 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
+ Peak usage frame count: [32.0 KB-64.0 KB]: 54601 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
 
231
  Used Block count 1
232
  Peak Allocated bytes 1.0 MB
233
  [ALLOC_CACHEOBJECTS_MAIN]
234
+ Peak usage frame count: [0.5 MB-1.0 MB]: 54601 frames
235
  Requested Block Size 4.0 MB
236
  Peak Block count 1
237
  Peak Allocated memory 0.6 MB
238
  Peak Large allocation bytes 0 B
239
  [ALLOC_CACHEOBJECTS_THREAD]
240
+ Peak usage frame count: [0.5 MB-1.0 MB]: 54600 frames, [2.0 MB-4.0 MB]: 1 frames
241
  Requested Block Size 4.0 MB
242
  Peak Block count 1
243
  Peak Allocated memory 2.2 MB
 
249
  Used Block count 1
250
  Peak Allocated bytes 1.0 MB
251
  [ALLOC_TYPETREE_MAIN]
252
+ Peak usage frame count: [0-1.0 KB]: 54601 frames
253
  Requested Block Size 2.0 MB
254
  Peak Block count 1
255
  Peak Allocated memory 1.0 KB
256
  Peak Large allocation bytes 0 B
257
  [ALLOC_TYPETREE_THREAD]
258
+ Peak usage frame count: [1.0 KB-2.0 KB]: 54601 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -2,153 +2,153 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.8669962286949158,
6
- "min": 0.8669962286949158,
7
- "max": 2.869570255279541,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8287.6171875,
12
- "min": 8287.6171875,
13
- "max": 29387.26953125,
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": 12.66847038269043,
30
- "min": 0.45318853855133057,
31
- "max": 12.66847038269043,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2470.351806640625,
36
- "min": 87.9185791015625,
37
- "max": 2574.646484375,
38
- "count": 20
39
  },
40
- "SnowballTarget.Environment.EpisodeLength.mean": {
41
- "value": 199.0,
42
- "min": 199.0,
43
- "max": 199.0,
44
- "count": 20
45
  },
46
- "SnowballTarget.Environment.EpisodeLength.sum": {
47
- "value": 8756.0,
48
- "min": 8756.0,
49
- "max": 10945.0,
50
- "count": 20
 
 
 
 
 
 
 
 
 
 
 
 
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06753355493299965,
54
- "min": 0.06494867389750046,
55
- "max": 0.07367765676691289,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.2701342197319986,
60
- "min": 0.26150085703428727,
61
- "max": 0.3518778981381853,
62
- "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.18394062193293198,
66
- "min": 0.11935577595688622,
67
- "max": 0.3019716292619705,
68
- "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.7357624877317279,
72
- "min": 0.4774231038275449,
73
- "max": 1.349198090095146,
74
- "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 8.082097306000005e-06,
78
- "min": 8.082097306000005e-06,
79
- "max": 0.000291882002706,
80
- "count": 20
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 3.232838922400002e-05,
84
- "min": 3.232838922400002e-05,
85
- "max": 0.00138516003828,
86
- "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.10269400000000001,
90
- "min": 0.10269400000000001,
91
- "max": 0.19729400000000002,
92
- "count": 20
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.41077600000000003,
96
- "min": 0.41077600000000003,
97
- "max": 0.96172,
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": 24.977272727272727,
114
- "min": 3.340909090909091,
115
- "max": 24.977272727272727,
116
- "count": 20
117
- },
118
- "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1099.0,
120
- "min": 147.0,
121
- "max": 1343.0,
122
- "count": 20
123
- },
124
- "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 24.977272727272727,
126
- "min": 3.340909090909091,
127
- "max": 24.977272727272727,
128
- "count": 20
129
- },
130
- "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1099.0,
132
- "min": 147.0,
133
- "max": 1343.0,
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": "1703733181",
152
  "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
153
  "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.1.0.dev0",
@@ -156,59 +156,59 @@
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.1.2+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1703733626"
160
  },
161
- "total": 444.9509761369999,
162
  "count": 1,
163
- "self": 0.4379683639998575,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.053479809999998906,
167
  "count": 1,
168
- "self": 0.053479809999998906
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 444.459527963,
172
  "count": 1,
173
- "self": 0.5459963899983222,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.2033515960000614,
177
  "count": 1,
178
- "self": 3.2033515960000614
179
  },
180
  "TrainerController.advance": {
181
- "total": 440.62231021600155,
182
- "count": 18200,
183
- "self": 0.2626727869825345,
184
  "children": {
185
  "env_step": {
186
- "total": 440.359637429019,
187
- "count": 18200,
188
- "self": 288.21511279604624,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 151.86545625198835,
192
- "count": 18200,
193
- "self": 1.4392349629639511,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 150.4262212890244,
197
- "count": 18200,
198
- "self": 150.4262212890244
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.27906838098442677,
204
- "count": 18200,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 443.3267502729932,
209
- "count": 18200,
210
  "is_parallel": true,
211
- "self": 219.03763023398915,
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": 0.0050096449999728065,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0034699119997867456,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.001539733000186061,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.001539733000186061
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.051181425999971,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0007588099998656617,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00041097300004366843,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00041097300004366843
244
  },
245
  "communicator.exchange": {
246
- "total": 0.04814685999997437,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.04814685999997437
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0018647830000873,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0003552319999471365,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0015095510001401635,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0015095510001401635
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 224.28912003900405,
271
- "count": 18199,
272
  "is_parallel": true,
273
- "self": 10.658013661026985,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.23273210699881,
277
- "count": 18199,
278
  "is_parallel": true,
279
- "self": 5.23273210699881
280
  },
281
  "communicator.exchange": {
282
- "total": 174.956716884961,
283
- "count": 18199,
284
  "is_parallel": true,
285
- "self": 174.956716884961
286
  },
287
  "steps_from_proto": {
288
- "total": 33.441657386017255,
289
- "count": 18199,
290
  "is_parallel": true,
291
- "self": 6.176670708015649,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 27.264986678001605,
295
- "count": 181990,
296
  "is_parallel": true,
297
- "self": 27.264986678001605
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00011886200013577763,
313
  "count": 1,
314
- "self": 0.00011886200013577763,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 435.2241449229941,
324
- "count": 677405,
325
  "is_parallel": true,
326
- "self": 13.744515058067122,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 239.4991322549257,
330
- "count": 677405,
331
  "is_parallel": true,
332
- "self": 238.5485157069255,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 0.9506165480001982,
336
  "count": 4,
337
  "is_parallel": true,
338
- "self": 0.9506165480001982
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 181.9804976100013,
344
- "count": 90,
345
  "is_parallel": true,
346
- "self": 57.51711164299843,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 124.46338596700286,
350
- "count": 4587,
351
  "is_parallel": true,
352
- "self": 124.46338596700286
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.08775089899995692,
364
  "count": 1,
365
- "self": 0.0009682820000307402,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.08678261699992618,
369
  "count": 1,
370
- "self": 0.08678261699992618
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.839410126209259,
6
+ "min": 0.839410126209259,
7
+ "max": 2.844252109527588,
8
+ "count": 40
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 42363.3515625,
12
+ "min": 40732.9296875,
13
+ "max": 144451.03125,
14
+ "count": 40
15
+ },
16
+ "SnowballTarget.Environment.EpisodeLength.mean": {
17
+ "value": 199.0,
18
+ "min": 199.0,
19
+ "max": 199.0,
20
+ "count": 40
21
+ },
22
+ "SnowballTarget.Environment.EpisodeLength.sum": {
23
+ "value": 50347.0,
24
+ "min": 48158.0,
25
+ "max": 52536.0,
26
+ "count": 40
27
  },
28
  "SnowballTarget.Step.mean": {
29
+ "value": 1999800.0,
30
+ "min": 49800.0,
31
+ "max": 1999800.0,
32
+ "count": 40
33
  },
34
  "SnowballTarget.Step.sum": {
35
+ "value": 1999800.0,
36
+ "min": 49800.0,
37
+ "max": 1999800.0,
38
+ "count": 40
39
  },
40
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
41
+ "value": 14.501752853393555,
42
+ "min": 0.5022461414337158,
43
+ "max": 14.501752853393555,
44
+ "count": 40
45
  },
46
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
47
+ "value": 3625.438232421875,
48
+ "min": 125.05929565429688,
49
+ "max": 3625.438232421875,
50
+ "count": 40
51
  },
52
+ "SnowballTarget.Environment.CumulativeReward.mean": {
53
+ "value": 28.388,
54
+ "min": 5.008032128514056,
55
+ "max": 28.448,
56
+ "count": 40
57
  },
58
+ "SnowballTarget.Environment.CumulativeReward.sum": {
59
+ "value": 7097.0,
60
+ "min": 1247.0,
61
+ "max": 7112.0,
62
+ "count": 40
63
+ },
64
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
+ "value": 28.388,
66
+ "min": 5.008032128514056,
67
+ "max": 28.448,
68
+ "count": 40
69
+ },
70
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
+ "value": 7097.0,
72
+ "min": 1247.0,
73
+ "max": 7112.0,
74
+ "count": 40
75
  },
76
  "SnowballTarget.Losses.PolicyLoss.mean": {
77
+ "value": 0.069219311003226,
78
+ "min": 0.0659932713580287,
79
+ "max": 0.0739939942222383,
80
+ "count": 40
81
  },
82
  "SnowballTarget.Losses.PolicyLoss.sum": {
83
+ "value": 0.276877244012904,
84
+ "min": 0.2639730854321148,
85
+ "max": 0.3581072422068817,
86
+ "count": 40
87
  },
88
  "SnowballTarget.Losses.ValueLoss.mean": {
89
+ "value": 0.15687800026407428,
90
+ "min": 0.14771346322836815,
91
+ "max": 0.2919780290740378,
92
+ "count": 40
93
  },
94
  "SnowballTarget.Losses.ValueLoss.sum": {
95
+ "value": 0.6275120010562971,
96
+ "min": 0.6275120010562971,
97
+ "max": 1.3910198542445091,
98
+ "count": 40
99
  },
100
  "SnowballTarget.Policy.LearningRate.mean": {
101
+ "value": 3.825098724999995e-06,
102
+ "min": 3.825098724999995e-06,
103
+ "max": 0.00029587500137499996,
104
+ "count": 40
105
  },
106
  "SnowballTarget.Policy.LearningRate.sum": {
107
+ "value": 1.530039489999998e-05,
108
+ "min": 1.530039489999998e-05,
109
+ "max": 0.0014422500192499998,
110
+ "count": 40
111
  },
112
  "SnowballTarget.Policy.Epsilon.mean": {
113
+ "value": 0.10127499999999999,
114
+ "min": 0.10127499999999999,
115
+ "max": 0.19862500000000005,
116
+ "count": 40
117
  },
118
  "SnowballTarget.Policy.Epsilon.sum": {
119
+ "value": 0.40509999999999996,
120
+ "min": 0.40509999999999996,
121
+ "max": 0.9807500000000001,
122
+ "count": 40
123
  },
124
  "SnowballTarget.Policy.Beta.mean": {
125
+ "value": 7.362249999999992e-05,
126
+ "min": 7.362249999999992e-05,
127
+ "max": 0.0049313875,
128
+ "count": 40
129
  },
130
  "SnowballTarget.Policy.Beta.sum": {
131
+ "value": 0.0002944899999999997,
132
+ "min": 0.0002944899999999997,
133
+ "max": 0.024039425,
134
+ "count": 40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 40
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 40
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1703744704",
152
  "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
153
  "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.1.0.dev0",
 
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.1.2+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1703749228"
160
  },
161
+ "total": 4524.0049186979995,
162
  "count": 1,
163
+ "self": 0.6768422829991323,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.06769795000002432,
167
  "count": 1,
168
+ "self": 0.06769795000002432
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 4523.260378465,
172
  "count": 1,
173
+ "self": 6.153770934033673,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.387389077000023,
177
  "count": 1,
178
+ "self": 3.387389077000023
179
  },
180
  "TrainerController.advance": {
181
+ "total": 4513.5815245649665,
182
+ "count": 182002,
183
+ "self": 2.794995134952842,
184
  "children": {
185
  "env_step": {
186
+ "total": 4510.786529430014,
187
+ "count": 182002,
188
+ "self": 2907.504590901017,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 1600.249445852959,
192
+ "count": 182002,
193
+ "self": 15.010505520020615,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 1585.2389403329385,
197
+ "count": 182002,
198
+ "self": 1585.2389403329385
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 3.032492676037407,
204
+ "count": 182002,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 4511.344607695967,
209
+ "count": 182002,
210
  "is_parallel": true,
211
+ "self": 2199.071089124015,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.004833086000019193,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.003405404999966777,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0014276810000524165,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0014276810000524165
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.0377329269999791,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0007396139999968909,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00040095899998959794,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00040095899998959794
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.034467437999978756,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.034467437999978756
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0021249160000138545,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00041478200006395127,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0017101339999499032,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0017101339999499032
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 2312.273518571952,
271
+ "count": 182001,
272
  "is_parallel": true,
273
+ "self": 110.96179828893128,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 53.66522611495839,
277
+ "count": 182001,
278
  "is_parallel": true,
279
+ "self": 53.66522611495839
280
  },
281
  "communicator.exchange": {
282
+ "total": 1805.0553392249547,
283
+ "count": 182001,
284
  "is_parallel": true,
285
+ "self": 1805.0553392249547
286
  },
287
  "steps_from_proto": {
288
+ "total": 342.5911549431076,
289
+ "count": 182001,
290
  "is_parallel": true,
291
+ "self": 63.7990347122423,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 278.7921202308653,
295
+ "count": 1820010,
296
  "is_parallel": true,
297
+ "self": 278.7921202308653
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.001607125000191445,
313
  "count": 1,
314
+ "self": 0.001607125000191445,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 4457.231079032006,
324
+ "count": 6689180,
325
  "is_parallel": true,
326
+ "self": 142.82890651324124,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 2243.318894835765,
330
+ "count": 6689180,
331
  "is_parallel": true,
332
+ "self": 2242.5206855647652,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 0.7982092709999051,
336
  "count": 4,
337
  "is_parallel": true,
338
+ "self": 0.7982092709999051
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 2071.0832776830002,
344
+ "count": 181,
345
  "is_parallel": true,
346
+ "self": 620.9278815499742,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 1450.155396133026,
350
+ "count": 46161,
351
  "is_parallel": true,
352
+ "self": 1450.155396133026
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.1360867639996286,
364
  "count": 1,
365
+ "self": 0.0017097370000556111,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.134377026999573,
369
  "count": 1,
370
+ "self": 0.134377026999573
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -2,58 +2,58 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 12.636363636363637,
8
- "creation_time": 1703733295.7324486,
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": 1703733407.587789,
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": 23.181818181818183,
26
- "creation_time": 1703733517.5242794,
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": 24.363636363636363,
35
- "creation_time": 1703733625.6377993,
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": 24.363636363636363,
44
- "creation_time": 1703733625.7565851,
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": 24.363636363636363,
54
- "creation_time": 1703733625.7565851,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 499800,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499800.onnx",
7
+ "reward": 26.625,
8
+ "creation_time": 1703745843.0743196,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-499800.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 999800,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-999800.onnx",
16
+ "reward": 27.632653061224488,
17
+ "creation_time": 1703746971.4188666,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-999800.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 1499800,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1499800.onnx",
25
+ "reward": 28.31578947368421,
26
+ "creation_time": 1703748101.412122,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-1499800.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 1999800,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1999800.onnx",
34
+ "reward": 28.75,
35
+ "creation_time": 1703749227.0901036,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-1999800.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 2002000,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-2002000.onnx",
43
+ "reward": 28.927272727272726,
44
+ "creation_time": 1703749227.4071867,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-2002000.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
+ "steps": 2002000,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
+ "reward": 28.927272727272726,
54
+ "creation_time": 1703749227.4071867,
55
  "auxillary_file_paths": [
56
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-2002000.pt"
57
  ]
58
  }
59
  },