Hugging Face's logo

jfelgate
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
jfelgate commited on
Commit
9d83d7a
·
1 Parent(s): 9aa067c

Second Push

Browse files
Files changed (18) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-149984.onnx +1 -1
  3. SnowballTarget/SnowballTarget-149984.pt +1 -1
  4. SnowballTarget/SnowballTarget-199984.onnx +1 -1
  5. SnowballTarget/SnowballTarget-199984.pt +1 -1
  6. SnowballTarget/SnowballTarget-200200.onnx +3 -0
  7. SnowballTarget/SnowballTarget-200200.pt +3 -0
  8. SnowballTarget/SnowballTarget-49952.onnx +3 -0
  9. SnowballTarget/SnowballTarget-49952.pt +3 -0
  10. SnowballTarget/SnowballTarget-99896.onnx +3 -0
  11. SnowballTarget/SnowballTarget-99896.pt +3 -0
  12. SnowballTarget/checkpoint.pt +1 -1
  13. SnowballTarget/events.out.tfevents.1696844566.4a5ea7ff132f.12562.0 +3 -0
  14. config.json +1 -1
  15. configuration.yaml +4 -4
  16. run_logs/Player-0.log +13 -16
  17. run_logs/timers.json +142 -142
  18. run_logs/training_status.json +28 -28
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:595a88691bcf06f5b154586944235d64044f6bb41100189bc1381022e665c6c7
3
  size 650645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3e43f92a062d644dc582760821375e1804e67b50d87b820c153cc4fd2d59ef7
3
  size 650645
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9fc673cdaa5b57131edc7a312ee01bc49ae71ed0e50b46a06da0b34adf59329
3
  size 650645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17f0c3ab4a748037b80af97459b280bae729108ce6a0c5245cccaa4a0f0e316c
3
  size 650645
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0599e2b5fb893bb3545a8c8526bc257bc39d24ab0f6c79eaa1ffb271a0d6746d
3
  size 3849614
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a993388d68fe2737f4cbe53bf5e9af19d9950ca00aec749392723c041e802aa9
3
  size 3849614
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:595a88691bcf06f5b154586944235d64044f6bb41100189bc1381022e665c6c7
3
  size 650645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3e43f92a062d644dc582760821375e1804e67b50d87b820c153cc4fd2d59ef7
3
  size 650645
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b847be3b97a4e745a47e9312425d368709b08663700c7ee7247229dd959f673
3
  size 3849614
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:301e7543dfe532acd65b232699d51da7fc3708af12449124ae417f95e9601a1b
3
  size 3849614
SnowballTarget/SnowballTarget-200200.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3e43f92a062d644dc582760821375e1804e67b50d87b820c153cc4fd2d59ef7
3
+ size 650645
SnowballTarget/SnowballTarget-200200.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd9c7a48297b180ac099d2f20148d437094557b43dd65fa26466bd8e9597b977
3
+ size 3849614
SnowballTarget/SnowballTarget-49952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24a9144a1cc1e1ace8a4aed2f7468c05830e46ed1ff474ba46b599cac9f36725
3
+ size 650645
SnowballTarget/SnowballTarget-49952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:935d36a6fb32b1d111fe8357017c137fdded20161ba98b2bd1ace10120ce969d
3
+ size 3849541
SnowballTarget/SnowballTarget-99896.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0c8bc8da9ea070a1f1c3a04c80f517193dd0f7e4e2ee6db8babc1209ffb7ac5
3
+ size 650645
SnowballTarget/SnowballTarget-99896.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:928f1f98c501158883951891c3064a50daa1f948e6a89552d69d03fe78f32331
3
+ size 3849541
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4743ef7942fa79db95a8546d25db1d0d53c1dda036339a73a1734f006f1f6626
3
  size 3848811
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa89e0ae8db8b42fb21a7aa4daccdc9b5fe83928381ecc11a4bf10c908487ee1
3
  size 3848811
SnowballTarget/events.out.tfevents.1696844566.4a5ea7ff132f.12562.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:413ccbcca5189c34bea4fd0864e7360003bcb694eab0b18baccae306b357adbd
3
+ size 23830
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, "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": 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": 64, "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": 15, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 128, "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": "SnowballTarget2", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -3,7 +3,7 @@ behaviors:
3
  SnowballTarget:
4
  trainer_type: ppo
5
  hyperparameters:
6
- batch_size: 128
7
  buffer_size: 2048
8
  learning_rate: 0.0003
9
  beta: 0.005
@@ -36,10 +36,10 @@ behaviors:
36
  goal_conditioning_type: hyper
37
  deterministic: false
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
@@ -64,7 +64,7 @@ engine_settings:
64
  no_graphics: true
65
  environment_parameters: null
66
  checkpoint_settings:
67
- run_id: SnowballTarget1
68
  initialize_from: null
69
  load_model: false
70
  resume: false
 
3
  SnowballTarget:
4
  trainer_type: ppo
5
  hyperparameters:
6
+ batch_size: 64
7
  buffer_size: 2048
8
  learning_rate: 0.0003
9
  beta: 0.005
 
36
  goal_conditioning_type: hyper
37
  deterministic: false
38
  init_path: null
39
+ keep_checkpoints: 15
40
  even_checkpoints: false
41
  max_steps: 200000
42
+ time_horizon: 128
43
  summary_freq: 10000
44
  threaded: true
45
  self_play: null
 
64
  no_graphics: true
65
  environment_parameters: null
66
  checkpoint_settings:
67
+ run_id: SnowballTarget2
68
  initialize_from: null
69
  load_model: false
70
  resume: false
run_logs/Player-0.log CHANGED
@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
5
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
6
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
7
- Unable to load player prefs
8
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
9
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
@@ -45,7 +42,7 @@ 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: 0.649026 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 +50,7 @@ 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
@@ -169,19 +166,19 @@ 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 6.7 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
@@ -213,13 +210,13 @@ 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]: 3710 frames, [64.0 KB-128.0 KB]: 1750 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 67.3 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 +228,13 @@ 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 +246,13 @@ 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
 
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
 
 
 
5
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
6
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
7
  Forcing GfxDevice: Null
 
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: 0.625442 ms
46
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
47
  requesting resize 84 x 84
48
  Setting up 1 worker threads for Enlighten.
 
50
  [ALLOC_TEMP_TLS] TLS Allocator
51
  StackAllocators :
52
  [ALLOC_TEMP_MAIN]
53
+ Peak usage frame count: [8.0 KB-16.0 KB]: 5374 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
54
  Initial Block Size 4.0 MB
55
  Current Block Size 4.0 MB
56
  Peak Allocated Bytes 2.0 MB
 
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
+ Peak main deferred allocation count 41
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
173
  Peak Allocated bytes 1.0 MB
174
  [ALLOC_DEFAULT_MAIN]
175
+ Peak usage frame count: [4.0 MB-8.0 MB]: 5466 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 6.6 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5466 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
  Peak Allocated memory 17.8 MB
 
210
  Used Block count 1
211
  Peak Allocated bytes 1.0 MB
212
  [ALLOC_GFX_MAIN]
213
+ Peak usage frame count: [32.0 KB-64.0 KB]: 4522 frames, [64.0 KB-128.0 KB]: 944 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 66.8 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5466 frames
220
  Requested Block Size 16.0 MB
221
  Peak Block count 1
222
  Peak Allocated memory 39.6 KB
 
228
  Used Block count 1
229
  Peak Allocated bytes 1.0 MB
230
  [ALLOC_CACHEOBJECTS_MAIN]
231
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5466 frames
232
  Requested Block Size 4.0 MB
233
  Peak Block count 1
234
  Peak Allocated memory 0.6 MB
235
  Peak Large allocation bytes 0 B
236
  [ALLOC_CACHEOBJECTS_THREAD]
237
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5465 frames, [2.0 MB-4.0 MB]: 1 frames
238
  Requested Block Size 4.0 MB
239
  Peak Block count 1
240
  Peak Allocated memory 2.2 MB
 
246
  Used Block count 1
247
  Peak Allocated bytes 1.0 MB
248
  [ALLOC_TYPETREE_MAIN]
249
+ Peak usage frame count: [0-1.0 KB]: 5466 frames
250
  Requested Block Size 2.0 MB
251
  Peak Block count 1
252
  Peak Allocated memory 1.0 KB
253
  Peak Large allocation bytes 0 B
254
  [ALLOC_TYPETREE_THREAD]
255
+ Peak usage frame count: [1.0 KB-2.0 KB]: 5466 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -2,15 +2,15 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.9271310567855835,
6
- "min": 0.9271310567855835,
7
- "max": 2.8540031909942627,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8852.2470703125,
12
- "min": 8852.2470703125,
13
- "max": 29227.84765625,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 11.75457763671875,
30
- "min": 0.35696130990982056,
31
- "max": 11.75457763671875,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2292.142578125,
36
- "min": 69.25049591064453,
37
- "max": 2349.72216796875,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -49,88 +49,88 @@
49
  "max": 10945.0,
50
  "count": 20
51
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.0658158376554995,
54
- "min": 0.06220789182082037,
55
- "max": 0.07489069106933825,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.263263350621998,
60
- "min": 0.263263350621998,
61
- "max": 0.3744534553466913,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.18494724737955073,
66
- "min": 0.14298208610054253,
67
- "max": 0.2847507728227213,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.7397889895182029,
72
- "min": 0.5719283444021701,
73
- "max": 1.3867595447044747,
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": 23.477272727272727,
114
- "min": 3.6818181818181817,
115
- "max": 23.477272727272727,
116
- "count": 20
117
- },
118
- "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1033.0,
120
- "min": 162.0,
121
- "max": 1272.0,
122
- "count": 20
123
- },
124
- "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 23.477272727272727,
126
- "min": 3.6818181818181817,
127
- "max": 23.477272727272727,
128
- "count": 20
129
- },
130
- "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1033.0,
132
- "min": 162.0,
133
- "max": 1272.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
@@ -148,67 +148,67 @@
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1696842219",
152
  "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0",
155
  "mlagents_envs_version": "0.31.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.0.1+cu118",
158
  "numpy_version": "1.21.2",
159
- "end_time_seconds": "1696842725"
160
  },
161
- "total": 505.9093767769999,
162
  "count": 1,
163
- "self": 0.42475824200005263,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.047987001000024065,
167
  "count": 1,
168
- "self": 0.047987001000024065
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 505.43663153399984,
172
  "count": 1,
173
- "self": 0.6268358339972337,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 7.6607587020000665,
177
  "count": 1,
178
- "self": 7.6607587020000665
179
  },
180
  "TrainerController.advance": {
181
- "total": 497.0568763960024,
182
- "count": 18200,
183
- "self": 0.29877217199862116,
184
  "children": {
185
  "env_step": {
186
- "total": 496.7581042240038,
187
- "count": 18200,
188
- "self": 341.97471981500837,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 154.4674859939995,
192
- "count": 18200,
193
- "self": 1.5676757489960664,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 152.89981024500344,
197
- "count": 18200,
198
- "self": 152.89981024500344
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.31589841499589966,
204
- "count": 18200,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 504.0678951499975,
209
- "count": 18200,
210
  "is_parallel": true,
211
- "self": 248.3082742130075,
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": 0.002238820000002306,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0006859480000684925,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0015528719999338136,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0015528719999338136
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03928126100004192,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006466200001113975,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0005090549999522409,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0005090549999522409
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03589537699997436,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03589537699997436
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0022302090000039243,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00040800799990847736,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.001822201000095447,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.001822201000095447
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 255.75962093699002,
271
- "count": 18199,
272
  "is_parallel": true,
273
- "self": 10.949905010979592,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.669765296008791,
277
- "count": 18199,
278
  "is_parallel": true,
279
- "self": 5.669765296008791
280
  },
281
  "communicator.exchange": {
282
- "total": 199.32806832600863,
283
- "count": 18199,
284
  "is_parallel": true,
285
- "self": 199.32806832600863
286
  },
287
  "steps_from_proto": {
288
- "total": 39.811882303993,
289
- "count": 18199,
290
  "is_parallel": true,
291
- "self": 7.396991181976091,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 32.41489112201691,
295
- "count": 181990,
296
  "is_parallel": true,
297
- "self": 32.41489112201691
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 4.134200003136357e-05,
313
  "count": 1,
314
- "self": 4.134200003136357e-05,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 492.9373298760088,
324
- "count": 505388,
325
  "is_parallel": true,
326
- "self": 11.49458482501825,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 273.7357046679907,
330
- "count": 505388,
331
  "is_parallel": true,
332
- "self": 273.1262018519906,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 0.6095028160001448,
336
  "count": 4,
337
  "is_parallel": true,
338
- "self": 0.6095028160001448
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 207.70704038299982,
344
  "count": 90,
345
  "is_parallel": true,
346
- "self": 76.29465958899834,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 131.41238079400148,
350
- "count": 4587,
351
  "is_parallel": true,
352
- "self": 131.41238079400148
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.09211926000011772,
364
  "count": 1,
365
- "self": 0.0008073809999586956,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.09131187900015902,
369
  "count": 1,
370
- "self": 0.09131187900015902
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.9818136096000671,
6
+ "min": 0.9818136096000671,
7
+ "max": 2.867668390274048,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 8650.759765625,
12
+ "min": 8650.759765625,
13
+ "max": 31702.07421875,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 12.896153450012207,
30
+ "min": 0.46542888879776,
31
+ "max": 12.896153450012207,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 1302.511474609375,
36
+ "min": 45.146602630615234,
37
+ "max": 1302.511474609375,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
49
  "max": 10945.0,
50
  "count": 20
51
  },
52
+ "SnowballTarget.Environment.CumulativeReward.mean": {
53
+ "value": 25.192307692307693,
54
+ "min": 3.477272727272727,
55
+ "max": 25.46,
56
+ "count": 20
57
+ },
58
+ "SnowballTarget.Environment.CumulativeReward.sum": {
59
+ "value": 1310.0,
60
+ "min": 153.0,
61
+ "max": 1334.0,
62
+ "count": 20
63
+ },
64
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
+ "value": 25.192307692307693,
66
+ "min": 3.477272727272727,
67
+ "max": 25.46,
68
+ "count": 20
69
+ },
70
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
+ "value": 1310.0,
72
+ "min": 153.0,
73
+ "max": 1334.0,
74
+ "count": 20
75
+ },
76
  "SnowballTarget.Losses.PolicyLoss.mean": {
77
+ "value": 0.09862604142984871,
78
+ "min": 0.09153875104208022,
79
+ "max": 0.10303310712637329,
80
  "count": 20
81
  },
82
  "SnowballTarget.Losses.PolicyLoss.sum": {
83
+ "value": 0.39450416571939484,
84
+ "min": 0.36615500416832086,
85
+ "max": 0.5103479526714145,
86
  "count": 20
87
  },
88
  "SnowballTarget.Losses.ValueLoss.mean": {
89
+ "value": 0.22787976568698687,
90
+ "min": 0.13077158421533658,
91
+ "max": 0.2673187094795353,
92
  "count": 20
93
  },
94
  "SnowballTarget.Losses.ValueLoss.sum": {
95
+ "value": 0.9115190627479475,
96
+ "min": 0.5230863368613463,
97
+ "max": 1.3365935473976764,
98
  "count": 20
99
  },
100
  "SnowballTarget.Policy.LearningRate.mean": {
101
+ "value": 8.004097332000004e-06,
102
+ "min": 8.004097332000004e-06,
103
+ "max": 0.00029175000274999995,
104
  "count": 20
105
  },
106
  "SnowballTarget.Policy.LearningRate.sum": {
107
+ "value": 3.2016389328000014e-05,
108
+ "min": 3.2016389328000014e-05,
109
+ "max": 0.0013851480382839998,
110
  "count": 20
111
  },
112
  "SnowballTarget.Policy.Epsilon.mean": {
113
+ "value": 0.102668,
114
+ "min": 0.102668,
115
+ "max": 0.19724999999999998,
116
  "count": 20
117
  },
118
  "SnowballTarget.Policy.Epsilon.sum": {
119
+ "value": 0.410672,
120
+ "min": 0.410672,
121
+ "max": 0.961716,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.Beta.mean": {
125
+ "value": 0.00014313320000000005,
126
+ "min": 0.00014313320000000005,
127
+ "max": 0.004862775,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.Beta.sum": {
131
+ "value": 0.0005725328000000002,
132
+ "min": 0.0005725328000000002,
133
+ "max": 0.023089628400000003,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1696844565",
152
  "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
154
  "mlagents_version": "0.31.0.dev0",
155
  "mlagents_envs_version": "0.31.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.0.1+cu118",
158
  "numpy_version": "1.21.2",
159
+ "end_time_seconds": "1696845051"
160
  },
161
+ "total": 485.724892836,
162
  "count": 1,
163
+ "self": 0.7981269819997578,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.046111746999940806,
167
  "count": 1,
168
+ "self": 0.046111746999940806
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 484.8806541070003,
172
  "count": 1,
173
+ "self": 0.6237864650070151,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.8252636830002302,
177
  "count": 1,
178
+ "self": 2.8252636830002302
179
  },
180
  "TrainerController.advance": {
181
+ "total": 481.29648568699304,
182
+ "count": 18219,
183
+ "self": 0.27385319798077035,
184
  "children": {
185
  "env_step": {
186
+ "total": 481.02263248901227,
187
+ "count": 18219,
188
+ "self": 305.3376902350169,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 175.3947359979943,
192
+ "count": 18219,
193
+ "self": 1.5458529869738413,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 173.84888301102046,
197
+ "count": 18219,
198
+ "self": 173.84888301102046
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.2902062560010563,
204
+ "count": 18219,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 483.31973866200906,
209
+ "count": 18219,
210
  "is_parallel": true,
211
+ "self": 233.56290503694936,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.002128088000063144,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.000633400999049627,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0014946870010135171,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0014946870010135171
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.09923197799980699,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006173549991217442,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004802790003850532,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004802790003850532
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.09607249200007573,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.09607249200007573
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0020618520002244622,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00036929900034010643,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0016925529998843558,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0016925529998843558
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 249.7568336250597,
271
+ "count": 18218,
272
  "is_parallel": true,
273
+ "self": 10.5427471200519,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.4190480060265145,
277
+ "count": 18218,
278
  "is_parallel": true,
279
+ "self": 5.4190480060265145
280
  },
281
  "communicator.exchange": {
282
+ "total": 195.00553036598876,
283
+ "count": 18218,
284
  "is_parallel": true,
285
+ "self": 195.00553036598876
286
  },
287
  "steps_from_proto": {
288
+ "total": 38.78950813299252,
289
+ "count": 18218,
290
  "is_parallel": true,
291
+ "self": 7.2216988799277715,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 31.567809253064752,
295
+ "count": 182180,
296
  "is_parallel": true,
297
+ "self": 31.567809253064752
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.00023640300014449167,
313
  "count": 1,
314
+ "self": 0.00023640300014449167,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 481.57466612795133,
324
+ "count": 37812,
325
  "is_parallel": true,
326
+ "self": 0.8226898269886078,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 68.34923789396407,
330
+ "count": 37812,
331
  "is_parallel": true,
332
+ "self": 67.36544494896407,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 0.9837929450000047,
336
  "count": 4,
337
  "is_parallel": true,
338
+ "self": 0.9837929450000047
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 412.40273840699865,
344
  "count": 90,
345
  "is_parallel": true,
346
+ "self": 91.2735077299917,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 321.12923067700694,
350
+ "count": 9180,
351
  "is_parallel": true,
352
+ "self": 321.12923067700694
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.13488186899985521,
364
  "count": 1,
365
+ "self": 0.0011127099996883771,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.13376915900016684,
369
  "count": 1,
370
+ "self": 0.13376915900016684
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": 14.181818181818182,
8
- "creation_time": 1696842355.568735,
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": 19.09090909090909,
17
- "creation_time": 1696842476.2839308,
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": 21.454545454545453,
26
- "creation_time": 1696842602.1682744,
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": 22.454545454545453,
35
- "creation_time": 1696842724.696504,
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": 22.454545454545453,
44
- "creation_time": 1696842724.8269088,
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": 22.454545454545453,
54
- "creation_time": 1696842724.8269088,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 49952,
6
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-49952.onnx",
7
+ "reward": 14.5,
8
+ "creation_time": 1696844690.3706982,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-49952.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 99896,
15
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99896.onnx",
16
+ "reward": 22.0,
17
+ "creation_time": 1696844811.9783642,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-99896.pt"
20
  ]
21
  },
22
  {
23
  "steps": 149984,
24
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": null,
26
+ "creation_time": 1696844934.5443916,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
30
  },
31
  {
32
  "steps": 199984,
33
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 26.5,
35
+ "creation_time": 1696845050.6524959,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 200200,
42
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-200200.onnx",
43
+ "reward": 26.181818181818183,
44
+ "creation_time": 1696845050.8324506,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-200200.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
+ "steps": 200200,
52
+ "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
53
+ "reward": 26.181818181818183,
54
+ "creation_time": 1696845050.8324506,
55
  "auxillary_file_paths": [
56
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-200200.pt"
57
  ]
58
  }
59
  },