Hugging Face's logo

CzarnyRycerz
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
 Metrics Community
CzarnyRycerz commited on
Commit
8904cf9
·
1 Parent(s): 1fa0fc8

First Push

Browse files
Files changed (21) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-249976.onnx +3 -0
  3. SnowballTarget/SnowballTarget-249976.pt +3 -0
  4. SnowballTarget/SnowballTarget-299936.onnx +3 -0
  5. SnowballTarget/SnowballTarget-299936.pt +3 -0
  6. SnowballTarget/SnowballTarget-300128.onnx +3 -0
  7. SnowballTarget/SnowballTarget-300128.pt +3 -0
  8. SnowballTarget/SnowballTarget-349936.onnx +3 -0
  9. SnowballTarget/SnowballTarget-349936.pt +3 -0
  10. SnowballTarget/SnowballTarget-399960.onnx +3 -0
  11. SnowballTarget/SnowballTarget-399960.pt +3 -0
  12. SnowballTarget/SnowballTarget-400536.onnx +3 -0
  13. SnowballTarget/SnowballTarget-400536.pt +3 -0
  14. SnowballTarget/checkpoint.pt +1 -1
  15. SnowballTarget/events.out.tfevents.1693976214.facb3874e344.8826.0 +3 -0
  16. SnowballTarget/events.out.tfevents.1693977055.facb3874e344.12316.0 +3 -0
  17. config.json +1 -1
  18. configuration.yaml +1 -1
  19. run_logs/Player-0.log +15 -15
  20. run_logs/timers.json +161 -161
  21. run_logs/training_status.json +58 -49
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ae7195212f5c6158ac3ae715ac19cb220858fff74a2f7dabd0025c8c612abd3
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ca7f4faf05257ead741ad0f4bb457f274bbacb16b2d247330024ba5f0f8840d
3
  size 646532
SnowballTarget/SnowballTarget-249976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7a485fd2617f9662d6cc7b1321c2bebc3f20224662f6e89cf6f04896a4fba35
3
+ size 646532
SnowballTarget/SnowballTarget-249976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93e3e379e202e67b7cfd6cbedeaf0bb2ae823e6a2c49e9503cd713dc8d3ddb23
3
+ size 3843968
SnowballTarget/SnowballTarget-299936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aa3b036e66bddd3e0138aac65a3fdb5051efd28c2051bd7b5db085a05880134
3
+ size 646532
SnowballTarget/SnowballTarget-299936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02518e369d4b1c073289927faed685e91950a645a5bdc797ab17108c9838573d
3
+ size 3843968
SnowballTarget/SnowballTarget-300128.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aa3b036e66bddd3e0138aac65a3fdb5051efd28c2051bd7b5db085a05880134
3
+ size 646532
SnowballTarget/SnowballTarget-300128.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcbdf2d520610083a414a2f95d755b1d3e11a5c1656bec1195191983ba9d108c
3
+ size 3843968
SnowballTarget/SnowballTarget-349936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f46cd04711ff6d7ccc01e58e73a248d43972e471d3bc87255c6de7ae6b306f41
3
+ size 646532
SnowballTarget/SnowballTarget-349936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba791a9da70b54d5168e5da63544f6185e449f435b4569408e0c932e7aecc5fc
3
+ size 3843968
SnowballTarget/SnowballTarget-399960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ca7f4faf05257ead741ad0f4bb457f274bbacb16b2d247330024ba5f0f8840d
3
+ size 646532
SnowballTarget/SnowballTarget-399960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6979f8823ca8d2978b24a4160fb760b426a5be924070feb6b7b7ee1601d0e5d
3
+ size 3843968
SnowballTarget/SnowballTarget-400536.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ca7f4faf05257ead741ad0f4bb457f274bbacb16b2d247330024ba5f0f8840d
3
+ size 646532
SnowballTarget/SnowballTarget-400536.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3378c87d7beb68bc962fc340d6945456a2cccfeb13a708c8a7d8a4a18d85b987
3
+ size 3843968
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71f1b8f754652cf83baa5ed66ede1239f3a6fb271a3aa93fd9840f1b664a262a
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3378c87d7beb68bc962fc340d6945456a2cccfeb13a708c8a7d8a4a18d85b987
3
  size 3843968
SnowballTarget/events.out.tfevents.1693976214.facb3874e344.8826.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1acf7f5020a528ad12753f90227c8f8e7157241eea87e3eaaec00b0f8df88593
3
+ size 27878
SnowballTarget/events.out.tfevents.1693977055.facb3874e344.12316.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0e2b158b23bf321190bddcf3b453e458518c3ef1f26c6261bd3e9e629ecf99f
3
+ size 27699
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 32, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 4, "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": 3000, "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": 32, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 4, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 400000, "time_horizon": 64, "summary_freq": 3000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -38,7 +38,7 @@ behaviors:
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
- max_steps: 200000
42
  time_horizon: 64
43
  summary_freq: 3000
44
  threaded: true
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 400000
42
  time_horizon: 64
43
  summary_freq: 3000
44
  threaded: true
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 0.079 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: 0.829442 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]: 4247 frames, [16.0 KB-32.0 KB]: 72 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 40
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]: 4320 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
- Peak Allocated memory 6.3 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
- Peak usage frame count: [16.0 MB-32.0 MB]: 4320 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]: 3601 frames, [64.0 KB-128.0 KB]: 719 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]: 4320 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]: 4320 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]: 4319 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]: 4320 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]: 4320 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 0.086 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: 0.643889 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]: 2695 frames, [16.0 KB-32.0 KB]: 45 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 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]: 2741 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 6.0 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 2741 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]: 2673 frames, [64.0 KB-128.0 KB]: 68 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]: 2741 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]: 2741 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]: 2740 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]: 2741 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]: 2741 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -2,153 +2,153 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.973520815372467,
6
- "min": 0.973520815372467,
7
- "max": 2.16020131111145,
8
- "count": 52
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 2848.52197265625,
12
- "min": 2848.52197265625,
13
- "max": 7174.62890625,
14
- "count": 52
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 197968.0,
18
- "min": 44952.0,
19
- "max": 197968.0,
20
- "count": 52
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 197968.0,
24
- "min": 44952.0,
25
- "max": 197968.0,
26
- "count": 52
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.948724746704102,
30
- "min": 4.858739376068115,
31
- "max": 12.948724746704102,
32
- "count": 52
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 738.0773315429688,
36
- "min": 252.65444946289062,
37
- "max": 853.0018920898438,
38
- "count": 52
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
- "count": 52
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 2189.0,
48
  "min": 2189.0,
49
  "max": 4378.0,
50
- "count": 52
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.14024724545443484,
54
- "min": 0.12285150930454299,
55
- "max": 0.15466621355945415,
56
- "count": 52
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.14024724545443484,
60
- "min": 0.12285150930454299,
61
- "max": 0.298292769715344,
62
- "count": 52
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.19191537496140776,
66
- "min": 0.16604865493033738,
67
- "max": 0.29316760281867843,
68
- "count": 52
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.19191537496140776,
72
- "min": 0.16604865493033738,
73
- "max": 0.5609768284210825,
74
- "count": 52
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 5.7720980760000106e-06,
78
- "min": 5.7720980760000106e-06,
79
- "max": 0.00023347202217599997,
80
- "count": 52
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 5.7720980760000106e-06,
84
- "min": 5.7720980760000106e-06,
85
- "max": 0.00045044404985200006,
86
- "count": 52
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.10192400000000001,
90
- "min": 0.10192400000000001,
91
- "max": 0.177824,
92
- "count": 52
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.10192400000000001,
96
- "min": 0.10192400000000001,
97
- "max": 0.350148,
98
- "count": 52
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
- "value": 0.00010600760000000018,
102
- "min": 0.00010600760000000018,
103
- "max": 0.0038934176000000017,
104
- "count": 52
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.00010600760000000018,
108
- "min": 0.00010600760000000018,
109
- "max": 0.0075123852,
110
- "count": 52
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.09090909090909,
114
- "min": 13.363636363636363,
115
- "max": 26.294117647058822,
116
- "count": 52
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 276.0,
120
- "min": 147.0,
121
- "max": 570.0,
122
- "count": 52
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.09090909090909,
126
- "min": 13.363636363636363,
127
- "max": 26.294117647058822,
128
- "count": 52
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 276.0,
132
- "min": 147.0,
133
- "max": 570.0,
134
- "count": 52
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 52
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 52
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1693975247",
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",
@@ -156,59 +156,59 @@
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
- "end_time_seconds": "1693975793"
160
  },
161
- "total": 545.700916239,
162
  "count": 1,
163
- "self": 0.4253394990000743,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.04011162200004037,
167
  "count": 1,
168
- "self": 0.04011162200004037
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 545.2354651179999,
172
  "count": 1,
173
- "self": 0.48676995201412865,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.817562704000011,
177
  "count": 1,
178
- "self": 3.817562704000011
179
  },
180
  "TrainerController.advance": {
181
- "total": 540.7769796699858,
182
- "count": 14397,
183
- "self": 0.22014425098450374,
184
  "children": {
185
  "env_step": {
186
- "total": 540.5568354190013,
187
- "count": 14397,
188
- "self": 443.73492106402205,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 96.59199142998136,
192
- "count": 14397,
193
- "self": 1.3881042679931852,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 95.20388716198818,
197
- "count": 14397,
198
- "self": 95.20388716198818
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.2299229249979362,
204
- "count": 14397,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 543.7444277739778,
209
- "count": 14397,
210
  "is_parallel": true,
211
- "self": 338.5093219339799,
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": 0.0022385030001714767,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0005634470003315073,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0016750559998399694,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0016750559998399694
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.0501824759999181,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.000425338999775704,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0004411899999468005,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0004411899999468005
244
  },
245
  "communicator.exchange": {
246
- "total": 0.046980707000102484,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.046980707000102484
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0023352400000931084,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0005317410000316158,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0018034990000614926,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0018034990000614926
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 205.2351058399979,
271
- "count": 14396,
272
  "is_parallel": true,
273
- "self": 8.602804240008027,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 4.418585109002834,
277
- "count": 14396,
278
  "is_parallel": true,
279
- "self": 4.418585109002834
280
  },
281
  "communicator.exchange": {
282
- "total": 161.50488136299327,
283
- "count": 14396,
284
  "is_parallel": true,
285
- "self": 161.50488136299327
286
  },
287
  "steps_from_proto": {
288
- "total": 30.70883512799378,
289
- "count": 14396,
290
  "is_parallel": true,
291
- "self": 5.547985514964921,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 25.16084961302886,
295
- "count": 143960,
296
  "is_parallel": true,
297
- "self": 25.16084961302886
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.0004364500000519911,
313
  "count": 1,
314
- "self": 0.0004364500000519911,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 537.5237717099917,
324
- "count": 348833,
325
  "is_parallel": true,
326
- "self": 8.33882607499163,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 206.5121035990005,
330
- "count": 348833,
331
  "is_parallel": true,
332
- "self": 205.69581619500082,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 0.816287403999695,
336
- "count": 4,
337
  "is_parallel": true,
338
- "self": 0.816287403999695
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 322.67284203599957,
344
- "count": 71,
345
  "is_parallel": true,
346
- "self": 75.03024551100725,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 247.6425965249923,
350
- "count": 19304,
351
  "is_parallel": true,
352
- "self": 247.6425965249923
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.1537163419998251,
364
  "count": 1,
365
- "self": 0.001152523999735422,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.15256381800008967,
369
  "count": 1,
370
- "self": 0.15256381800008967
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.797355592250824,
6
+ "min": 0.7581087350845337,
7
+ "max": 0.8182294368743896,
8
+ "count": 33
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 2324.29150390625,
12
+ "min": 2181.07421875,
13
+ "max": 2795.636474609375,
14
+ "count": 33
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 398976.0,
18
+ "min": 302968.0,
19
+ "max": 398976.0,
20
+ "count": 33
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 398976.0,
24
+ "min": 302968.0,
25
+ "max": 398976.0,
26
+ "count": 33
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.718708992004395,
30
+ "min": 13.261983871459961,
31
+ "max": 13.755999565124512,
32
+ "count": 33
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 781.9664306640625,
36
+ "min": 733.2086181640625,
37
+ "max": 914.442626953125,
38
+ "count": 33
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 33
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 2189.0,
48
  "min": 2189.0,
49
  "max": 4378.0,
50
+ "count": 33
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.13582518982858507,
54
+ "min": 0.12891576110397343,
55
+ "max": 0.1564085631593223,
56
+ "count": 33
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.13582518982858507,
60
+ "min": 0.12891576110397343,
61
+ "max": 0.2866393176336581,
62
+ "count": 33
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.15960697087404482,
66
+ "min": 0.13604065400603063,
67
+ "max": 0.23627591431688738,
68
+ "count": 33
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.15960697087404482,
72
+ "min": 0.13604065400603063,
73
+ "max": 0.47255182863377476,
74
+ "count": 33
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 2.370099210000006e-06,
78
+ "min": 2.370099210000006e-06,
79
+ "max": 7.332007555999997e-05,
80
+ "count": 33
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 2.370099210000006e-06,
84
+ "min": 2.370099210000006e-06,
85
+ "max": 0.00013839015387,
86
+ "count": 33
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10079000000000002,
90
+ "min": 0.10079000000000002,
91
+ "max": 0.12443999999999997,
92
+ "count": 33
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.10079000000000002,
96
+ "min": 0.10079000000000002,
97
+ "max": 0.24612999999999996,
98
+ "count": 33
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 4.942100000000011e-05,
102
+ "min": 4.942100000000011e-05,
103
+ "max": 0.001229556,
104
+ "count": 33
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 4.942100000000011e-05,
108
+ "min": 4.942100000000011e-05,
109
+ "max": 0.0023218870000000008,
110
+ "count": 33
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 28.0,
114
+ "min": 25.09090909090909,
115
+ "max": 28.0,
116
+ "count": 33
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 308.0,
120
+ "min": 276.0,
121
+ "max": 604.0,
122
+ "count": 33
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 28.0,
126
+ "min": 25.09090909090909,
127
+ "max": 28.0,
128
+ "count": 33
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 308.0,
132
+ "min": 276.0,
133
+ "max": 604.0,
134
+ "count": 33
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 33
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 33
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1693977054",
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",
 
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
+ "end_time_seconds": "1693977400"
160
  },
161
+ "total": 345.79725418,
162
  "count": 1,
163
+ "self": 0.4237240119996386,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.040160575000300014,
167
  "count": 1,
168
+ "self": 0.040160575000300014
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 345.33336959300004,
172
  "count": 1,
173
+ "self": 0.31888352497435335,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.7732079690003957,
177
  "count": 1,
178
+ "self": 3.7732079690003957
179
  },
180
  "TrainerController.advance": {
181
+ "total": 341.0883677640254,
182
+ "count": 9134,
183
+ "self": 0.13976847102185275,
184
  "children": {
185
  "env_step": {
186
+ "total": 340.94859929300355,
187
+ "count": 9134,
188
+ "self": 282.4736051970176,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 58.330774057010785,
192
+ "count": 9134,
193
+ "self": 0.8345183350256775,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 57.49625572198511,
197
+ "count": 9134,
198
+ "self": 57.49625572198511
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.14422003897516333,
204
+ "count": 9134,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 344.419517767004,
209
+ "count": 9134,
210
  "is_parallel": true,
211
+ "self": 214.39105570796164,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.001942073000009259,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0005948780003564025,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0013471949996528565,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0013471949996528565
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.05170605500006786,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006715610002174799,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0005327979997673538,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0005327979997673538
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.047981914000047254,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.047981914000047254
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.002519782000035775,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0006054520003999642,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.001914329999635811,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.001914329999635811
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 130.02846205904234,
271
+ "count": 9133,
272
  "is_parallel": true,
273
+ "self": 5.423039985051673,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 2.9251952319959855,
277
+ "count": 9133,
278
  "is_parallel": true,
279
+ "self": 2.9251952319959855
280
  },
281
  "communicator.exchange": {
282
+ "total": 102.1828211349657,
283
+ "count": 9133,
284
  "is_parallel": true,
285
+ "self": 102.1828211349657
286
  },
287
  "steps_from_proto": {
288
+ "total": 19.497405707028975,
289
+ "count": 9133,
290
  "is_parallel": true,
291
+ "self": 3.5163126480429128,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 15.981093058986062,
295
+ "count": 91330,
296
  "is_parallel": true,
297
+ "self": 15.981093058986062
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.0003787989999182173,
313
  "count": 1,
314
+ "self": 0.0003787989999182173,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 339.18571295902075,
324
+ "count": 205298,
325
  "is_parallel": true,
326
+ "self": 5.010294575976786,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 129.0157915980435,
330
+ "count": 205298,
331
  "is_parallel": true,
332
+ "self": 128.4002305150434,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 0.6155610830001024,
336
+ "count": 2,
337
  "is_parallel": true,
338
+ "self": 0.6155610830001024
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 205.15962678500046,
344
+ "count": 45,
345
  "is_parallel": true,
346
+ "self": 53.52448141699415,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 151.6351453680063,
350
+ "count": 12232,
351
  "is_parallel": true,
352
+ "self": 151.6351453680063
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.1525315359999695,
364
  "count": 1,
365
+ "self": 0.0010572880000836449,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.15147424799988585,
369
  "count": 1,
370
+ "self": 0.15147424799988585
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -1,51 +1,6 @@
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
4
- {
5
- "steps": 7304,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-7304.onnx",
7
- "reward": 4.181818181818182,
8
- "creation_time": 1693974796.9038873,
9
- "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-7304.pt"
11
- ]
12
- },
13
- {
14
- "steps": 20416,
15
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-20416.onnx",
16
- "reward": 7.181818181818182,
17
- "creation_time": 1693975094.8423986,
18
- "auxillary_file_paths": [
19
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-20416.pt"
20
- ]
21
- },
22
- {
23
- "steps": 33528,
24
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-33528.onnx",
25
- "reward": null,
26
- "creation_time": 1693975202.0202415,
27
- "auxillary_file_paths": [
28
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-33528.pt"
29
- ]
30
- },
31
- {
32
- "steps": 42240,
33
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-42240.onnx",
34
- "reward": null,
35
- "creation_time": 1693975242.9915428,
36
- "auxillary_file_paths": [
37
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-42240.pt"
38
- ]
39
- },
40
- {
41
- "steps": 49992,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49992.onnx",
43
- "reward": 14.545454545454545,
44
- "creation_time": 1693975276.9934976,
45
- "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-49992.pt"
47
- ]
48
- },
49
  {
50
  "steps": 99952,
51
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99952.onnx",
@@ -81,15 +36,69 @@
81
  "auxillary_file_paths": [
82
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200552.pt"
83
  ]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
84
  }
85
  ],
86
  "final_checkpoint": {
87
- "steps": 200552,
88
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
89
- "reward": 25.272727272727273,
90
- "creation_time": 1693975792.6364193,
91
  "auxillary_file_paths": [
92
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200552.pt"
93
  ]
94
  }
95
  },
 
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  {
5
  "steps": 99952,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99952.onnx",
 
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200552.pt"
38
  ]
39
+ },
40
+ {
41
+ "steps": 249976,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249976.onnx",
43
+ "reward": 26.09090909090909,
44
+ "creation_time": 1693976385.0726578,
45
+ "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-249976.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 299936,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299936.onnx",
52
+ "reward": 26.181818181818183,
53
+ "creation_time": 1693976554.5373092,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-299936.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 300128,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-300128.onnx",
61
+ "reward": 26.181818181818183,
62
+ "creation_time": 1693976554.7254746,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-300128.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 349936,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349936.onnx",
70
+ "reward": 26.454545454545453,
71
+ "creation_time": 1693977228.7585704,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-349936.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 399960,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399960.onnx",
79
+ "reward": 27.272727272727273,
80
+ "creation_time": 1693977400.0036075,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-399960.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 400536,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-400536.onnx",
88
+ "reward": 27.272727272727273,
89
+ "creation_time": 1693977400.228383,
90
+ "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-400536.pt"
92
+ ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 400536,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 27.272727272727273,
99
+ "creation_time": 1693977400.228383,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-400536.pt"
102
  ]
103
  }
104
  },