Hugging Face's logo

tux
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
tux commited on
Commit
9fec05b
·
1 Parent(s): 68c582e

Second Push

Browse files
Files changed (26) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-449944.onnx +3 -0
  3. SnowballTarget/SnowballTarget-449944.pt +3 -0
  4. SnowballTarget/SnowballTarget-499968.onnx +3 -0
  5. SnowballTarget/SnowballTarget-499968.pt +3 -0
  6. SnowballTarget/SnowballTarget-549992.onnx +3 -0
  7. SnowballTarget/SnowballTarget-549992.pt +3 -0
  8. SnowballTarget/SnowballTarget-599992.onnx +3 -0
  9. SnowballTarget/SnowballTarget-599992.pt +3 -0
  10. SnowballTarget/SnowballTarget-649952.onnx +3 -0
  11. SnowballTarget/SnowballTarget-649952.pt +3 -0
  12. SnowballTarget/SnowballTarget-699976.onnx +3 -0
  13. SnowballTarget/SnowballTarget-699976.pt +3 -0
  14. SnowballTarget/SnowballTarget-749936.onnx +3 -0
  15. SnowballTarget/SnowballTarget-749936.pt +3 -0
  16. SnowballTarget/SnowballTarget-799936.onnx +3 -0
  17. SnowballTarget/SnowballTarget-799936.pt +3 -0
  18. SnowballTarget/SnowballTarget-800448.onnx +3 -0
  19. SnowballTarget/SnowballTarget-800448.pt +3 -0
  20. SnowballTarget/checkpoint.pt +1 -1
  21. SnowballTarget/events.out.tfevents.1687089783.0fd2ca80588f.19260.0 +3 -0
  22. config.json +1 -1
  23. configuration.yaml +2 -2
  24. run_logs/Player-0.log +14 -14
  25. run_logs/timers.json +161 -161
  26. 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 sha256:0eb32c4466e2e06c75fab8f8173c2785bde57043bd64d122cd82c03cb86b0986
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:770d5d9223726b508d919e870f1b88b44fdacfa5efcba9506c96fdbc8facba0d
3
  size 646532
SnowballTarget/SnowballTarget-449944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6e7e139a970ef3d9713b5a93eafaddf4ba98baea70317aef5bc5b856a027723
3
+ size 646532
SnowballTarget/SnowballTarget-449944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6170b243a6d551e6a9162d8cc12bd06eed9cabe467a2eca0bc3280211dd56e0a
3
+ size 3843968
SnowballTarget/SnowballTarget-499968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00118e6bf35f7c4b26f0631446688ba401b51c38e1ea59e3f24d81e4f324bda1
3
+ size 646532
SnowballTarget/SnowballTarget-499968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f420ff10335c04fa5fa5347176668ed8526333ffe0da2289d0a4c569a4e3e4b
3
+ size 3843968
SnowballTarget/SnowballTarget-549992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5da67ead4ee9474ac043713fe384ec270d9b10ce119fa02fa1be1f024a14f19c
3
+ size 646532
SnowballTarget/SnowballTarget-549992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb14fb2c66cd92a9e10b0c87dc016402ca29148cc55c30e3070df4d2fd13815b
3
+ size 3843968
SnowballTarget/SnowballTarget-599992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ffdf7e2bee2a7393b58475f5765e1d5be1889ea6b5e866f5dbb4346f9f9d897
3
+ size 646532
SnowballTarget/SnowballTarget-599992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d4813b4a68cfe65167f651f4c2a4f1fc0459199ce5a10f4ee8d52763b09c644
3
+ size 3843968
SnowballTarget/SnowballTarget-649952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:405f9d79bea0de7c2715144062a0e9c8b9834bcc6de0ced56b1d29d0c7a0298b
3
+ size 646532
SnowballTarget/SnowballTarget-649952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bae2e1948540cb53eca3746566c22eaad7543b5d5f499d232d57755aea36eb77
3
+ size 3843968
SnowballTarget/SnowballTarget-699976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f2cb7ea18ebc08572b6b40ae4f2db803ac1809f6b7365df4e6add3b7816c766
3
+ size 646532
SnowballTarget/SnowballTarget-699976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f7df4464cf09fbafc777438d5ad658cecc4ea49728896da2ff71267f60060c0
3
+ size 3843968
SnowballTarget/SnowballTarget-749936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b33504005068a79ca86a1ad9af82a3025adba1bfe9e430bc3064c87b2d2a576
3
+ size 646532
SnowballTarget/SnowballTarget-749936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af3b163fe4401a9b2a83f78c0edd9ced65af86a8f76faf41d7ca3ea777f8525b
3
+ size 3843968
SnowballTarget/SnowballTarget-799936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:770d5d9223726b508d919e870f1b88b44fdacfa5efcba9506c96fdbc8facba0d
3
+ size 646532
SnowballTarget/SnowballTarget-799936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:502832056fc0f256d3183b807ef8c92e2533ff8ca28e5f985313da90d1423399
3
+ size 3843968
SnowballTarget/SnowballTarget-800448.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:770d5d9223726b508d919e870f1b88b44fdacfa5efcba9506c96fdbc8facba0d
3
+ size 646532
SnowballTarget/SnowballTarget-800448.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c084811969b4f47c5a7f379eb292ef8e30a1b7cf0252a55280cfc5249366b41
3
+ size 3843968
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52958a0b24c1b0b79a881d37d9c3e1978bf5c97e621918b046d3c3c05d355177
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c084811969b4f47c5a7f379eb292ef8e30a1b7cf0252a55280cfc5249366b41
3
  size 3843968
SnowballTarget/events.out.tfevents.1687089783.0fd2ca80588f.19260.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a55265959d0379b0c52810796c06978f688f558affead412e5aa482d7401ab00
3
+ size 34074
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": 400000, "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": 0.0001, "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": 800000, "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
@@ -5,7 +5,7 @@ behaviors:
5
  hyperparameters:
6
  batch_size: 128
7
  buffer_size: 2048
8
- learning_rate: 0.0003
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
@@ -38,7 +38,7 @@ behaviors:
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
- max_steps: 400000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
 
5
  hyperparameters:
6
  batch_size: 128
7
  buffer_size: 2048
8
+ learning_rate: 0.0001
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 800000
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: 0.837779 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]: 3487 frames, [16.0 KB-32.0 KB]: 59 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
@@ -166,22 +166,22 @@ Memory Statistics:
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
- Peak main deferred allocation count 34
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]: 3547 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
- Peak Allocated memory 6.1 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
- Peak usage frame count: [16.0 MB-32.0 MB]: 3547 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
- Peak Allocated memory 17.7 MB
185
  Peak Large allocation bytes 16.0 MB
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 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]: 3441 frames, [64.0 KB-128.0 KB]: 106 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]: 3547 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]: 3547 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]: 3546 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]: 3547 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]: 3547 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: 0.842931 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]: 10738 frames, [16.0 KB-32.0 KB]: 182 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 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]: 9840 frames, [8.0 MB-16.0 MB]: 1081 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 8.7 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 10921 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.4 MB
185
  Peak Large allocation bytes 16.0 MB
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
 
210
  Used Block count 1
211
  Peak Allocated bytes 1.0 MB
212
  [ALLOC_GFX_MAIN]
213
+ Peak usage frame count: [32.0 KB-64.0 KB]: 10590 frames, [64.0 KB-128.0 KB]: 331 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]: 10921 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]: 10921 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]: 10920 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]: 10921 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]: 10921 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": 0.6749759912490845,
6
- "min": 0.6749759912490845,
7
- "max": 0.8381103873252869,
8
- "count": 13
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 6459.5205078125,
12
- "min": 6459.5205078125,
13
- "max": 8555.4306640625,
14
- "count": 13
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 399944.0,
18
- "min": 279992.0,
19
- "max": 399944.0,
20
- "count": 13
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 399944.0,
24
- "min": 279992.0,
25
- "max": 399944.0,
26
- "count": 13
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.998022079467773,
30
- "min": 12.612207412719727,
31
- "max": 13.121735572814941,
32
- "count": 13
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2521.6162109375,
36
- "min": 2397.19091796875,
37
- "max": 2676.833984375,
38
- "count": 13
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
- "count": 13
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 8756.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
- "count": 13
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06842379256248059,
54
- "min": 0.06274938085330445,
55
- "max": 0.07379341599087497,
56
- "count": 13
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.27369517024992235,
60
- "min": 0.2530691640870417,
61
- "max": 0.36896707995437483,
62
- "count": 13
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.19016173211675066,
66
- "min": 0.18351931782329783,
67
- "max": 0.2117971901800118,
68
- "count": 13
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.7606469284670027,
72
- "min": 0.7515429112256742,
73
- "max": 1.058985950900059,
74
- "count": 13
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 4.0230986590000025e-06,
78
- "min": 4.0230986590000025e-06,
79
- "max": 9.312306895899999e-05,
80
- "count": 13
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 1.609239463600001e-05,
84
- "min": 1.609239463600001e-05,
85
- "max": 0.0003954903681699999,
86
- "count": 13
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.10134100000000001,
90
- "min": 0.10134100000000001,
91
- "max": 0.13104100000000002,
92
- "count": 13
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.40536400000000006,
96
- "min": 0.40536400000000006,
97
- "max": 0.63183,
98
- "count": 13
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
- "value": 7.691590000000003e-05,
102
- "min": 7.691590000000003e-05,
103
- "max": 0.0015589459000000005,
104
- "count": 13
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.0003076636000000001,
108
- "min": 0.0003076636000000001,
109
- "max": 0.006628317,
110
- "count": 13
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.681818181818183,
114
- "min": 24.454545454545453,
115
- "max": 26.022727272727273,
116
- "count": 13
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1130.0,
120
- "min": 1076.0,
121
- "max": 1423.0,
122
- "count": 13
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.681818181818183,
126
- "min": 24.454545454545453,
127
- "max": 26.022727272727273,
128
- "count": 13
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1130.0,
132
- "min": 1076.0,
133
- "max": 1423.0,
134
- "count": 13
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 13
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 13
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1687089213",
152
  "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
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 --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": "1687089515"
160
  },
161
- "total": 302.4342371169996,
162
  "count": 1,
163
- "self": 0.8387473499997213,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.06620121099967946,
167
  "count": 1,
168
- "self": 0.06620121099967946
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 301.5292885560002,
172
  "count": 1,
173
- "self": 0.3744299729842169,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 4.302400324000246,
177
  "count": 1,
178
- "self": 4.302400324000246
179
  },
180
  "TrainerController.advance": {
181
- "total": 296.62832749101517,
182
- "count": 11821,
183
- "self": 0.16391955803783276,
184
  "children": {
185
  "env_step": {
186
- "total": 296.46440793297734,
187
- "count": 11821,
188
- "self": 218.3596087559531,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 77.9404431580283,
192
- "count": 11821,
193
- "self": 1.2103973100033727,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 76.73004584802493,
197
- "count": 11821,
198
- "self": 76.73004584802493
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.16435601899593166,
204
- "count": 11821,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 300.37892925197,
209
- "count": 11821,
210
  "is_parallel": true,
211
- "self": 142.82830187891295,
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": 0.003400146999865683,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0007431369999721937,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0026570099998934893,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0026570099998934893
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.04434941599993181,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0005497960000866442,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00032860099963727407,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00032860099963727407
244
  },
245
  "communicator.exchange": {
246
- "total": 0.041253743000197574,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.041253743000197574
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0022172760000103153,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0004083720004928182,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0018089039995174971,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0018089039995174971
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 157.55062737305707,
271
- "count": 11820,
272
  "is_parallel": true,
273
- "self": 6.540792842022256,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 3.3528731100345794,
277
- "count": 11820,
278
  "is_parallel": true,
279
- "self": 3.3528731100345794
280
  },
281
  "communicator.exchange": {
282
- "total": 125.86504411401711,
283
- "count": 11820,
284
  "is_parallel": true,
285
- "self": 125.86504411401711
286
  },
287
  "steps_from_proto": {
288
- "total": 21.791917306983123,
289
- "count": 11820,
290
  "is_parallel": true,
291
- "self": 3.9140963719200954,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 17.877820935063028,
295
- "count": 118200,
296
  "is_parallel": true,
297
- "self": 17.877820935063028
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00018013600038102595,
313
  "count": 1,
314
- "self": 0.00018013600038102595,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 294.4034886741424,
324
- "count": 275822,
325
  "is_parallel": true,
326
- "self": 6.150136907125216,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 160.87285804101384,
330
- "count": 275822,
331
  "is_parallel": true,
332
- "self": 159.30715024501342,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 1.5657077960004244,
336
- "count": 3,
337
  "is_parallel": true,
338
- "self": 1.5657077960004244
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 127.38049372600335,
344
- "count": 58,
345
  "is_parallel": true,
346
- "self": 49.78196640102624,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 77.59852732497711,
350
- "count": 2955,
351
  "is_parallel": true,
352
- "self": 77.59852732497711
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.2239506320001965,
364
  "count": 1,
365
- "self": 0.0018281009997735964,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.2221225310004229,
369
  "count": 1,
370
- "self": 0.2221225310004229
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.5968165993690491,
6
+ "min": 0.5571640729904175,
7
+ "max": 0.6767531037330627,
8
+ "count": 40
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 6059.47900390625,
12
+ "min": 5325.931640625,
13
+ "max": 6923.18408203125,
14
+ "count": 40
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 799936.0,
18
+ "min": 409960.0,
19
+ "max": 799936.0,
20
+ "count": 40
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 799936.0,
24
+ "min": 409960.0,
25
+ "max": 799936.0,
26
+ "count": 40
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.41425609588623,
30
+ "min": 13.004890441894531,
31
+ "max": 13.57406234741211,
32
+ "count": 40
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2602.36572265625,
36
+ "min": 2496.93896484375,
37
+ "max": 2773.11474609375,
38
+ "count": 40
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 40
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 8756.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 40
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.061910159999635936,
54
+ "min": 0.061336681612666845,
55
+ "max": 0.07427937125746623,
56
+ "count": 40
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.24764063999854374,
60
+ "min": 0.2468815198483165,
61
+ "max": 0.3713968562873311,
62
+ "count": 40
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.19015458178724728,
66
+ "min": 0.17026756718462588,
67
+ "max": 0.21914647823455286,
68
+ "count": 40
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.7606183271489891,
72
+ "min": 0.6810702687385035,
73
+ "max": 1.0957323911727643,
74
+ "count": 40
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 6.315993685000017e-07,
78
+ "min": 6.315993685000017e-07,
79
+ "max": 4.93065506935e-05,
80
+ "count": 40
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 2.526397474000007e-06,
84
+ "min": 2.526397474000007e-06,
85
+ "max": 0.00024034525965500002,
86
+ "count": 40
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.1006315,
90
+ "min": 0.1006315,
91
+ "max": 0.14930650000000004,
92
+ "count": 40
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.402526,
96
+ "min": 0.402526,
97
+ "max": 0.7403449999999999,
98
+ "count": 40
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 4.151185000000009e-05,
102
+ "min": 4.151185000000009e-05,
103
+ "max": 0.0024703943500000002,
104
+ "count": 40
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.00016604740000000036,
108
+ "min": 0.00016604740000000036,
109
+ "max": 0.012043215500000001,
110
+ "count": 40
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 26.227272727272727,
114
+ "min": 25.40909090909091,
115
+ "max": 26.931818181818183,
116
+ "count": 40
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1154.0,
120
+ "min": 1118.0,
121
+ "max": 1466.0,
122
+ "count": 40
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 26.227272727272727,
126
+ "min": 25.40909090909091,
127
+ "max": 26.931818181818183,
128
+ "count": 40
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1154.0,
132
+ "min": 1118.0,
133
+ "max": 1466.0,
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": "1687089782",
152
  "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
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 --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": "1687090700"
160
  },
161
+ "total": 918.2208542879998,
162
  "count": 1,
163
+ "self": 0.43315540999992663,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.06538150100004714,
167
  "count": 1,
168
+ "self": 0.06538150100004714
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 917.7223173769999,
172
  "count": 1,
173
+ "self": 1.0854520769435112,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 4.475140212000042,
177
  "count": 1,
178
+ "self": 4.475140212000042
179
  },
180
  "TrainerController.advance": {
181
+ "total": 912.0262006520552,
182
+ "count": 36403,
183
+ "self": 0.5186194420703032,
184
  "children": {
185
  "env_step": {
186
+ "total": 911.5075812099849,
187
+ "count": 36403,
188
+ "self": 661.585453451039,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 249.4243560518662,
192
+ "count": 36403,
193
+ "self": 3.537187362854638,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 245.88716868901156,
197
+ "count": 36403,
198
+ "self": 245.88716868901156
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.49777170707966434,
204
+ "count": 36403,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 914.748001949014,
209
+ "count": 36403,
210
  "is_parallel": true,
211
+ "self": 431.38485729802323,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0030115030003798893,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0008040019993131864,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.002207501001066703,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.002207501001066703
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.04861170599997422,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006083189991841209,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0003593700002966216,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0003593700002966216
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.04547960800027795,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.04547960800027795
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.002164409000215528,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0003751030008061207,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0017893059994094074,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0017893059994094074
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 483.36314465099076,
271
+ "count": 36402,
272
  "is_parallel": true,
273
+ "self": 20.174957186999563,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 10.086550404983427,
277
+ "count": 36402,
278
  "is_parallel": true,
279
+ "self": 10.086550404983427
280
  },
281
  "communicator.exchange": {
282
+ "total": 385.741071097068,
283
+ "count": 36402,
284
  "is_parallel": true,
285
+ "self": 385.741071097068
286
  },
287
  "steps_from_proto": {
288
+ "total": 67.36056596193976,
289
+ "count": 36402,
290
  "is_parallel": true,
291
+ "self": 12.244435754751066,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 55.11613020718869,
295
+ "count": 364020,
296
  "is_parallel": true,
297
+ "self": 55.11613020718869
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.0003044640006919508,
313
  "count": 1,
314
+ "self": 0.0003044640006919508,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 904.3236935601626,
324
+ "count": 857395,
325
  "is_parallel": true,
326
+ "self": 20.16862705125277,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 491.96500578791256,
330
+ "count": 857395,
331
  "is_parallel": true,
332
+ "self": 489.68250432491277,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 2.2825014629997895,
336
+ "count": 8,
337
  "is_parallel": true,
338
+ "self": 2.2825014629997895
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 392.1900607209973,
344
+ "count": 181,
345
  "is_parallel": true,
346
+ "self": 149.23636622900904,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 242.95369449198824,
350
+ "count": 9228,
351
  "is_parallel": true,
352
+ "self": 242.95369449198824
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.1352199720004137,
364
  "count": 1,
365
+ "self": 0.0010199400003330084,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.13420003200008068,
369
  "count": 1,
370
+ "self": 0.13420003200008068
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": 22.818181818181817,
8
- "creation_time": 1687085979.7950647,
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": 24.272727272727273,
17
- "creation_time": 1687086101.357253,
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": 24.272727272727273,
26
- "creation_time": 1687086101.5429204,
27
  "auxillary_file_paths": [
28
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
29
  ]
30
  },
31
  {
32
- "steps": 200112,
33
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
34
- "reward": null,
35
- "creation_time": 1687088971.5190713,
36
  "auxillary_file_paths": [
37
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
38
  ]
39
  },
40
  {
41
- "steps": 249984,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.onnx",
43
- "reward": 23.636363636363637,
44
- "creation_time": 1687089134.6237562,
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.pt"
47
  ]
48
  },
49
  {
50
- "steps": 270424,
51
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-270424.onnx",
52
- "reward": null,
53
- "creation_time": 1687089187.0483046,
54
  "auxillary_file_paths": [
55
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-270424.pt"
56
  ]
57
  },
58
  {
59
- "steps": 299984,
60
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299984.onnx",
61
- "reward": 24.90909090909091,
62
- "creation_time": 1687089286.8308792,
63
  "auxillary_file_paths": [
64
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-299984.pt"
65
  ]
66
  },
67
  {
68
- "steps": 349944,
69
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349944.onnx",
70
- "reward": 26.454545454545453,
71
- "creation_time": 1687089401.55398,
72
  "auxillary_file_paths": [
73
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-349944.pt"
74
  ]
75
  },
76
  {
77
- "steps": 399944,
78
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399944.onnx",
79
- "reward": 25.545454545454547,
80
- "creation_time": 1687089514.595855,
81
  "auxillary_file_paths": [
82
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-399944.pt"
83
  ]
84
  },
85
  {
86
- "steps": 400136,
87
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-400136.onnx",
88
- "reward": 25.545454545454547,
89
- "creation_time": 1687089514.8510673,
90
  "auxillary_file_paths": [
91
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-400136.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
- "steps": 400136,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
- "reward": 25.545454545454547,
99
- "creation_time": 1687089514.8510673,
100
  "auxillary_file_paths": [
101
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-400136.pt"
102
  ]
103
  }
104
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 400136,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-400136.onnx",
7
+ "reward": 25.545454545454547,
8
+ "creation_time": 1687089514.8510673,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-400136.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 449944,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449944.onnx",
16
+ "reward": 26.545454545454547,
17
+ "creation_time": 1687089901.4305108,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-449944.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 499968,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499968.onnx",
25
+ "reward": 25.545454545454547,
26
+ "creation_time": 1687090015.7021675,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-499968.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 549992,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-549992.onnx",
34
+ "reward": 25.181818181818183,
35
+ "creation_time": 1687090129.1450574,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-549992.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 599992,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-599992.onnx",
43
+ "reward": 27.727272727272727,
44
+ "creation_time": 1687090242.2976713,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-599992.pt"
47
  ]
48
  },
49
  {
50
+ "steps": 649952,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-649952.onnx",
52
+ "reward": 26.363636363636363,
53
+ "creation_time": 1687090355.535074,
54
  "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-649952.pt"
56
  ]
57
  },
58
  {
59
+ "steps": 699976,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-699976.onnx",
61
+ "reward": 26.636363636363637,
62
+ "creation_time": 1687090470.7309177,
63
  "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-699976.pt"
65
  ]
66
  },
67
  {
68
+ "steps": 749936,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-749936.onnx",
70
+ "reward": 25.09090909090909,
71
+ "creation_time": 1687090585.101098,
72
  "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-749936.pt"
74
  ]
75
  },
76
  {
77
+ "steps": 799936,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-799936.onnx",
79
+ "reward": 26.272727272727273,
80
+ "creation_time": 1687090700.1685355,
81
  "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-799936.pt"
83
  ]
84
  },
85
  {
86
+ "steps": 800448,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-800448.onnx",
88
+ "reward": 26.272727272727273,
89
+ "creation_time": 1687090700.3607516,
90
  "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-800448.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 800448,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 26.272727272727273,
99
+ "creation_time": 1687090700.3607516,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-800448.pt"
102
  ]
103
  }
104
  },