Hugging Face's logo

Adulala20
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
Adulala20 commited on
Commit
6283fcd
·
1 Parent(s): 06e98f0

First Push

Browse files
Files changed (18) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-149984.onnx +3 -0
  3. SnowballTarget/SnowballTarget-149984.pt +3 -0
  4. SnowballTarget/SnowballTarget-199984.onnx +3 -0
  5. SnowballTarget/SnowballTarget-199984.pt +3 -0
  6. SnowballTarget/SnowballTarget-200200.onnx +3 -0
  7. SnowballTarget/SnowballTarget-200200.pt +3 -0
  8. SnowballTarget/SnowballTarget-49936.onnx +1 -1
  9. SnowballTarget/SnowballTarget-49936.pt +1 -1
  10. SnowballTarget/SnowballTarget-99960.onnx +3 -0
  11. SnowballTarget/SnowballTarget-99960.pt +3 -0
  12. SnowballTarget/checkpoint.pt +1 -1
  13. SnowballTarget/events.out.tfevents.1692546883.12350e56738c.8903.0 +3 -0
  14. config.json +1 -1
  15. configuration.yaml +6 -6
  16. run_logs/Player-0.log +15 -15
  17. run_logs/timers.json +182 -182
  18. run_logs/training_status.json +26 -35
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca16935f27504f70e471799c0890e80f6f024db3ea94ada052197b7f4db3d64b
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4ca3b99cbd162e4e511800bbbb1d6688930a55c61d9edfdff7510b092ea47ba
3
  size 646532
SnowballTarget/SnowballTarget-149984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a214aa6e609cf5a78f0dc64e8ed2554ae536590fe83c72adf142ec895bbc1a4f
3
+ size 646532
SnowballTarget/SnowballTarget-149984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c436af89e8045169d902c1d0996623a19813f3b3503f395f5193edf7a001c0c3
3
+ size 3843968
SnowballTarget/SnowballTarget-199984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4ca3b99cbd162e4e511800bbbb1d6688930a55c61d9edfdff7510b092ea47ba
3
+ size 646532
SnowballTarget/SnowballTarget-199984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f051d62a37769094b4effb583a33062248a09fef6c7154f429629090c72da0f
3
+ size 3843968
SnowballTarget/SnowballTarget-200200.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4ca3b99cbd162e4e511800bbbb1d6688930a55c61d9edfdff7510b092ea47ba
3
+ size 646532
SnowballTarget/SnowballTarget-200200.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c46128972a873ddfef4d1502e47a3ad9fae34193cbe1b44afdd6ced9446eda36
3
+ size 3843968
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b613e25286f4df5ff172c949eabbf04fb1dc1b2c259e90ab0e5d5e4f7615d236
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1c9758c4cd1f41701e8b033b4b6dbe4363b564cd2715c5735c7999364cc5727
3
  size 646532
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26fd7f1785aeab49f75f84f76bd04ce61740ead805166436d348e270a5581044
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be8ee7c6e96eaf12eaebc73be24bb2648e51431186ecb49d0fefbe4ea14aa3b3
3
  size 3843968
SnowballTarget/SnowballTarget-99960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b24a894dbb28ffc774317bcc6a6bf26c6c29640f007e2a74fee776b1b58b148
3
+ size 646532
SnowballTarget/SnowballTarget-99960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f1cf6c6928c265f84de97323cf99409c24a1732461e1af62191c9886c37dcfd
3
+ size 3843968
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42b2f7b4b97683b930eb846da13e786a155cff622a592cad0e2d0efe79902f60
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c46128972a873ddfef4d1502e47a3ad9fae34193cbe1b44afdd6ced9446eda36
3
  size 3843968
SnowballTarget/events.out.tfevents.1692546883.12350e56738c.8903.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65ab00781830f77a536a989986925b6917d8c0f375584893186a231174665601
3
+ size 28909
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": 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": 512, "buffer_size": 10000, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.3, "lambd": 0.95, "num_epoch": 7, "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": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -3,13 +3,13 @@ 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
10
- epsilon: 0.2
11
  lambd: 0.95
12
- num_epoch: 3
13
  shared_critic: false
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
@@ -67,8 +67,8 @@ checkpoint_settings:
67
  run_id: SnowballTarget1
68
  initialize_from: null
69
  load_model: false
70
- resume: true
71
- force: false
72
  train_model: false
73
  inference: false
74
  results_dir: results
 
3
  SnowballTarget:
4
  trainer_type: ppo
5
  hyperparameters:
6
+ batch_size: 512
7
+ buffer_size: 10000
8
  learning_rate: 0.0003
9
  beta: 0.005
10
+ epsilon: 0.3
11
  lambd: 0.95
12
+ num_epoch: 7
13
  shared_critic: false
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
 
67
  run_id: SnowballTarget1
68
  initialize_from: null
69
  load_model: false
70
+ resume: false
71
+ force: true
72
  train_model: false
73
  inference: false
74
  results_dir: results
run_logs/Player-0.log CHANGED
@@ -31,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
- - Completed reload, in 0.084 seconds
35
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -42,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
42
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
43
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
44
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
45
- UnloadTime: 0.653990 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]: 3665 frames, [16.0 KB-32.0 KB]: 62 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 32
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]: 3728 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
- Peak Allocated memory 6.2 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
- Peak usage frame count: [16.0 MB-32.0 MB]: 3728 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
- Peak Allocated memory 17.8 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]: 3590 frames, [64.0 KB-128.0 KB]: 138 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]: 3728 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]: 3728 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]: 3727 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]: 3728 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]: 3728 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
 
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.080 seconds
35
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
42
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
43
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
44
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
45
+ UnloadTime: 0.664936 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]: 5369 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
54
  Initial Block Size 4.0 MB
55
  Current Block Size 4.0 MB
56
  Peak Allocated Bytes 2.0 MB
 
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
+ Peak main deferred allocation count 42
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
173
  Peak Allocated bytes 1.0 MB
174
  [ALLOC_DEFAULT_MAIN]
175
+ Peak usage frame count: [4.0 MB-8.0 MB]: 5461 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 7.3 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.3 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]: 4489 frames, [64.0 KB-128.0 KB]: 972 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 67.3 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5461 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]: 5461 frames
232
  Requested Block Size 4.0 MB
233
  Peak Block count 1
234
  Peak Allocated memory 0.6 MB
235
  Peak Large allocation bytes 0 B
236
  [ALLOC_CACHEOBJECTS_THREAD]
237
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5460 frames, [2.0 MB-4.0 MB]: 1 frames
238
  Requested Block Size 4.0 MB
239
  Peak Block count 1
240
  Peak Allocated memory 2.2 MB
 
246
  Used Block count 1
247
  Peak Allocated bytes 1.0 MB
248
  [ALLOC_TYPETREE_MAIN]
249
+ Peak usage frame count: [0-1.0 KB]: 5461 frames
250
  Requested Block Size 2.0 MB
251
  Peak Block count 1
252
  Peak Allocated memory 1.0 KB
253
  Peak Large allocation bytes 0 B
254
  [ALLOC_TYPETREE_THREAD]
255
+ Peak usage frame count: [1.0 KB-2.0 KB]: 5461 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -2,213 +2,213 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.836672842502594,
6
- "min": 0.836672842502594,
7
- "max": 1.8354339599609375,
8
- "count": 14
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8043.77294921875,
12
- "min": 8043.77294921875,
13
- "max": 17563.78515625,
14
- "count": 14
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 199960.0,
18
- "min": 69968.0,
19
- "max": 199960.0,
20
- "count": 14
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 199960.0,
24
- "min": 69968.0,
25
- "max": 199960.0,
26
- "count": 14
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.781302452087402,
30
- "min": 7.125820159912109,
31
- "max": 12.781302452087402,
32
- "count": 14
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2492.35400390625,
36
- "min": 833.720947265625,
37
- "max": 2593.813720703125,
38
- "count": 14
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
- "count": 14
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
- "value": 10945.0,
48
- "min": 4378.0,
49
  "max": 10945.0,
50
- "count": 14
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06581170070064984,
54
- "min": 0.065043459268054,
55
- "max": 0.08029949526946224,
56
- "count": 14
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.2632468028025994,
60
- "min": 0.1312331338658445,
61
- "max": 0.4014974763473112,
62
- "count": 14
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.1939256189792764,
66
- "min": 0.18633982268910781,
67
- "max": 0.25311718063027255,
68
- "count": 14
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.7757024759171056,
72
- "min": 0.5029456494558675,
73
- "max": 1.2505602845374275,
74
- "count": 14
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 8.214097262000005e-06,
78
- "min": 8.214097262000005e-06,
79
- "max": 0.00019961403346200002,
80
- "count": 14
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 3.285638904800002e-05,
84
- "min": 3.285638904800002e-05,
85
- "max": 0.00094032018656,
86
- "count": 14
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.10273800000000001,
90
- "min": 0.10273800000000001,
91
- "max": 0.16653800000000002,
92
- "count": 14
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.41095200000000004,
96
- "min": 0.33307600000000004,
97
- "max": 0.8134400000000002,
98
- "count": 14
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
- "value": 0.0001466262000000001,
102
- "min": 0.0001466262000000001,
103
- "max": 0.0033302462000000007,
104
- "count": 14
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.0005865048000000004,
108
- "min": 0.0005865048000000004,
109
- "max": 0.015690656000000004,
110
- "count": 14
111
- },
112
- "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.09090909090909,
114
- "min": 17.727272727272727,
115
- "max": 25.431818181818183,
116
- "count": 14
117
- },
118
- "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1104.0,
120
- "min": 390.0,
121
- "max": 1388.0,
122
- "count": 14
123
- },
124
- "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.09090909090909,
126
- "min": 17.727272727272727,
127
- "max": 25.431818181818183,
128
- "count": 14
129
- },
130
- "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1104.0,
132
- "min": 390.0,
133
- "max": 1388.0,
134
- "count": 14
135
- },
136
- "SnowballTarget.IsTraining.mean": {
137
- "value": 1.0,
138
- "min": 1.0,
139
- "max": 1.0,
140
- "count": 14
141
- },
142
- "SnowballTarget.IsTraining.sum": {
143
- "value": 1.0,
144
- "min": 1.0,
145
- "max": 1.0,
146
- "count": 14
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1692545544",
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 --resume",
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": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
- "end_time_seconds": "1692545861"
160
  },
161
- "total": 317.6313503980001,
162
  "count": 1,
163
- "self": 0.7840919160000794,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.04170700500003477,
167
  "count": 1,
168
- "self": 0.04170700500003477
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 316.805551477,
172
  "count": 1,
173
- "self": 0.38119174001519696,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.9177380400000175,
177
  "count": 1,
178
- "self": 3.9177380400000175
179
  },
180
  "TrainerController.advance": {
181
- "total": 312.27118551198475,
182
- "count": 12424,
183
- "self": 0.18747485698986566,
184
  "children": {
185
  "env_step": {
186
- "total": 312.0837106549949,
187
- "count": 12424,
188
- "self": 228.62752408799213,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 83.26534969100692,
192
- "count": 12424,
193
- "self": 1.2040676890179611,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 82.06128200198896,
197
- "count": 12424,
198
- "self": 82.06128200198896
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.1908368759958421,
204
- "count": 12424,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 315.55860512299535,
209
- "count": 12424,
210
  "is_parallel": true,
211
- "self": 147.2086571580037,
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": 0.0018325449999565535,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0005223669999168123,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0013101780000397412,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0013101780000397412
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03423124400001143,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0005997139998044076,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0004083150000724345,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0004083150000724345
244
  },
245
  "communicator.exchange": {
246
- "total": 0.031070490000047357,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.031070490000047357
250
  },
251
  "steps_from_proto": {
252
- "total": 0.00215272500008723,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0005045410002821882,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0016481839998050418,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0016481839998050418
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 168.34994796499166,
271
- "count": 12423,
272
  "is_parallel": true,
273
- "self": 7.057714106998219,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 3.5819989389972307,
277
- "count": 12423,
278
  "is_parallel": true,
279
- "self": 3.5819989389972307
280
  },
281
  "communicator.exchange": {
282
- "total": 133.4748783099982,
283
- "count": 12423,
284
  "is_parallel": true,
285
- "self": 133.4748783099982
286
  },
287
  "steps_from_proto": {
288
- "total": 24.235356608998018,
289
- "count": 12423,
290
  "is_parallel": true,
291
- "self": 4.414643972016165,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 19.820712636981852,
295
- "count": 124230,
296
  "is_parallel": true,
297
- "self": 19.820712636981852
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00011547899998731737,
313
  "count": 1,
314
- "self": 0.00011547899998731737,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 309.8994989799986,
324
- "count": 283728,
325
  "is_parallel": true,
326
- "self": 6.091263030016762,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 169.19533811698216,
330
- "count": 283728,
331
  "is_parallel": true,
332
- "self": 167.65719715898217,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 1.5381409579999854,
336
- "count": 3,
337
  "is_parallel": true,
338
- "self": 1.5381409579999854
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 134.6128978329997,
344
- "count": 61,
345
  "is_parallel": true,
346
- "self": 53.76158820299975,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 80.85130962999995,
350
- "count": 3108,
351
  "is_parallel": true,
352
- "self": 80.85130962999995
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.23532070600003863,
364
  "count": 1,
365
- "self": 0.0019433209999988321,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.2333773850000398,
369
  "count": 1,
370
- "self": 0.2333773850000398
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 1.524087905883789,
6
+ "min": 1.524087905883789,
7
+ "max": 2.890340805053711,
8
+ "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 14568.755859375,
12
+ "min": 14568.755859375,
13
+ "max": 29631.7734375,
14
+ "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 199984.0,
18
+ "min": 9952.0,
19
+ "max": 199984.0,
20
+ "count": 20
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 199984.0,
24
+ "min": 9952.0,
25
+ "max": 199984.0,
26
+ "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 8.589315414428711,
30
+ "min": 0.027471229434013367,
31
+ "max": 8.589315414428711,
32
+ "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 1674.91650390625,
36
+ "min": 5.329418659210205,
37
+ "max": 1681.61962890625,
38
+ "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 20
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 8756.0,
48
+ "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 20
51
+ },
52
+ "SnowballTarget.Environment.CumulativeReward.mean": {
53
+ "value": 21.704545454545453,
54
+ "min": 2.6363636363636362,
55
+ "max": 22.363636363636363,
56
+ "count": 20
57
+ },
58
+ "SnowballTarget.Environment.CumulativeReward.sum": {
59
+ "value": 955.0,
60
+ "min": 116.0,
61
+ "max": 1230.0,
62
+ "count": 20
63
+ },
64
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
+ "value": 21.704545454545453,
66
+ "min": 2.6363636363636362,
67
+ "max": 22.363636363636363,
68
+ "count": 20
69
+ },
70
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
+ "value": 955.0,
72
+ "min": 116.0,
73
+ "max": 1230.0,
74
+ "count": 20
75
+ },
76
+ "SnowballTarget.IsTraining.mean": {
77
+ "value": 1.0,
78
+ "min": 1.0,
79
+ "max": 1.0,
80
+ "count": 20
81
+ },
82
+ "SnowballTarget.IsTraining.sum": {
83
+ "value": 1.0,
84
+ "min": 1.0,
85
+ "max": 1.0,
86
+ "count": 20
87
  },
88
  "SnowballTarget.Losses.PolicyLoss.mean": {
89
+ "value": 0.03813731559494045,
90
+ "min": 0.030352596685144163,
91
+ "max": 0.03813731559494045,
92
+ "count": 19
93
  },
94
  "SnowballTarget.Losses.PolicyLoss.sum": {
95
+ "value": 0.03813731559494045,
96
+ "min": 0.030352596685144163,
97
+ "max": 0.03813731559494045,
98
+ "count": 19
99
  },
100
  "SnowballTarget.Losses.ValueLoss.mean": {
101
+ "value": 0.261536289538656,
102
+ "min": 0.07737695226879944,
103
+ "max": 0.33659222083432333,
104
+ "count": 19
105
  },
106
  "SnowballTarget.Losses.ValueLoss.sum": {
107
+ "value": 0.261536289538656,
108
+ "min": 0.07737695226879944,
109
+ "max": 0.33659222083432333,
110
+ "count": 19
111
  },
112
  "SnowballTarget.Policy.LearningRate.mean": {
113
+ "value": 7.488097503999998e-06,
114
+ "min": 7.488097503999998e-06,
115
+ "max": 0.00028468800510399997,
116
+ "count": 19
117
  },
118
  "SnowballTarget.Policy.LearningRate.sum": {
119
+ "value": 7.488097503999998e-06,
120
+ "min": 7.488097503999998e-06,
121
+ "max": 0.00028468800510399997,
122
+ "count": 19
123
  },
124
  "SnowballTarget.Policy.Epsilon.mean": {
125
+ "value": 0.10499199999999999,
126
+ "min": 0.10499199999999999,
127
+ "max": 0.28979199999999994,
128
+ "count": 19
129
  },
130
  "SnowballTarget.Policy.Epsilon.sum": {
131
+ "value": 0.10499199999999999,
132
+ "min": 0.10499199999999999,
133
+ "max": 0.28979199999999994,
134
+ "count": 19
135
  },
136
  "SnowballTarget.Policy.Beta.mean": {
137
+ "value": 0.00013455039999999988,
138
+ "min": 0.00013455039999999988,
139
+ "max": 0.0047453104,
140
+ "count": 19
141
  },
142
  "SnowballTarget.Policy.Beta.sum": {
143
+ "value": 0.00013455039999999988,
144
+ "min": 0.00013455039999999988,
145
+ "max": 0.0047453104,
146
+ "count": 19
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1692546882",
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 --force",
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": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
+ "end_time_seconds": "1692547414"
160
  },
161
+ "total": 531.493570528,
162
  "count": 1,
163
+ "self": 0.438592632000109,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.050082269000085944,
167
  "count": 1,
168
+ "self": 0.050082269000085944
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 531.0048956269998,
172
  "count": 1,
173
+ "self": 0.5461930540013782,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 4.4186103289998755,
177
  "count": 1,
178
+ "self": 4.4186103289998755
179
  },
180
  "TrainerController.advance": {
181
+ "total": 525.8932921079986,
182
+ "count": 18202,
183
+ "self": 0.2556655550188225,
184
  "children": {
185
  "env_step": {
186
+ "total": 525.6376265529798,
187
+ "count": 18202,
188
+ "self": 405.4591730799416,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 119.91368708700747,
192
+ "count": 18202,
193
+ "self": 1.9687249190587863,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 117.94496216794869,
197
+ "count": 18202,
198
+ "self": 117.94496216794869
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.2647663860307148,
204
+ "count": 18202,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 529.6026522519887,
209
+ "count": 18202,
210
  "is_parallel": true,
211
+ "self": 290.3153083829852,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0018283710001014697,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0004956860011589015,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0013326849989425682,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0013326849989425682
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.06508506799991665,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006614669996451994,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004135310000492609,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004135310000492609
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.061839138000323146,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.061839138000323146
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0021709319998990395,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0005372180003178073,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0016337139995812322,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0016337139995812322
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 239.2873438690035,
271
+ "count": 18201,
272
  "is_parallel": true,
273
+ "self": 10.342141128946878,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.226137717036181,
277
+ "count": 18201,
278
  "is_parallel": true,
279
+ "self": 5.226137717036181
280
  },
281
  "communicator.exchange": {
282
+ "total": 188.4299399129991,
283
+ "count": 18201,
284
  "is_parallel": true,
285
+ "self": 188.4299399129991
286
  },
287
  "steps_from_proto": {
288
+ "total": 35.28912511002136,
289
+ "count": 18201,
290
  "is_parallel": true,
291
+ "self": 6.320004223180604,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 28.969120886840756,
295
+ "count": 182010,
296
  "is_parallel": true,
297
+ "self": 28.969120886840756
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.00017537399980938062,
313
  "count": 1,
314
+ "self": 0.00017537399980938062,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 520.6744152131068,
324
+ "count": 594430,
325
  "is_parallel": true,
326
+ "self": 13.519625416097824,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 327.58573930000966,
330
+ "count": 594430,
331
  "is_parallel": true,
332
+ "self": 326.30826315300965,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 1.2774761470000158,
336
+ "count": 4,
337
  "is_parallel": true,
338
+ "self": 1.2774761470000158
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 179.56905049699935,
344
+ "count": 19,
345
  "is_parallel": true,
346
+ "self": 129.0545505799896,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 50.51449991700974,
350
+ "count": 2611,
351
  "is_parallel": true,
352
+ "self": 50.51449991700974
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.14662476200010133,
364
  "count": 1,
365
+ "self": 0.0010891460001403175,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.145535615999961,
369
  "count": 1,
370
+ "self": 0.145535615999961
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -4,65 +4,56 @@
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 14.727272727272727,
8
- "creation_time": 1692545493.83069,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
12
  },
13
  {
14
- "steps": 63712,
15
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-63712.onnx",
16
- "reward": null,
17
- "creation_time": 1692545525.808099,
18
  "auxillary_file_paths": [
19
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-63712.pt"
20
  ]
21
  },
22
  {
23
- "steps": 99936,
24
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99936.onnx",
25
- "reward": 22.454545454545453,
26
- "creation_time": 1692545631.1899426,
27
  "auxillary_file_paths": [
28
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-99936.pt"
29
  ]
30
  },
31
  {
32
- "steps": 149960,
33
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149960.onnx",
34
- "reward": 25.181818181818183,
35
- "creation_time": 1692545745.901099,
36
  "auxillary_file_paths": [
37
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-149960.pt"
38
  ]
39
  },
40
  {
41
- "steps": 199960,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199960.onnx",
43
- "reward": 24.818181818181817,
44
- "creation_time": 1692545860.6253152,
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-199960.pt"
47
- ]
48
- },
49
- {
50
- "steps": 200024,
51
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200024.onnx",
52
- "reward": 24.818181818181817,
53
- "creation_time": 1692545860.8711016,
54
- "auxillary_file_paths": [
55
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200024.pt"
56
  ]
57
  }
58
  ],
59
  "final_checkpoint": {
60
- "steps": 200024,
61
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
62
- "reward": 24.818181818181817,
63
- "creation_time": 1692545860.8711016,
64
  "auxillary_file_paths": [
65
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200024.pt"
66
  ]
67
  }
68
  },
 
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 10.068181818181818,
8
+ "creation_time": 1692547013.5427196,
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": 16.818181818181817,
17
+ "creation_time": 1692547146.0255828,
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": 20.363636363636363,
26
+ "creation_time": 1692547279.119288,
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": 22.227272727272727,
35
+ "creation_time": 1692547413.4882064,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 200200,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.onnx",
43
+ "reward": 22.393939393939394,
44
+ "creation_time": 1692547413.6942494,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.pt"
 
 
 
 
 
 
 
 
 
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
+ "steps": 200200,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
+ "reward": 22.393939393939394,
54
+ "creation_time": 1692547413.6942494,
55
  "auxillary_file_paths": [
56
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.pt"
57
  ]
58
  }
59
  },