Hugging Face's logo

osmancanyuca
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
osmancanyuca commited on
Commit
7d3bbdb
•
1 Parent(s): b9eced2

First Push

Browse files
Files changed (28) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-1000120.onnx +3 -0
  3. SnowballTarget/SnowballTarget-1000120.pt +3 -0
  4. SnowballTarget/SnowballTarget-599976.onnx +3 -0
  5. SnowballTarget/SnowballTarget-599976.pt +3 -0
  6. SnowballTarget/SnowballTarget-649936.onnx +3 -0
  7. SnowballTarget/SnowballTarget-649936.pt +3 -0
  8. SnowballTarget/SnowballTarget-699936.onnx +3 -0
  9. SnowballTarget/SnowballTarget-699936.pt +3 -0
  10. SnowballTarget/SnowballTarget-749960.onnx +3 -0
  11. SnowballTarget/SnowballTarget-749960.pt +3 -0
  12. SnowballTarget/SnowballTarget-799984.onnx +3 -0
  13. SnowballTarget/SnowballTarget-799984.pt +3 -0
  14. SnowballTarget/SnowballTarget-849944.onnx +3 -0
  15. SnowballTarget/SnowballTarget-849944.pt +3 -0
  16. SnowballTarget/SnowballTarget-899944.onnx +3 -0
  17. SnowballTarget/SnowballTarget-899944.pt +3 -0
  18. SnowballTarget/SnowballTarget-949968.onnx +3 -0
  19. SnowballTarget/SnowballTarget-949968.pt +3 -0
  20. SnowballTarget/SnowballTarget-999992.onnx +3 -0
  21. SnowballTarget/SnowballTarget-999992.pt +3 -0
  22. SnowballTarget/checkpoint.pt +1 -1
  23. SnowballTarget/events.out.tfevents.1690891386.7123b5f7e039.7895.0 +3 -0
  24. config.json +1 -1
  25. configuration.yaml +1 -1
  26. run_logs/Player-0.log +13 -13
  27. run_logs/timers.json +161 -161
  28. run_logs/training_status.json +54 -54
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6b368200b8c7fee1be9c1eaf6e61131149588ab22d0b713d749e2f62bc74b94
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52051ae92e3dcdc3c7bce23a2471b3b48b13cd8b229be0ff4239fee35f316df9
3
  size 646532
SnowballTarget/SnowballTarget-1000120.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52051ae92e3dcdc3c7bce23a2471b3b48b13cd8b229be0ff4239fee35f316df9
3
+ size 646532
SnowballTarget/SnowballTarget-1000120.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62ef4b23daefacf8dae92cbb8073878fdf014f3c0e74a18c369a4badbc4b29ae
3
+ size 3843968
SnowballTarget/SnowballTarget-599976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e57ae1c2666bf581d5bc9ab04ffa915625f93b73d8a0489b6d1dc6ba458f1c26
3
+ size 646532
SnowballTarget/SnowballTarget-599976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:124eeab3dd69673dfa77e151579111c7a3fe6c95aa721cf53366a7490597eb9e
3
+ size 3843968
SnowballTarget/SnowballTarget-649936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f305c40d12a8b747a6e27b61aeacf46158cfba947f8038354d7c596e87853a24
3
+ size 646532
SnowballTarget/SnowballTarget-649936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cdc7f0d5295f5acdc07f6d1a8e96537b14c578febbbfe3da3165fd1a23bf967
3
+ size 3843968
SnowballTarget/SnowballTarget-699936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bddf83a4c0962528adcd0bf519f40b79c7240090726742d5c7fb3dd14d5c6db
3
+ size 646532
SnowballTarget/SnowballTarget-699936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aa541ef6436551d24d78a86965362acd90ec4b7a63705619207bec28a8bc314
3
+ size 3843968
SnowballTarget/SnowballTarget-749960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a2f6087fed390d8bfa5ad18900797a9eb87ed8d3477d7e1348076607a894321
3
+ size 646532
SnowballTarget/SnowballTarget-749960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c51a002b08039b86d2c9ae3ac3a598ae31a68f3b698a9dbf3540d1efb8186b76
3
+ size 3843968
SnowballTarget/SnowballTarget-799984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e335293156ced073334a1e7d15d085b46e06f6e96c6cce69ab9f351f47b2193a
3
+ size 646532
SnowballTarget/SnowballTarget-799984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b5f157e30821421346b0968819207508a2d1eeea3610f3548745b6b4f4901fa
3
+ size 3843968
SnowballTarget/SnowballTarget-849944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:897d922ff5a17f973ea785edfacdf26b12106983a8bd39a14bd663e23c657cfb
3
+ size 646532
SnowballTarget/SnowballTarget-849944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29d3de6b72888a4c4a61766ae2cd677243a52e01a223cf866d73ca68b9eaec9b
3
+ size 3843968
SnowballTarget/SnowballTarget-899944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d46419b9cc9d51658338d7f93b8e7ec835dfbca974d46a244ad7c01ac34ddf3
3
+ size 646532
SnowballTarget/SnowballTarget-899944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:735642c872294dcdd3c919dbdb017f20a85248a8b08fd713a907b5b0d34d08c1
3
+ size 3843968
SnowballTarget/SnowballTarget-949968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e66d56bc360f0f022aeef9b47729ab12a6adf378b676403c46529657f4a5fef
3
+ size 646532
SnowballTarget/SnowballTarget-949968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4caddf3d4f478a68d9fabf9d6a9b9ef01e263fbf0a3ef35597fb0248febc12a6
3
+ size 3843968
SnowballTarget/SnowballTarget-999992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52051ae92e3dcdc3c7bce23a2471b3b48b13cd8b229be0ff4239fee35f316df9
3
+ size 646532
SnowballTarget/SnowballTarget-999992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:676153898cf296747c159e5eac14edab148e4bee00dfc8566c985b8e3ff605e1
3
+ size 3843968
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ec70361e0c19d32caa430601219818986ece93339be046809b3d892d385b18b
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62ef4b23daefacf8dae92cbb8073878fdf014f3c0e74a18c369a4badbc4b29ae
3
  size 3843968
SnowballTarget/events.out.tfevents.1690891386.7123b5f7e039.7895.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aa751738739594af9a7751e916d7f2e6394580a79d07c7312264528ea88ad0a
3
+ size 41861
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": 500000, "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, "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": true, "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": 0.0003, "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": 1000000, "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, "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -38,7 +38,7 @@ behaviors:
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
- max_steps: 500000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 1000000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
run_logs/Player-0.log CHANGED
@@ -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: 0.624853 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]: 8047 frames, [16.0 KB-32.0 KB]: 136 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]: 8184 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
- Peak Allocated memory 7.5 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
- Peak usage frame count: [16.0 MB-32.0 MB]: 8184 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
  Peak Allocated memory 17.7 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]: 7926 frames, [64.0 KB-128.0 KB]: 258 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
- Peak Allocated memory 66.0 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
- Peak usage frame count: [32.0 KB-64.0 KB]: 8184 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]: 8184 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]: 8183 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]: 8184 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]: 8184 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
 
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: 0.819935 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]: 13415 frames, [16.0 KB-32.0 KB]: 227 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 37
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]: 11611 frames, [8.0 MB-16.0 MB]: 2032 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 9.6 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 13643 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
  Peak Allocated memory 17.7 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]: 13296 frames, [64.0 KB-128.0 KB]: 347 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]: 13643 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]: 13643 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]: 13642 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]: 13643 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]: 13643 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
@@ -2,153 +2,153 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.49389326572418213,
6
- "min": 0.48974916338920593,
7
- "max": 0.8311858773231506,
8
- "count": 30
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 4780.88671875,
12
- "min": 4665.3505859375,
13
- "max": 8503.03125,
14
- "count": 30
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 499952.0,
18
- "min": 209936.0,
19
- "max": 499952.0,
20
- "count": 30
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 499952.0,
24
- "min": 209936.0,
25
- "max": 499952.0,
26
- "count": 30
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 13.264318466186523,
30
- "min": 12.78330135345459,
31
- "max": 13.550152778625488,
32
- "count": 30
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2705.9208984375,
36
- "min": 2454.393798828125,
37
- "max": 2754.96923828125,
38
- "count": 30
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
- "count": 30
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
- "count": 30
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06444381270489162,
54
- "min": 0.06138828125846225,
55
- "max": 0.07410374682605798,
56
- "count": 30
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.3222190635244581,
60
- "min": 0.245553125033849,
61
- "max": 0.35996163713257284,
62
- "count": 30
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.16523896856050865,
66
- "min": 0.16523896856050865,
67
- "max": 0.20906220627766028,
68
- "count": 30
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.8261948428025433,
72
- "min": 0.6695908378152287,
73
- "max": 1.0453110313883014,
74
- "count": 30
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 3.1056989647999945e-06,
78
- "min": 3.1056989647999945e-06,
79
- "max": 0.00017668564110480002,
80
- "count": 30
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 1.5528494823999972e-05,
84
- "min": 1.5528494823999972e-05,
85
- "max": 0.000853728215424,
86
- "count": 30
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.10103520000000002,
90
- "min": 0.10103520000000002,
91
- "max": 0.15889520000000001,
92
- "count": 30
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.5051760000000001,
96
- "min": 0.4120608,
97
- "max": 0.7845760000000002,
98
- "count": 30
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
- "value": 6.165647999999992e-05,
102
- "min": 6.165647999999992e-05,
103
- "max": 0.002948870480000001,
104
- "count": 30
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.0003082823999999996,
108
- "min": 0.0003082823999999996,
109
- "max": 0.0142503424,
110
- "count": 30
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 26.054545454545455,
114
- "min": 25.01818181818182,
115
- "max": 27.045454545454547,
116
- "count": 30
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1433.0,
120
- "min": 1106.0,
121
- "max": 1460.0,
122
- "count": 30
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 26.054545454545455,
126
- "min": 25.01818181818182,
127
- "max": 27.045454545454547,
128
- "count": 30
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1433.0,
132
- "min": 1106.0,
133
- "max": 1460.0,
134
- "count": 30
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 30
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 30
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1690890343",
152
  "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
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 --resume",
154
  "mlagents_version": "0.31.0.dev0",
@@ -156,59 +156,59 @@
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
- "end_time_seconds": "1690891037"
160
  },
161
- "total": 694.623827245,
162
  "count": 1,
163
- "self": 0.43983715800004575,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.0312753050000083,
167
  "count": 1,
168
- "self": 0.0312753050000083
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 694.152714782,
172
  "count": 1,
173
- "self": 0.7819660919807347,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.913775874999942,
177
  "count": 1,
178
- "self": 3.913775874999942
179
  },
180
  "TrainerController.advance": {
181
- "total": 689.3154025650192,
182
- "count": 27279,
183
- "self": 0.37225476100275046,
184
  "children": {
185
  "env_step": {
186
- "total": 688.9431478040165,
187
- "count": 27279,
188
- "self": 502.8756942400214,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 185.61299342100756,
192
- "count": 27279,
193
- "self": 2.58825859700994,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 183.02473482399762,
197
- "count": 27279,
198
- "self": 183.02473482399762
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.45446014298750015,
204
- "count": 27279,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 691.9716259699957,
209
- "count": 27279,
210
  "is_parallel": true,
211
- "self": 327.18913087799194,
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": 0.0018565589999752774,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.000559727999984716,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0012968309999905614,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0012968309999905614
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03499106699996446,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006187319999071406,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0004812870000705516,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0004812870000705516
244
  },
245
  "communicator.exchange": {
246
- "total": 0.0318589549999615,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.0318589549999615
250
  },
251
  "steps_from_proto": {
252
- "total": 0.00203209300002527,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00048141700005999155,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0015506759999652786,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0015506759999652786
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 364.7824950920037,
271
- "count": 27278,
272
  "is_parallel": true,
273
- "self": 15.603054116971748,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 7.835772952041566,
277
- "count": 27278,
278
  "is_parallel": true,
279
- "self": 7.835772952041566
280
  },
281
  "communicator.exchange": {
282
- "total": 290.0039097430006,
283
- "count": 27278,
284
  "is_parallel": true,
285
- "self": 290.0039097430006
286
  },
287
  "steps_from_proto": {
288
- "total": 51.33975827998984,
289
- "count": 27278,
290
  "is_parallel": true,
291
- "self": 9.260755715980281,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 42.079002564009556,
295
- "count": 272780,
296
  "is_parallel": true,
297
- "self": 42.079002564009556
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00010633400006554439,
313
  "count": 1,
314
- "self": 0.00010633400006554439,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 684.0919438569363,
324
- "count": 623524,
325
  "is_parallel": true,
326
- "self": 13.70914407186956,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 367.81647221106573,
330
- "count": 623524,
331
  "is_parallel": true,
332
- "self": 366.1795820880658,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 1.6368901229999437,
336
- "count": 6,
337
  "is_parallel": true,
338
- "self": 1.6368901229999437
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 302.566327574001,
344
- "count": 136,
345
  "is_parallel": true,
346
- "self": 122.20453180500476,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 180.36179576899622,
350
- "count": 6930,
351
  "is_parallel": true,
352
- "self": 180.36179576899622
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.14146391600002062,
364
  "count": 1,
365
- "self": 0.0010155050001685595,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.14044841099985206,
369
  "count": 1,
370
- "self": 0.14044841099985206
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.4204990863800049,
6
+ "min": 0.41473114490509033,
7
+ "max": 0.5147774815559387,
8
+ "count": 50
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 4061.18017578125,
12
+ "min": 4042.697265625,
13
+ "max": 5294.486328125,
14
+ "count": 50
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 999992.0,
18
+ "min": 509968.0,
19
+ "max": 999992.0,
20
+ "count": 50
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 999992.0,
24
+ "min": 509968.0,
25
+ "max": 999992.0,
26
+ "count": 50
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.856378555297852,
30
+ "min": 13.292767524719238,
31
+ "max": 13.918790817260742,
32
+ "count": 50
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2840.5576171875,
36
+ "min": 2578.796875,
37
+ "max": 2853.35205078125,
38
+ "count": 50
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 50
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 50
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.0718381038335079,
54
+ "min": 0.05937582174697038,
55
+ "max": 0.07631100223380581,
56
+ "count": 50
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.3591905191675395,
60
+ "min": 0.2375032869878815,
61
+ "max": 0.38155501116902907,
62
+ "count": 50
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.1773360082916185,
66
+ "min": 0.1512796406652413,
67
+ "max": 0.19390156032407985,
68
+ "count": 50
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.8866800414580925,
72
+ "min": 0.6522421940576797,
73
+ "max": 0.9695078016203992,
74
+ "count": 50
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 1.521699492799996e-06,
78
+ "min": 1.521699492799996e-06,
79
+ "max": 0.0001483716505428,
80
+ "count": 50
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 7.60849746399998e-06,
84
+ "min": 7.60849746399998e-06,
85
+ "max": 0.0007270082576640001,
86
+ "count": 50
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10050719999999999,
90
+ "min": 0.10050719999999999,
91
+ "max": 0.1494572,
92
+ "count": 50
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.502536,
96
+ "min": 0.40598880000000004,
97
+ "max": 0.7423360000000001,
98
+ "count": 50
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 3.530927999999995e-05,
102
+ "min": 3.530927999999995e-05,
103
+ "max": 0.0024779142800000005,
104
+ "count": 50
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.00017654639999999973,
108
+ "min": 0.00017654639999999973,
109
+ "max": 0.0121425664,
110
+ "count": 50
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 27.054545454545455,
114
+ "min": 25.65909090909091,
115
+ "max": 27.5,
116
+ "count": 50
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1488.0,
120
+ "min": 1129.0,
121
+ "max": 1503.0,
122
+ "count": 50
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 27.054545454545455,
126
+ "min": 25.65909090909091,
127
+ "max": 27.5,
128
+ "count": 50
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1488.0,
132
+ "min": 1129.0,
133
+ "max": 1503.0,
134
+ "count": 50
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 50
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 50
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1690891385",
152
  "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
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 --resume",
154
  "mlagents_version": "0.31.0.dev0",
 
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
+ "end_time_seconds": "1690892546"
160
  },
161
+ "total": 1160.662677215,
162
  "count": 1,
163
+ "self": 0.4239330450000125,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.03380916800006162,
167
  "count": 1,
168
+ "self": 0.03380916800006162
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 1160.204935002,
172
  "count": 1,
173
+ "self": 1.3026766430307362,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.896834601000137,
177
  "count": 1,
178
+ "self": 3.896834601000137
179
  },
180
  "TrainerController.advance": {
181
+ "total": 1154.8614462209687,
182
+ "count": 45476,
183
+ "self": 0.6355414419135741,
184
  "children": {
185
  "env_step": {
186
+ "total": 1154.225904779055,
187
+ "count": 45476,
188
+ "self": 836.7392049760897,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 316.8335550379654,
192
+ "count": 45476,
193
+ "self": 4.2225153679412415,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 312.6110396700242,
197
+ "count": 45476,
198
+ "self": 312.6110396700242
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.6531447649999791,
204
+ "count": 45476,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 1156.4292470499945,
209
+ "count": 45476,
210
  "is_parallel": true,
211
+ "self": 549.7946691019188,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.001821205000169357,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0005339730000741838,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0012872320000951731,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0012872320000951731
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.03880305200004841,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006078620001517265,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004058579997945344,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004058579997945344
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03573670800005857,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03573670800005857
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.002052624000043579,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0004982790001122339,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0015543449999313452,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0015543449999313452
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 606.6345779480757,
271
+ "count": 45475,
272
  "is_parallel": true,
273
+ "self": 25.990496037154344,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 12.880096801027548,
277
+ "count": 45475,
278
  "is_parallel": true,
279
+ "self": 12.880096801027548
280
  },
281
  "communicator.exchange": {
282
+ "total": 481.7465131599515,
283
+ "count": 45475,
284
  "is_parallel": true,
285
+ "self": 481.7465131599515
286
  },
287
  "steps_from_proto": {
288
+ "total": 86.01747194994232,
289
+ "count": 45475,
290
  "is_parallel": true,
291
+ "self": 15.769068050099577,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 70.24840389984274,
295
+ "count": 454750,
296
  "is_parallel": true,
297
+ "self": 70.24840389984274
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.00013637900019602966,
313
  "count": 1,
314
+ "self": 0.00013637900019602966,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 1145.7589073039617,
324
+ "count": 1062056,
325
  "is_parallel": true,
326
+ "self": 23.823828691894278,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 615.1835517040679,
330
+ "count": 1062056,
331
  "is_parallel": true,
332
+ "self": 611.9219108580676,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 3.2616408460003186,
336
+ "count": 10,
337
  "is_parallel": true,
338
+ "self": 3.2616408460003186
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 506.7515269079995,
344
+ "count": 227,
345
  "is_parallel": true,
346
+ "self": 204.23789698899714,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 302.51362991900237,
350
+ "count": 11571,
351
  "is_parallel": true,
352
+ "self": 302.51362991900237
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.1438411580002139,
364
  "count": 1,
365
+ "self": 0.001152744000137318,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.1426884140000766,
369
  "count": 1,
370
+ "self": 0.1426884140000766
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -2,103 +2,103 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 149984,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
7
- "reward": 22.90909090909091,
8
- "creation_time": 1690890202.6211483,
9
  "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
11
  ]
12
  },
13
  {
14
- "steps": 199984,
15
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
16
- "reward": 24.90909090909091,
17
- "creation_time": 1690890317.6469834,
18
  "auxillary_file_paths": [
19
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
20
  ]
21
  },
22
  {
23
- "steps": 200112,
24
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
25
- "reward": 24.90909090909091,
26
- "creation_time": 1690890317.8116348,
27
  "auxillary_file_paths": [
28
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
29
  ]
30
  },
31
  {
32
- "steps": 249984,
33
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.onnx",
34
- "reward": 25.545454545454547,
35
- "creation_time": 1690890462.0969536,
36
  "auxillary_file_paths": [
37
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.pt"
38
  ]
39
  },
40
  {
41
- "steps": 299944,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.onnx",
43
- "reward": 25.454545454545453,
44
- "creation_time": 1690890576.445724,
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.pt"
47
  ]
48
  },
49
  {
50
- "steps": 349968,
51
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349968.onnx",
52
- "reward": 27.09090909090909,
53
- "creation_time": 1690890692.7718558,
54
  "auxillary_file_paths": [
55
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-349968.pt"
56
  ]
57
  },
58
  {
59
- "steps": 399968,
60
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.onnx",
61
- "reward": 25.272727272727273,
62
- "creation_time": 1690890806.5998008,
63
  "auxillary_file_paths": [
64
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.pt"
65
  ]
66
  },
67
  {
68
- "steps": 449992,
69
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449992.onnx",
70
- "reward": 27.727272727272727,
71
- "creation_time": 1690890922.4949217,
72
  "auxillary_file_paths": [
73
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-449992.pt"
74
  ]
75
  },
76
  {
77
- "steps": 499952,
78
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499952.onnx",
79
- "reward": 25.272727272727273,
80
- "creation_time": 1690891037.270085,
81
  "auxillary_file_paths": [
82
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-499952.pt"
83
  ]
84
  },
85
  {
86
- "steps": 500016,
87
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-500016.onnx",
88
- "reward": 25.272727272727273,
89
- "creation_time": 1690891037.4329965,
90
  "auxillary_file_paths": [
91
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-500016.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
- "steps": 500016,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
- "reward": 25.272727272727273,
99
- "creation_time": 1690891037.4329965,
100
  "auxillary_file_paths": [
101
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-500016.pt"
102
  ]
103
  }
104
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 599976,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-599976.onnx",
7
+ "reward": 27.272727272727273,
8
+ "creation_time": 1690891620.1450253,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-599976.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 649936,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-649936.onnx",
16
+ "reward": 26.90909090909091,
17
+ "creation_time": 1690891736.4502091,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-649936.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 699936,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-699936.onnx",
25
+ "reward": 26.363636363636363,
26
+ "creation_time": 1690891850.2111454,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-699936.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 749960,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-749960.onnx",
34
+ "reward": 26.818181818181817,
35
+ "creation_time": 1690891967.2421336,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-749960.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 799984,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-799984.onnx",
43
+ "reward": 27.454545454545453,
44
+ "creation_time": 1690892083.7017183,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-799984.pt"
47
  ]
48
  },
49
  {
50
+ "steps": 849944,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-849944.onnx",
52
+ "reward": 27.454545454545453,
53
+ "creation_time": 1690892199.3065507,
54
  "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-849944.pt"
56
  ]
57
  },
58
  {
59
+ "steps": 899944,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-899944.onnx",
61
+ "reward": 26.454545454545453,
62
+ "creation_time": 1690892314.5531464,
63
  "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-899944.pt"
65
  ]
66
  },
67
  {
68
+ "steps": 949968,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-949968.onnx",
70
+ "reward": 26.363636363636363,
71
+ "creation_time": 1690892429.9747906,
72
  "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-949968.pt"
74
  ]
75
  },
76
  {
77
+ "steps": 999992,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-999992.onnx",
79
+ "reward": 26.90909090909091,
80
+ "creation_time": 1690892545.8202746,
81
  "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-999992.pt"
83
  ]
84
  },
85
  {
86
+ "steps": 1000120,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000120.onnx",
88
+ "reward": 26.90909090909091,
89
+ "creation_time": 1690892545.9912167,
90
  "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000120.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 1000120,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 26.90909090909091,
99
+ "creation_time": 1690892545.9912167,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000120.pt"
102
  ]
103
  }
104
  },