Hugging Face's logo

hartman23
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
hartman23 commited on
Commit
1ec3516
·
verified ·
1 Parent(s): a014b2f

Add first optimized SnowbalThrower

Browse files
Files changed (18) hide show
  1. SnowballTarget.onnx +2 -2
  2. SnowballTarget/SnowballTarget-149984.onnx +2 -2
  3. SnowballTarget/SnowballTarget-149984.pt +2 -2
  4. SnowballTarget/SnowballTarget-199984.onnx +2 -2
  5. SnowballTarget/SnowballTarget-199984.pt +2 -2
  6. SnowballTarget/SnowballTarget-200184.onnx +2 -2
  7. SnowballTarget/SnowballTarget-200184.pt +2 -2
  8. SnowballTarget/SnowballTarget-49936.onnx +2 -2
  9. SnowballTarget/SnowballTarget-49936.pt +2 -2
  10. SnowballTarget/SnowballTarget-99960.onnx +2 -2
  11. SnowballTarget/SnowballTarget-99960.pt +2 -2
  12. SnowballTarget/checkpoint.pt +2 -2
  13. SnowballTarget/events.out.tfevents.1734712357.e5f9a005203d.18978.0 +3 -0
  14. config.json +1 -1
  15. configuration.yaml +11 -11
  16. run_logs/Player-0.log +15 -15
  17. run_logs/timers.json +131 -131
  18. run_logs/training_status.json +21 -21
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b81e5a96df91d78c21dcb723c7251ce2f2871f7ffc3f783878871bc524523c7
3
- size 485667
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da0f3b9a9bc306c307a978cfd73e9c2084ca146bef25aafa1f4d82d40214308d
3
+ size 941878
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5fb9cbf686798d422f938a4f0b62c9d4806928721ff2c0209883d62e98d5211f
3
- size 485667
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f647896f05b419ed790eae5f2da6f8ae3ac56218c24a40ad80005f888ac0f63
3
+ size 941878
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e3d6fbdd67caf05b08b9fab003ef13f159021b6a519112727a8cc16eda532e0
3
- size 2864907
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6175eba23ea975648028fe35e02ea47d204d458f3301d2bcf314e4fac7595431
3
+ size 5589211
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b81e5a96df91d78c21dcb723c7251ce2f2871f7ffc3f783878871bc524523c7
3
- size 485667
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da0f3b9a9bc306c307a978cfd73e9c2084ca146bef25aafa1f4d82d40214308d
3
+ size 941878
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9eb982a4bd7a43e2aac177971aed0e71eb41ed72b6a6c076dd8e937941baa7a0
3
- size 2864907
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2820445ee639abc23e56b3c4d4d941c40e1a8710f8af7024bb645679d6f48642
3
+ size 5589211
SnowballTarget/SnowballTarget-200184.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b81e5a96df91d78c21dcb723c7251ce2f2871f7ffc3f783878871bc524523c7
3
- size 485667
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da0f3b9a9bc306c307a978cfd73e9c2084ca146bef25aafa1f4d82d40214308d
3
+ size 941878
SnowballTarget/SnowballTarget-200184.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2ebdd82b5201968002d9c22ff1b360cea64ead8c34240ddb273d7824f3712d5
3
- size 2864907
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee42bd14f998083bd5d0d527642b1f7de329388db82eac42c29d00e682b025b2
3
+ size 5589211
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2e0cb13d4886516279a9d5357cb710a8f35290543600d5096ccefb98b1ed85c
3
- size 485667
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2d339482a6216fcf42bf72f731dd4e877d1d5f2ceb1af77fa75c6f587890e67
3
+ size 941878
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:267aa29e03f202a520aa6519639bf0b81edf1e69ea1a0cf924e5aa4721f81afc
3
- size 2864816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d97ba229b2fb42e9b779f495890e863ce1acf332f10653f30c3e554f2c40e7bd
3
+ size 5589136
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:070ae9dfdd9a37d0ca6643f1b193e05e5be93d2b8e50e0a2d4010ac900e43268
3
- size 485667
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2a6a8626f6a21da48ee65652b9595649c80bdfc5f51609589342986d8c72a75
3
+ size 941878
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ef0c20427fab80137874adc9a3297a1373c35e565ad17011b9e2c2597341139
3
- size 2864816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9012dd0af101791e7c6d7182ef5e8bd118a5853791c86f1e2a3dd83213242c3d
3
+ size 5589136
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7fece49937c7e0c00f62c1148ee66ac3ed4cc03387fc5e5c9ddc7c98a09fed37
3
- size 2863906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99088051f9ae6668e52fa3b18e71c1707a07952b9bc4164d4bba0970471066fd
3
+ size 5588386
SnowballTarget/events.out.tfevents.1734712357.e5f9a005203d.18978.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bc9e810da77196cf7858f1b35bc25935bf4cea377e5ad03bc16d6e95c1b3636
3
+ size 30177
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 129, "buffer_size": 1172, "learning_rate": 0.005848717855174421, "beta": 0.0006933626020387194, "epsilon": 0.0015104254518785796, "lambd": 0.9809480780691303, "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": 168, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.9417107177844183, "strength": 0.9576267730399072, "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, "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": "SnowballTarget11", "initialize_from": null, "load_model": false, "resume": false, "force": true, "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": 255, "buffer_size": 1051, "learning_rate": 0.0033585016653676788, "beta": 0.04458576263259719, "epsilon": 0.06481103071316076, "lambd": 0.9200382214218608, "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": 332, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.9344680687013123, "strength": 0.7743161246844508, "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, "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": "SnowballTarget14", "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
@@ -3,12 +3,12 @@ behaviors:
3
  SnowballTarget:
4
  trainer_type: ppo
5
  hyperparameters:
6
- batch_size: 129
7
- buffer_size: 1172
8
- learning_rate: 0.005848717855174421
9
- beta: 0.0006933626020387194
10
- epsilon: 0.0015104254518785796
11
- lambd: 0.9809480780691303
12
  num_epoch: 3
13
  shared_critic: false
14
  learning_rate_schedule: linear
@@ -17,16 +17,16 @@ behaviors:
17
  checkpoint_interval: 50000
18
  network_settings:
19
  normalize: false
20
- hidden_units: 168
21
- num_layers: 3
22
  vis_encode_type: simple
23
  memory: null
24
  goal_conditioning_type: hyper
25
  deterministic: false
26
  reward_signals:
27
  extrinsic:
28
- gamma: 0.9417107177844183
29
- strength: 0.9576267730399072
30
  network_settings:
31
  normalize: false
32
  hidden_units: 128
@@ -66,7 +66,7 @@ engine_settings:
66
  no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
- run_id: SnowballTarget11
70
  initialize_from: null
71
  load_model: false
72
  resume: false
 
3
  SnowballTarget:
4
  trainer_type: ppo
5
  hyperparameters:
6
+ batch_size: 255
7
+ buffer_size: 1051
8
+ learning_rate: 0.0033585016653676788
9
+ beta: 0.04458576263259719
10
+ epsilon: 0.06481103071316076
11
+ lambd: 0.9200382214218608
12
  num_epoch: 3
13
  shared_critic: false
14
  learning_rate_schedule: linear
 
17
  checkpoint_interval: 50000
18
  network_settings:
19
  normalize: false
20
+ hidden_units: 332
21
+ num_layers: 2
22
  vis_encode_type: simple
23
  memory: null
24
  goal_conditioning_type: hyper
25
  deterministic: false
26
  reward_signals:
27
  extrinsic:
28
+ gamma: 0.9344680687013123
29
+ strength: 0.7743161246844508
30
  network_settings:
31
  normalize: false
32
  hidden_units: 128
 
66
  no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
+ run_id: SnowballTarget14
70
  initialize_from: null
71
  load_model: false
72
  resume: 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 0.153 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: 0.754228 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]: 5371 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
@@ -166,22 +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 37
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
173
  Peak Allocated bytes 1.0 MB
174
  [ALLOC_DEFAULT_MAIN]
175
- Peak usage frame count: [4.0 MB-8.0 MB]: 5463 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
- Peak Allocated memory 6.7 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
- Peak usage frame count: [16.0 MB-32.0 MB]: 5463 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]: 5058 frames, [64.0 KB-128.0 KB]: 405 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
- Peak Allocated memory 66.4 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
- Peak usage frame count: [32.0 KB-64.0 KB]: 5463 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]: 5463 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]: 5462 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]: 5463 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]: 5463 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 0.107 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: 0.934545 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]: 5373 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 43
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]: 5465 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 6.9 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5465 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.6 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]: 4848 frames, [64.0 KB-128.0 KB]: 617 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]: 5465 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]: 5465 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]: 5464 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]: 5465 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]: 5465 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": 1.6439284086227417,
6
- "min": 1.6439284086227417,
7
- "max": 2.8902804851531982,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 15840.89453125,
12
- "min": 15840.89453125,
13
- "max": 29758.328125,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 1.9428905248641968,
30
- "min": 0.1823497712612152,
31
- "max": 1.9428905248641968,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 378.8636474609375,
36
- "min": 35.3758544921875,
37
- "max": 380.93072509765625,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,87 +50,87 @@
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06267216122382648,
54
- "min": 0.055472424205818945,
55
- "max": 0.07582000890679685,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.43870512856678534,
60
- "min": 0.3883069694407326,
61
- "max": 0.5136208887223149,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.136476278666294,
66
- "min": 0.058655292562828594,
67
- "max": 0.16762607907513521,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.9553339506640579,
72
- "min": 0.41058704793980016,
73
- "max": 1.1733825535259466,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 0.00014598409516915355,
78
- "min": 0.00014598409516915355,
79
- "max": 0.005700316389999796,
80
  "count": 20
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 0.0010218886661840748,
84
- "min": 0.0010218886661840748,
85
- "max": 0.037950692572355366,
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.09754170021927888,
90
- "min": 0.004009434256746251,
91
- "max": 0.09754170021927888,
92
  "count": 20
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.6827919015349522,
96
- "min": 0.024056605540477505,
97
- "max": 0.6827919015349522,
98
  "count": 20
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
- "value": 2.7056730546886436e-05,
102
- "min": 2.7056730546886436e-05,
103
- "max": 0.0006760234149496571,
104
  "count": 20
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.00018939711382820506,
108
- "min": 0.00018939711382820506,
109
- "max": 0.00450414858310068,
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 23.386363636363637,
114
- "min": 2.6545454545454548,
115
- "max": 23.386363636363637,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1029.0,
120
- "min": 124.0,
121
- "max": 1227.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 22.395407249981705,
126
- "min": 2.54206375208768,
127
- "max": 22.395407249981705,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 985.3979189991951,
132
- "min": 118.74571794271469,
133
- "max": 1175.0080181956291,
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": "1734645837",
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=SnowballTarget11 --no-graphics --force",
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": "1734646329"
160
  },
161
- "total": 492.4546862169991,
162
  "count": 1,
163
- "self": 0.5267043589992682,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.10980674199890927,
167
  "count": 1,
168
- "self": 0.10980674199890927
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 491.81817511600093,
172
  "count": 1,
173
- "self": 0.8021783462972962,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 2.2097316759973182,
177
  "count": 1,
178
- "self": 2.2097316759973182
179
  },
180
  "TrainerController.advance": {
181
- "total": 488.7256403117026,
182
- "count": 18209,
183
- "self": 0.372184840925911,
184
  "children": {
185
  "env_step": {
186
- "total": 488.3534554707767,
187
- "count": 18209,
188
- "self": 361.6315583955293,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 126.34392291447875,
192
- "count": 18209,
193
- "self": 2.022507725367177,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 124.32141518911158,
197
- "count": 18209,
198
- "self": 124.32141518911158
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.37797416076864465,
204
- "count": 18209,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 490.0476761838072,
209
- "count": 18209,
210
  "is_parallel": true,
211
- "self": 216.11597017761596,
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": 0.0025727829997777008,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0007713410050200764,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0018014419947576243,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0018014419947576243
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.04092625699922792,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0008045159993343987,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.000446805999672506,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.000446805999672506
244
  },
245
  "communicator.exchange": {
246
- "total": 0.037390420999145135,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.037390420999145135
250
  },
251
  "steps_from_proto": {
252
- "total": 0.002284514001075877,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0004699480050476268,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.00181456599602825,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.00181456599602825
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 273.93170600619123,
271
- "count": 18208,
272
  "is_parallel": true,
273
- "self": 12.34132495736776,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 6.28572836901003,
277
- "count": 18208,
278
  "is_parallel": true,
279
- "self": 6.28572836901003
280
  },
281
  "communicator.exchange": {
282
- "total": 215.35456801667533,
283
- "count": 18208,
284
  "is_parallel": true,
285
- "self": 215.35456801667533
286
  },
287
  "steps_from_proto": {
288
- "total": 39.950084663138114,
289
- "count": 18208,
290
  "is_parallel": true,
291
- "self": 7.68151135008884,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 32.268573313049274,
295
- "count": 182080,
296
  "is_parallel": true,
297
- "self": 32.268573313049274
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.0003680500012706034,
313
  "count": 1,
314
- "self": 0.0003680500012706034,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 485.92623232954793,
324
- "count": 372338,
325
  "is_parallel": true,
326
- "self": 8.142840825508756,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 182.39031493504444,
330
- "count": 372338,
331
  "is_parallel": true,
332
- "self": 181.79515693904614,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 0.5951579959983064,
336
  "count": 4,
337
  "is_parallel": true,
338
- "self": 0.5951579959983064
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 295.39307656899473,
344
- "count": 136,
345
  "is_parallel": true,
346
- "self": 83.54235101915401,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 211.85072554984072,
350
- "count": 4353,
351
  "is_parallel": true,
352
- "self": 211.85072554984072
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.08025673200245365,
364
  "count": 1,
365
- "self": 0.0012775960021826904,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.07897913600027096,
369
  "count": 1,
370
- "self": 0.07897913600027096
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 1.602304458618164,
6
+ "min": 1.602304458618164,
7
+ "max": 2.8853836059570312,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 15475.056640625,
12
+ "min": 15475.056640625,
13
+ "max": 29549.212890625,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 1.462786078453064,
30
+ "min": 0.20903053879737854,
31
+ "max": 1.462786078453064,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 285.2432861328125,
36
+ "min": 40.55192565917969,
37
+ "max": 295.2460021972656,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.04278062743071046,
54
+ "min": 0.03740328233245583,
55
+ "max": 0.05381372995640656,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.2994643920149732,
60
+ "min": 0.25109103050393367,
61
+ "max": 0.3492709052506447,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.064781530272393,
66
+ "min": 0.0370886461454488,
67
+ "max": 0.09625423115988573,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.45347071190675103,
72
+ "min": 0.2596205230181416,
73
+ "max": 0.5775253869593143,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 8.382829907157725e-05,
78
+ "min": 8.382829907157725e-05,
79
+ "max": 0.0032732852856490837,
80
  "count": 20
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 0.0005867980935010407,
84
+ "min": 0.0005867980935010407,
85
+ "max": 0.021797750579737155,
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.09912168332660047,
90
+ "min": 0.06570389216053214,
91
+ "max": 0.09912168332660047,
92
  "count": 20
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.6938517832862033,
96
+ "min": 0.3942233529631929,
97
+ "max": 0.6938517832862033,
98
  "count": 20
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 0.0011226110353096256,
102
+ "min": 0.0011226110353096256,
103
+ "max": 0.04345472694873276,
104
  "count": 20
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.007858277247167379,
108
+ "min": 0.007858277247167379,
109
+ "max": 0.2893809637295982,
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 24.386363636363637,
114
+ "min": 3.022727272727273,
115
+ "max": 24.386363636363637,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1073.0,
120
+ "min": 133.0,
121
+ "max": 1335.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 18.882754775610838,
126
+ "min": 2.3405465077270162,
127
+ "max": 18.882754775610838,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 830.8412101268768,
132
+ "min": 102.98404633998871,
133
+ "max": 1033.712035536766,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1734712356",
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=SnowballTarget14 --no-graphics --force",
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": "1734712934"
160
  },
161
+ "total": 578.3493716190005,
162
  "count": 1,
163
+ "self": 1.054238938000708,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.0741157310003473,
167
  "count": 1,
168
+ "self": 0.0741157310003473
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 577.2210169499995,
172
  "count": 1,
173
+ "self": 1.023016461919724,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.221277755000301,
177
  "count": 1,
178
+ "self": 3.221277755000301
179
  },
180
  "TrainerController.advance": {
181
+ "total": 572.8177740130795,
182
+ "count": 18215,
183
+ "self": 0.4886110569404991,
184
  "children": {
185
  "env_step": {
186
+ "total": 572.329162956139,
187
+ "count": 18215,
188
+ "self": 412.958888128067,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 158.93467012807014,
192
+ "count": 18215,
193
+ "self": 3.019371363108803,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 155.91529876496134,
197
+ "count": 18215,
198
+ "self": 155.91529876496134
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.43560470000193163,
204
+ "count": 18215,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 574.958547064989,
209
+ "count": 18215,
210
  "is_parallel": true,
211
+ "self": 249.5135799089685,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.003545269999449374,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0008927559983931133,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.002652514001056261,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.002652514001056261
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.1095645350005725,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0008891070010577096,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00045683400003326824,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00045683400003326824
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.10594400099944323,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.10594400099944323
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.002274593000038294,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0004177509981673211,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.001856842001870973,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.001856842001870973
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 325.44496715602054,
271
+ "count": 18214,
272
  "is_parallel": true,
273
+ "self": 15.366280455989,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 7.844114936006918,
277
+ "count": 18214,
278
  "is_parallel": true,
279
+ "self": 7.844114936006918
280
  },
281
  "communicator.exchange": {
282
+ "total": 255.65704095400451,
283
+ "count": 18214,
284
  "is_parallel": true,
285
+ "self": 255.65704095400451
286
  },
287
  "steps_from_proto": {
288
+ "total": 46.57753081002011,
289
+ "count": 18214,
290
  "is_parallel": true,
291
+ "self": 9.352727159182905,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 37.2248036508372,
295
+ "count": 182140,
296
  "is_parallel": true,
297
+ "self": 37.2248036508372
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.0003579949998311349,
313
  "count": 1,
314
+ "self": 0.0003579949998311349,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 568.5701288763703,
324
+ "count": 516846,
325
  "is_parallel": true,
326
+ "self": 12.44683584858194,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 251.86072053578755,
330
+ "count": 516846,
331
  "is_parallel": true,
332
+ "self": 250.94444069578822,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 0.9162798399993335,
336
  "count": 4,
337
  "is_parallel": true,
338
+ "self": 0.9162798399993335
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 304.2625724920008,
344
+ "count": 137,
345
  "is_parallel": true,
346
+ "self": 84.32923142198342,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 219.93334107001738,
350
+ "count": 2046,
351
  "is_parallel": true,
352
+ "self": 219.93334107001738
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.15859072500006732,
364
  "count": 1,
365
+ "self": 0.0022051480000300216,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.1563855770000373,
369
  "count": 1,
370
+ "self": 0.1563855770000373
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -3,57 +3,57 @@
3
  "checkpoints": [
4
  {
5
  "steps": 49936,
6
- "file_path": "results/SnowballTarget11/SnowballTarget/SnowballTarget-49936.onnx",
7
  "reward": null,
8
- "creation_time": 1734645962.7687764,
9
  "auxillary_file_paths": [
10
- "results/SnowballTarget11/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
12
  },
13
  {
14
  "steps": 99960,
15
- "file_path": "results/SnowballTarget11/SnowballTarget/SnowballTarget-99960.onnx",
16
  "reward": null,
17
- "creation_time": 1734646085.8705854,
18
  "auxillary_file_paths": [
19
- "results/SnowballTarget11/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
21
  },
22
  {
23
  "steps": 149984,
24
- "file_path": "results/SnowballTarget11/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 17.272727272727273,
26
- "creation_time": 1734646206.798937,
27
  "auxillary_file_paths": [
28
- "results/SnowballTarget11/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
30
  },
31
  {
32
  "steps": 199984,
33
- "file_path": "results/SnowballTarget11/SnowballTarget/SnowballTarget-199984.onnx",
34
  "reward": null,
35
- "creation_time": 1734646329.3024094,
36
  "auxillary_file_paths": [
37
- "results/SnowballTarget11/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
  "steps": 200184,
42
- "file_path": "results/SnowballTarget11/SnowballTarget/SnowballTarget-200184.onnx",
43
- "reward": 23.88888888888889,
44
- "creation_time": 1734646329.4213703,
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget11/SnowballTarget/SnowballTarget-200184.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
  "steps": 200184,
52
- "file_path": "results/SnowballTarget11/SnowballTarget.onnx",
53
- "reward": 23.88888888888889,
54
- "creation_time": 1734646329.4213703,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget11/SnowballTarget/SnowballTarget-200184.pt"
57
  ]
58
  }
59
  },
 
3
  "checkpoints": [
4
  {
5
  "steps": 49936,
6
+ "file_path": "results/SnowballTarget14/SnowballTarget/SnowballTarget-49936.onnx",
7
  "reward": null,
8
+ "creation_time": 1734712502.5868247,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget14/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
12
  },
13
  {
14
  "steps": 99960,
15
+ "file_path": "results/SnowballTarget14/SnowballTarget/SnowballTarget-99960.onnx",
16
  "reward": null,
17
+ "creation_time": 1734712646.3182104,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget14/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
21
  },
22
  {
23
  "steps": 149984,
24
+ "file_path": "results/SnowballTarget14/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 18.90909090909091,
26
+ "creation_time": 1734712788.6093626,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget14/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
30
  },
31
  {
32
  "steps": 199984,
33
+ "file_path": "results/SnowballTarget14/SnowballTarget/SnowballTarget-199984.onnx",
34
  "reward": null,
35
+ "creation_time": 1734712933.5976007,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget14/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
  "steps": 200184,
42
+ "file_path": "results/SnowballTarget14/SnowballTarget/SnowballTarget-200184.onnx",
43
+ "reward": 24.666666666666668,
44
+ "creation_time": 1734712933.8229642,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget14/SnowballTarget/SnowballTarget-200184.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
  "steps": 200184,
52
+ "file_path": "results/SnowballTarget14/SnowballTarget.onnx",
53
+ "reward": 24.666666666666668,
54
+ "creation_time": 1734712933.8229642,
55
  "auxillary_file_paths": [
56
+ "results/SnowballTarget14/SnowballTarget/SnowballTarget-200184.pt"
57
  ]
58
  }
59
  },