Hugging Face's logo

jensenwiedler
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
jensenwiedler commited on
Commit
faad574
·
verified ·
1 Parent(s): 2a7d5f0

second Push

Browse files
Files changed (18) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-549976.onnx +3 -0
  3. SnowballTarget/SnowballTarget-549976.pt +3 -0
  4. SnowballTarget/SnowballTarget-599936.onnx +3 -0
  5. SnowballTarget/SnowballTarget-599936.pt +3 -0
  6. SnowballTarget/SnowballTarget-649960.onnx +3 -0
  7. SnowballTarget/SnowballTarget-649960.pt +3 -0
  8. SnowballTarget/SnowballTarget-699960.onnx +3 -0
  9. SnowballTarget/SnowballTarget-699960.pt +3 -0
  10. SnowballTarget/SnowballTarget-700216.onnx +3 -0
  11. SnowballTarget/SnowballTarget-700216.pt +3 -0
  12. SnowballTarget/checkpoint.pt +1 -1
  13. SnowballTarget/events.out.tfevents.1735996792.358412b7f1d5.7231.0 +3 -0
  14. config.json +1 -1
  15. configuration.yaml +2 -2
  16. run_logs/Player-0.log +15 -15
  17. run_logs/timers.json +163 -163
  18. run_logs/training_status.json +49 -49
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:892ed4663f040154610c0c27bd9130771b3ed591703db9df3e2189faa84fad5a
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b69b5713932148c7adb707222b68501899ba0abfabdd2aa1f7e8e634ff7a76b3
3
  size 650646
SnowballTarget/SnowballTarget-549976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:763f3c90d1ea2173ad1e8346c2902f1bd8ba3bca3b050f0e7f2c120edc9ba04d
3
+ size 650646
SnowballTarget/SnowballTarget-549976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0cbef37288d8a771abbab0f090b9106e133226b480e46cf2cd65590cb0fce24
3
+ size 3850075
SnowballTarget/SnowballTarget-599936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91ee899f60a7b2a091715d5dd6765a75e99e5a1d930a6244cd5c6a100585c1e7
3
+ size 650646
SnowballTarget/SnowballTarget-599936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c436d411c6726b248971025e4aa5280e43f0982b68ecd9d88c628530f696e7be
3
+ size 3850075
SnowballTarget/SnowballTarget-649960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af897a4d6fab3b15fff12d12ab64098100035b52053bf6d9fe41a0a271c6736d
3
+ size 650646
SnowballTarget/SnowballTarget-649960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e54d611dc1e30d983999d0b25eb2e76ae481bafb3b0bf4140a73de6054c7f9d
3
+ size 3850075
SnowballTarget/SnowballTarget-699960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b69b5713932148c7adb707222b68501899ba0abfabdd2aa1f7e8e634ff7a76b3
3
+ size 650646
SnowballTarget/SnowballTarget-699960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22ea085092fde13684e0a92448a989c323b7f2e672eb46ac179a5a6681ec3e19
3
+ size 3850075
SnowballTarget/SnowballTarget-700216.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b69b5713932148c7adb707222b68501899ba0abfabdd2aa1f7e8e634ff7a76b3
3
+ size 650646
SnowballTarget/SnowballTarget-700216.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9b5d76fb6eb643b312825282fd710ee75c8d7f79eb4635d5e19bc4507f2d8d2
3
+ size 3850075
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ff7571f7515972757077b49f5ca68bfdcf48c2362cdf55d7ffbeaa9e7062423
3
  size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d6e73e62c0552157b38d2b0afa307cca1fa485ff46f2c555b25fd1007211ad2
3
  size 3849250
SnowballTarget/events.out.tfevents.1735996792.358412b7f1d5.7231.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10b3f974537bd9824da4e8e4673eb78f54745ba729906091836d90ebb2884ba0
3
+ size 17436
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 512, "buffer_size": 10240, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 500000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "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}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 512, "buffer_size": 10240, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 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": 700000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget2", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -38,7 +38,7 @@ behaviors:
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
- max_steps: 500000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: false
@@ -69,7 +69,7 @@ checkpoint_settings:
69
  run_id: SnowballTarget2
70
  initialize_from: null
71
  load_model: false
72
- resume: false
73
  force: false
74
  train_model: false
75
  inference: false
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 700000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: false
 
69
  run_id: SnowballTarget2
70
  initialize_from: null
71
  load_model: false
72
+ resume: true
73
  force: false
74
  train_model: false
75
  inference: false
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: 0.600158 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]: 13412 frames, [16.0 KB-32.0 KB]: 227 frames, [2.0 MB-4.0 MB]: 1 frames
54
  Initial Block Size 4.0 MB
55
  Current Block Size 4.0 MB
56
  Peak Allocated Bytes 2.0 MB
@@ -166,22 +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 44
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]: 12691 frames, [8.0 MB-16.0 MB]: 949 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
- Peak Allocated memory 9.5 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
- Peak usage frame count: [16.0 MB-32.0 MB]: 13640 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
- Peak Allocated memory 17.9 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]: 9992 frames, [64.0 KB-128.0 KB]: 3648 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
- Peak Allocated memory 67.7 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
- Peak usage frame count: [32.0 KB-64.0 KB]: 13640 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]: 13640 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]: 13639 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]: 13640 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]: 13640 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 0.085 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: 0.690879 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]: 5367 frames, [16.0 KB-32.0 KB]: 90 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]: 5458 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 6.8 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5458 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
  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]: 5263 frames, [64.0 KB-128.0 KB]: 195 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]: 5458 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]: 5458 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]: 5457 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]: 5458 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]: 5458 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": 1.0433436632156372,
6
- "min": 1.0433436632156372,
7
- "max": 2.8903353214263916,
8
- "count": 50
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 10007.7529296875,
12
- "min": 10007.7529296875,
13
- "max": 29582.12109375,
14
- "count": 50
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 499976.0,
18
- "min": 9952.0,
19
- "max": 499976.0,
20
- "count": 50
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 499976.0,
24
- "min": 9952.0,
25
- "max": 499976.0,
26
- "count": 50
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 11.941898345947266,
30
- "min": -0.029164781793951988,
31
- "max": 11.941898345947266,
32
- "count": 50
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2448.089111328125,
36
- "min": -5.657967567443848,
37
- "max": 2448.089111328125,
38
- "count": 50
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
- "count": 50
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
- "value": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
- "count": 50
51
  },
52
  "SnowballTarget.Environment.CumulativeReward.mean": {
53
- "value": 24.836363636363636,
54
- "min": 2.772727272727273,
55
- "max": 24.836363636363636,
56
- "count": 50
57
  },
58
  "SnowballTarget.Environment.CumulativeReward.sum": {
59
- "value": 1366.0,
60
- "min": 122.0,
61
- "max": 1366.0,
62
- "count": 50
63
  },
64
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
- "value": 24.836363636363636,
66
- "min": 2.772727272727273,
67
- "max": 24.836363636363636,
68
- "count": 50
69
  },
70
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
- "value": 1366.0,
72
- "min": 122.0,
73
- "max": 1366.0,
74
- "count": 50
75
  },
76
  "SnowballTarget.IsTraining.mean": {
77
  "value": 1.0,
78
  "min": 1.0,
79
  "max": 1.0,
80
- "count": 50
81
  },
82
  "SnowballTarget.IsTraining.sum": {
83
  "value": 1.0,
84
  "min": 1.0,
85
  "max": 1.0,
86
- "count": 50
87
  },
88
  "SnowballTarget.Losses.PolicyLoss.mean": {
89
- "value": 0.033749266809597125,
90
- "min": 0.029031308105451955,
91
- "max": 0.04455755887320265,
92
- "count": 47
93
  },
94
  "SnowballTarget.Losses.PolicyLoss.sum": {
95
- "value": 0.033749266809597125,
96
- "min": 0.029031308105451955,
97
- "max": 0.04455755887320265,
98
- "count": 47
99
  },
100
  "SnowballTarget.Losses.ValueLoss.mean": {
101
- "value": 0.21887490873535473,
102
- "min": 0.09664271038676066,
103
- "max": 0.29807205746571225,
104
- "count": 47
105
  },
106
  "SnowballTarget.Losses.ValueLoss.sum": {
107
- "value": 0.21887490873535473,
108
- "min": 0.09664271038676066,
109
- "max": 0.29807205746571225,
110
- "count": 47
111
  },
112
  "SnowballTarget.Policy.LearningRate.mean": {
113
- "value": 5.21769826079999e-06,
114
- "min": 5.21769826079999e-06,
115
- "max": 0.00029345280218239997,
116
- "count": 47
117
  },
118
  "SnowballTarget.Policy.LearningRate.sum": {
119
- "value": 5.21769826079999e-06,
120
- "min": 5.21769826079999e-06,
121
- "max": 0.00029345280218239997,
122
- "count": 47
123
  },
124
  "SnowballTarget.Policy.Epsilon.mean": {
125
- "value": 0.1017392,
126
- "min": 0.1017392,
127
- "max": 0.19781760000000007,
128
- "count": 47
129
  },
130
  "SnowballTarget.Policy.Epsilon.sum": {
131
- "value": 0.1017392,
132
- "min": 0.1017392,
133
- "max": 0.19781760000000007,
134
- "count": 47
135
  },
136
  "SnowballTarget.Policy.Beta.mean": {
137
- "value": 9.678607999999981e-05,
138
- "min": 9.678607999999981e-05,
139
- "max": 0.004891098240000002,
140
- "count": 47
141
  },
142
  "SnowballTarget.Policy.Beta.sum": {
143
- "value": 9.678607999999981e-05,
144
- "min": 9.678607999999981e-05,
145
- "max": 0.004891098240000002,
146
- "count": 47
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1735995543",
152
  "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.5.1+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1735996536"
160
  },
161
- "total": 993.28940263,
162
  "count": 1,
163
- "self": 0.4245706540000356,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.056337170000006154,
167
  "count": 1,
168
- "self": 0.056337170000006154
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 992.808494806,
172
  "count": 1,
173
- "self": 0.9585018079978909,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 1.9245968129999937,
177
  "count": 1,
178
- "self": 1.9245968129999937
179
  },
180
  "TrainerController.advance": {
181
- "total": 989.8385282080022,
182
- "count": 45464,
183
- "self": 0.9712684860089666,
184
  "children": {
185
  "env_step": {
186
- "total": 774.9790556860028,
187
- "count": 45464,
188
- "self": 590.8048344499957,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 183.58603823599964,
192
- "count": 45464,
193
- "self": 3.256037505008635,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 180.330000730991,
197
- "count": 45464,
198
- "self": 180.330000730991
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.5881830000073478,
204
- "count": 45464,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 989.5127421100162,
209
- "count": 45464,
210
  "is_parallel": true,
211
- "self": 472.04015061402083,
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": 0.0027205869999988863,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0008482860000640358,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0018723009999348506,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0018723009999348506
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.035676571000010426,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0007358680000493223,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00040279299997791895,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00040279299997791895
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03248728099998743,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03248728099998743
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0020506289999957517,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0003799519999461154,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0016706770000496363,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0016706770000496363
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 517.4725914959954,
271
- "count": 45463,
272
  "is_parallel": true,
273
- "self": 25.08902946298963,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 13.955431312991777,
277
- "count": 45463,
278
  "is_parallel": true,
279
- "self": 13.955431312991777
280
  },
281
  "communicator.exchange": {
282
- "total": 395.8330503900043,
283
- "count": 45463,
284
  "is_parallel": true,
285
- "self": 395.8330503900043
286
  },
287
  "steps_from_proto": {
288
- "total": 82.5950803300097,
289
- "count": 45463,
290
  "is_parallel": true,
291
- "self": 14.943817725006454,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 67.65126260500324,
295
- "count": 454630,
296
  "is_parallel": true,
297
- "self": 67.65126260500324
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 213.8882040359905,
311
- "count": 45464,
312
- "self": 1.0506595439910598,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 73.19176906499933,
316
- "count": 45464,
317
- "self": 72.10983122599907,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 1.0819378390002612,
321
- "count": 10,
322
- "self": 1.0819378390002612
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 139.6457754270001,
328
- "count": 47,
329
- "self": 96.88497372299588,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 42.76080170400422,
333
- "count": 2856,
334
- "self": 42.76080170400422
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 1.0310000106983352e-06,
344
  "count": 1,
345
- "self": 1.0310000106983352e-06
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.08686694599987277,
349
  "count": 1,
350
- "self": 0.0009152679997441737,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.0859516780001286,
354
  "count": 1,
355
- "self": 0.0859516780001286
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.9545086026191711,
6
+ "min": 0.9391207695007324,
7
+ "max": 1.0479693412780762,
8
+ "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 9743.6240234375,
12
+ "min": 9086.201171875,
13
+ "max": 10697.6708984375,
14
+ "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 699960.0,
18
+ "min": 509992.0,
19
+ "max": 699960.0,
20
+ "count": 20
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 699960.0,
24
+ "min": 509992.0,
25
+ "max": 699960.0,
26
+ "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.043752670288086,
30
+ "min": 11.944348335266113,
31
+ "max": 13.043752670288086,
32
+ "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2543.53173828125,
36
+ "min": 2305.25927734375,
37
+ "max": 2657.7587890625,
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": 26.068181818181817,
54
+ "min": 24.795454545454547,
55
+ "max": 26.204545454545453,
56
+ "count": 20
57
  },
58
  "SnowballTarget.Environment.CumulativeReward.sum": {
59
+ "value": 1147.0,
60
+ "min": 1091.0,
61
+ "max": 1435.0,
62
+ "count": 20
63
  },
64
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
+ "value": 26.068181818181817,
66
+ "min": 24.795454545454547,
67
+ "max": 26.204545454545453,
68
+ "count": 20
69
  },
70
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
+ "value": 1147.0,
72
+ "min": 1091.0,
73
+ "max": 1435.0,
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": 0.035822989675216375,
90
+ "min": 0.02571102942974903,
91
+ "max": 0.042859831821018206,
92
+ "count": 19
93
  },
94
  "SnowballTarget.Losses.PolicyLoss.sum": {
95
+ "value": 0.035822989675216375,
96
+ "min": 0.02571102942974903,
97
+ "max": 0.042859831821018206,
98
+ "count": 19
99
  },
100
  "SnowballTarget.Losses.ValueLoss.mean": {
101
+ "value": 0.20447064662973086,
102
+ "min": 0.1857440204374374,
103
+ "max": 0.22445170631011327,
104
+ "count": 19
105
  },
106
  "SnowballTarget.Losses.ValueLoss.sum": {
107
+ "value": 0.20447064662973086,
108
+ "min": 0.1857440204374374,
109
+ "max": 0.22445170631011327,
110
+ "count": 19
111
  },
112
  "SnowballTarget.Policy.LearningRate.mean": {
113
+ "value": 5.109569725714209e-07,
114
+ "min": 5.109569725714209e-07,
115
+ "max": 8.09932158594286e-05,
116
+ "count": 19
117
  },
118
  "SnowballTarget.Policy.LearningRate.sum": {
119
+ "value": 5.109569725714209e-07,
120
+ "min": 5.109569725714209e-07,
121
+ "max": 8.09932158594286e-05,
122
+ "count": 19
123
  },
124
  "SnowballTarget.Policy.Epsilon.mean": {
125
+ "value": 0.10017028571428567,
126
+ "min": 0.10017028571428567,
127
+ "max": 0.1269977142857143,
128
+ "count": 19
129
  },
130
  "SnowballTarget.Policy.Epsilon.sum": {
131
+ "value": 0.10017028571428567,
132
+ "min": 0.10017028571428567,
133
+ "max": 0.1269977142857143,
134
+ "count": 19
135
  },
136
  "SnowballTarget.Policy.Beta.mean": {
137
+ "value": 1.849725714285702e-05,
138
+ "min": 1.849725714285702e-05,
139
+ "max": 0.001357185942857142,
140
+ "count": 19
141
  },
142
  "SnowballTarget.Policy.Beta.sum": {
143
+ "value": 1.849725714285702e-05,
144
+ "min": 1.849725714285702e-05,
145
+ "max": 0.001357185942857142,
146
+ "count": 19
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1735996791",
152
  "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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 --resume",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.5.1+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1735997191"
160
  },
161
+ "total": 399.9202619810003,
162
  "count": 1,
163
+ "self": 0.4796982510004,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.0578861000001325,
167
  "count": 1,
168
+ "self": 0.0578861000001325
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 399.38267762999976,
172
  "count": 1,
173
+ "self": 0.3915310579748166,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 1.9863931160000448,
177
  "count": 1,
178
+ "self": 1.9863931160000448
179
  },
180
  "TrainerController.advance": {
181
+ "total": 396.91193451302524,
182
+ "count": 18192,
183
+ "self": 0.4041940640381654,
184
  "children": {
185
  "env_step": {
186
+ "total": 313.65146303799315,
187
+ "count": 18192,
188
+ "self": 237.38310407998324,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 76.02799335198642,
192
+ "count": 18192,
193
+ "self": 1.3212031129937714,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 74.70679023899265,
197
+ "count": 18192,
198
+ "self": 74.70679023899265
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.240365606023488,
204
+ "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 397.9537662330033,
209
+ "count": 18192,
210
  "is_parallel": true,
211
+ "self": 190.60895667900672,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.002276298999959181,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.000686218000282679,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.001590080999676502,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.001590080999676502
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.03597535900007642,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0007059810000100697,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004053479999583942,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004053479999583942
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.032811723000122583,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.032811723000122583
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.002052306999985376,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0003964780003116175,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0016558289996737585,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0016558289996737585
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 207.34480955399658,
271
+ "count": 18191,
272
  "is_parallel": true,
273
+ "self": 10.10729122898806,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.548815729996477,
277
+ "count": 18191,
278
  "is_parallel": true,
279
+ "self": 5.548815729996477
280
  },
281
  "communicator.exchange": {
282
+ "total": 158.47915548401443,
283
+ "count": 18191,
284
  "is_parallel": true,
285
+ "self": 158.47915548401443
286
  },
287
  "steps_from_proto": {
288
+ "total": 33.20954711099762,
289
+ "count": 18191,
290
  "is_parallel": true,
291
+ "self": 6.0152952949040355,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 27.194251816093583,
295
+ "count": 181910,
296
  "is_parallel": true,
297
+ "self": 27.194251816093583
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 82.85627741099393,
311
+ "count": 18192,
312
+ "self": 0.43775320799977635,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 26.99354049599424,
316
+ "count": 18192,
317
+ "self": 26.54805537999414,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.4454851160000999,
321
+ "count": 4,
322
+ "self": 0.4454851160000999
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 55.42498370699991,
328
+ "count": 19,
329
+ "self": 37.852424140002086,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 17.572559566997825,
333
+ "count": 1155,
334
+ "self": 17.572559566997825
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 8.659999366500415e-07,
344
  "count": 1,
345
+ "self": 8.659999366500415e-07
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.09281807699971978,
349
  "count": 1,
350
+ "self": 0.0011537249997672916,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.09166435199995249,
354
  "count": 1,
355
+ "self": 0.09166435199995249
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -1,51 +1,6 @@
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
4
- {
5
- "steps": 99960,
6
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.onnx",
7
- "reward": 11.818181818181818,
8
- "creation_time": 1735995742.583181,
9
- "auxillary_file_paths": [
10
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.pt"
11
- ]
12
- },
13
- {
14
- "steps": 149984,
15
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
16
- "reward": 14.045454545454545,
17
- "creation_time": 1735995840.8040826,
18
- "auxillary_file_paths": [
19
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.pt"
20
- ]
21
- },
22
- {
23
- "steps": 199984,
24
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
25
- "reward": null,
26
- "creation_time": 1735995940.2837977,
27
- "auxillary_file_paths": [
28
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.pt"
29
- ]
30
- },
31
- {
32
- "steps": 249944,
33
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-249944.onnx",
34
- "reward": 19.15909090909091,
35
- "creation_time": 1735996037.2722485,
36
- "auxillary_file_paths": [
37
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-249944.pt"
38
- ]
39
- },
40
- {
41
- "steps": 299968,
42
- "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-299968.onnx",
43
- "reward": 20.636363636363637,
44
- "creation_time": 1735996138.734955,
45
- "auxillary_file_paths": [
46
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-299968.pt"
47
- ]
48
- },
49
  {
50
  "steps": 349992,
51
  "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-349992.onnx",
@@ -90,15 +45,60 @@
90
  "auxillary_file_paths": [
91
  "results/SnowballTarget2/SnowballTarget/SnowballTarget-500104.pt"
92
  ]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
93
  }
94
  ],
95
  "final_checkpoint": {
96
- "steps": 500104,
97
  "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
98
- "reward": 24.681818181818183,
99
- "creation_time": 1735996536.097647,
100
  "auxillary_file_paths": [
101
- "results/SnowballTarget2/SnowballTarget/SnowballTarget-500104.pt"
102
  ]
103
  }
104
  },
 
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  {
5
  "steps": 349992,
6
  "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-349992.onnx",
 
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget2/SnowballTarget/SnowballTarget-500104.pt"
47
  ]
48
+ },
49
+ {
50
+ "steps": 549976,
51
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-549976.onnx",
52
+ "reward": 24.757575757575758,
53
+ "creation_time": 1735996891.9949698,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-549976.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 599936,
60
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-599936.onnx",
61
+ "reward": 26.181818181818183,
62
+ "creation_time": 1735996992.509469,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-599936.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 649960,
69
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-649960.onnx",
70
+ "reward": 25.636363636363637,
71
+ "creation_time": 1735997092.3204386,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-649960.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 699960,
78
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-699960.onnx",
79
+ "reward": null,
80
+ "creation_time": 1735997190.804446,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-699960.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 700216,
87
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-700216.onnx",
88
+ "reward": null,
89
+ "creation_time": 1735997190.9208763,
90
+ "auxillary_file_paths": [
91
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-700216.pt"
92
+ ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 700216,
97
  "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
98
+ "reward": null,
99
+ "creation_time": 1735997190.9208763,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-700216.pt"
102
  ]
103
  }
104
  },