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
e39fb3e
·
1 Parent(s): 2522387

First Push

Browse files
Files changed (22) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-549984.onnx +3 -0
  3. SnowballTarget/SnowballTarget-549984.pt +3 -0
  4. SnowballTarget/SnowballTarget-599944.onnx +3 -0
  5. SnowballTarget/SnowballTarget-599944.pt +3 -0
  6. SnowballTarget/SnowballTarget-608656.onnx +3 -0
  7. SnowballTarget/SnowballTarget-608656.pt +3 -0
  8. SnowballTarget/SnowballTarget-639368.onnx +3 -0
  9. SnowballTarget/SnowballTarget-639368.pt +3 -0
  10. SnowballTarget/SnowballTarget-649960.onnx +3 -0
  11. SnowballTarget/SnowballTarget-649960.pt +3 -0
  12. SnowballTarget/SnowballTarget-698680.onnx +3 -0
  13. SnowballTarget/SnowballTarget-698680.pt +3 -0
  14. SnowballTarget/checkpoint.pt +1 -1
  15. SnowballTarget/events.out.tfevents.1693978579.facb3874e344.18906.0 +3 -0
  16. SnowballTarget/events.out.tfevents.1693978835.facb3874e344.20053.0 +3 -0
  17. SnowballTarget/events.out.tfevents.1693978949.facb3874e344.20593.0 +3 -0
  18. config.json +1 -1
  19. configuration.yaml +1 -1
  20. run_logs/Player-0.log +15 -15
  21. run_logs/timers.json +172 -172
  22. run_logs/training_status.json +53 -53
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:871779c3533466126d1759ceb22e7d31c2ed5c144e96c5fb70dbe7972e01759d
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33a3c4a26980a5e987705e9382b4a80368167354110af7bdcfb43dbf269c909b
3
  size 646532
SnowballTarget/SnowballTarget-549984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd8b3b37ef7858345a2cb42f9193d798c507f8b19d314ebc05d596f1e134efea
3
+ size 651247
SnowballTarget/SnowballTarget-549984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d03cc0cbe931463e9e87f937bdf0ea0f3e57db01e37f7cad028f41575f707232
3
+ size 3865766
SnowballTarget/SnowballTarget-599944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36d6acd571b8835cb0429a621e668fb384219dd49eff13351e3b907b93f1b039
3
+ size 651247
SnowballTarget/SnowballTarget-599944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9814d5c322ff95e8ef46aee9acd0423541a7d5deadf73334fcfc385bb257ebb
3
+ size 3865766
SnowballTarget/SnowballTarget-608656.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c84b8330e47449c599c42da4e7cefabbb61279f0b467f326ce229b37ce65c138
3
+ size 651247
SnowballTarget/SnowballTarget-608656.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44c3d38ac84444e429a69bcb54fcae078b233e2a64fcd921a430daab2cde42f1
3
+ size 3865766
SnowballTarget/SnowballTarget-639368.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72ebefa81cbb37b3b93646ed845036a616dd1b3daca06776ff16d77b9efe75b5
3
+ size 646532
SnowballTarget/SnowballTarget-639368.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b44fa7befc33efe672298f342464480f24a14aa391031bcd860a8e512ce0cc8
3
+ size 3843968
SnowballTarget/SnowballTarget-649960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f417a2dfb19602ee385d2b2f0162c8fb3ebe375bb5985e1e733505149151cfc3
3
+ size 646532
SnowballTarget/SnowballTarget-649960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15be7a0a5a8c41de5507e397c67429329dfcd3df6a4e992ef896d819fe5fd36
3
+ size 3843968
SnowballTarget/SnowballTarget-698680.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33a3c4a26980a5e987705e9382b4a80368167354110af7bdcfb43dbf269c909b
3
+ size 646532
SnowballTarget/SnowballTarget-698680.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a78ede33d2d3a440e16dc56d9d18db067ce1e9adf0d5b64a37b813ab37c3d93
3
+ size 3843968
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3139b305ef89dd2bb0c563130f5528eb8b4e92aa5612000a008d2550eaa2074
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e914870a55003a21883e6796222e00aeff6ff33b57892dcd34392307ded48689
3
  size 3843968
SnowballTarget/events.out.tfevents.1693978579.facb3874e344.18906.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:518fd8e769878f04a60fd9ab326228f717942374cd19b5ff7932a391db680f09
3
+ size 21992
SnowballTarget/events.out.tfevents.1693978835.facb3874e344.20053.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e49f22fc73cbf56bb01513dfc7bd086b69551c2dcff38516ccc87f0a3752767e
3
+ size 9293
SnowballTarget/events.out.tfevents.1693978949.facb3874e344.20593.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d87bad0fbc2149965eaf8a59d971cf4e57ba5c1ace1fa1f9e93d11d6a6df3881
3
+ size 16387
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": 800000, "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": 0.15, "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": 800000, "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
@@ -7,7 +7,7 @@ behaviors:
7
  buffer_size: 2048
8
  learning_rate: 0.0003
9
  beta: 0.005
10
- epsilon: 0.2
11
  lambd: 0.95
12
  num_epoch: 4
13
  shared_critic: false
 
7
  buffer_size: 2048
8
  learning_rate: 0.0003
9
  beta: 0.005
10
+ epsilon: 0.15
11
  lambd: 0.95
12
  num_epoch: 4
13
  shared_critic: 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 0.130 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: 0.932772 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]: 3714 frames, [16.0 KB-32.0 KB]: 62 frames, [2.0 MB-4.0 MB]: 1 frames
54
  Initial Block Size 4.0 MB
55
  Current Block Size 4.0 MB
56
  Peak Allocated Bytes 2.0 MB
@@ -166,22 +166,22 @@ Memory Statistics:
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
- Peak main deferred allocation count 39
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]: 3777 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
- Peak Allocated memory 6.4 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
- Peak usage frame count: [16.0 MB-32.0 MB]: 3777 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
- Peak Allocated memory 17.4 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]: 3703 frames, [64.0 KB-128.0 KB]: 74 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]: 3777 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]: 3777 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]: 3776 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]: 3777 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]: 3777 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 0.129 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: 0.869507 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]: 1605 frames, [16.0 KB-32.0 KB]: 27 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 32
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
173
  Peak Allocated bytes 1.0 MB
174
  [ALLOC_DEFAULT_MAIN]
175
+ Peak usage frame count: [4.0 MB-8.0 MB]: 1633 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 5.7 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 1633 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
  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]: 1590 frames, [64.0 KB-128.0 KB]: 43 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 65.6 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 1633 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]: 1633 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]: 1632 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]: 1633 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]: 1633 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": 0.8609923124313354,
6
- "min": 0.7671712040901184,
7
- "max": 0.8963980078697205,
8
- "count": 46
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 2613.97265625,
12
- "min": 1681.4407958984375,
13
- "max": 3052.009765625,
14
- "count": 46
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 536936.0,
18
- "min": 401944.0,
19
- "max": 536936.0,
20
- "count": 46
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 536936.0,
24
- "min": 401944.0,
25
- "max": 536936.0,
26
- "count": 46
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 13.71523380279541,
30
- "min": 13.287278175354004,
31
- "max": 13.71523380279541,
32
- "count": 46
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 905.2054443359375,
36
- "min": 301.0721130371094,
37
- "max": 916.0462646484375,
38
- "count": 46
39
- },
40
- "SnowballTarget.IsTraining.mean": {
41
- "value": 1.0,
42
- "min": 1.0,
43
- "max": 1.0,
44
- "count": 46
45
- },
46
- "SnowballTarget.IsTraining.sum": {
47
- "value": 1.0,
48
- "min": 1.0,
49
- "max": 1.0,
50
- "count": 46
51
  },
52
  "SnowballTarget.Environment.EpisodeLength.mean": {
53
  "value": 199.0,
54
  "min": 199.0,
55
  "max": 199.0,
56
- "count": 45
57
  },
58
  "SnowballTarget.Environment.EpisodeLength.sum": {
59
- "value": 4378.0,
60
  "min": 2189.0,
61
  "max": 4378.0,
62
- "count": 45
63
  },
64
  "SnowballTarget.Losses.PolicyLoss.mean": {
65
- "value": 0.14580393347301546,
66
- "min": 0.12194017217295956,
67
- "max": 0.15101367198595278,
68
- "count": 45
69
  },
70
  "SnowballTarget.Losses.PolicyLoss.sum": {
71
- "value": 0.2916078669460309,
72
- "min": 0.12194017217295956,
73
- "max": 0.30202734397190556,
74
- "count": 45
75
  },
76
  "SnowballTarget.Losses.ValueLoss.mean": {
77
- "value": 0.16894823786638238,
78
- "min": 0.13423623076147018,
79
- "max": 0.24278216433766134,
80
- "count": 45
81
  },
82
  "SnowballTarget.Losses.ValueLoss.sum": {
83
- "value": 0.33789647573276477,
84
- "min": 0.13423623076147018,
85
- "max": 0.39804124256924667,
86
- "count": 45
87
  },
88
  "SnowballTarget.Policy.LearningRate.mean": {
89
- "value": 9.909456696850002e-05,
90
- "min": 9.909456696850002e-05,
91
- "max": 0.00014859455046849999,
92
- "count": 45
93
  },
94
  "SnowballTarget.Policy.LearningRate.sum": {
95
- "value": 0.00019818913393700004,
96
- "min": 0.00010033206655599996,
97
- "max": 0.00029718910093699997,
98
- "count": 45
99
  },
100
  "SnowballTarget.Policy.Epsilon.mean": {
101
- "value": 0.13303150000000002,
102
- "min": 0.13303150000000002,
103
- "max": 0.1495315,
104
- "count": 45
105
  },
106
  "SnowballTarget.Policy.Epsilon.sum": {
107
- "value": 0.26606300000000005,
108
- "min": 0.133444,
109
- "max": 0.299063,
110
- "count": 45
111
  },
112
  "SnowballTarget.Policy.Beta.mean": {
113
- "value": 0.0016582718500000003,
114
- "min": 0.0016582718500000003,
115
- "max": 0.0024816218500000008,
116
- "count": 45
117
  },
118
  "SnowballTarget.Policy.Beta.sum": {
119
- "value": 0.0033165437000000006,
120
- "min": 0.0016788555999999997,
121
- "max": 0.0049632437000000015,
122
- "count": 45
123
  },
124
  "SnowballTarget.Environment.CumulativeReward.mean": {
125
- "value": 27.363636363636363,
126
- "min": 24.727272727272727,
127
- "max": 27.454545454545453,
128
- "count": 45
129
  },
130
  "SnowballTarget.Environment.CumulativeReward.sum": {
131
- "value": 602.0,
132
- "min": 272.0,
133
- "max": 602.0,
134
- "count": 45
135
  },
136
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
137
- "value": 27.363636363636363,
138
- "min": 24.727272727272727,
139
- "max": 27.454545454545453,
140
- "count": 45
141
  },
142
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
143
- "value": 602.0,
144
- "min": 272.0,
145
- "max": 602.0,
146
- "count": 45
 
 
 
 
 
 
 
 
 
 
 
 
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1693978029",
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": "1693978504"
160
  },
161
- "total": 474.8700097029996,
162
  "count": 1,
163
- "self": 0.434162629999264,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.06851832799975455,
167
  "count": 1,
168
- "self": 0.06851832799975455
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 474.3673287450006,
172
  "count": 1,
173
- "self": 0.4086392410499684,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 4.675718478000363,
177
  "count": 1,
178
- "self": 4.675718478000363
179
  },
180
  "TrainerController.advance": {
181
- "total": 469.1431288809499,
182
- "count": 12588,
183
- "self": 0.20727837096956137,
184
  "children": {
185
  "env_step": {
186
- "total": 468.93585050998036,
187
- "count": 12588,
188
- "self": 381.2652551070196,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 87.46600245596937,
192
- "count": 12588,
193
- "self": 1.3898065150342518,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 86.07619594093512,
197
- "count": 12588,
198
- "self": 86.07619594093512
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.20459294699139718,
204
- "count": 12588,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 473.16458812898463,
209
- "count": 12588,
210
  "is_parallel": true,
211
- "self": 281.4758804659227,
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": 0.0031181909998849733,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0008199429998967389,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0022982479999882344,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0022982479999882344
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.04117933800034734,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.000683250000292901,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0004196280001451669,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0004196280001451669
244
  },
245
  "communicator.exchange": {
246
- "total": 0.037652889999662875,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.037652889999662875
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0024235700002464,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0005971230002614902,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0018264469999849098,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0018264469999849098
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 191.6887076630619,
271
- "count": 12587,
272
  "is_parallel": true,
273
- "self": 7.772609568037296,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 4.0108150700075385,
277
- "count": 12587,
278
  "is_parallel": true,
279
- "self": 4.0108150700075385
280
  },
281
  "communicator.exchange": {
282
- "total": 151.27287381999167,
283
- "count": 12587,
284
  "is_parallel": true,
285
- "self": 151.27287381999167
286
  },
287
  "steps_from_proto": {
288
- "total": 28.632409205025397,
289
- "count": 12587,
290
  "is_parallel": true,
291
- "self": 5.37353484107598,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 23.258874363949417,
295
- "count": 125870,
296
  "is_parallel": true,
297
- "self": 23.258874363949417
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 4.291299956094008e-05,
313
  "count": 1,
314
- "self": 4.291299956094008e-05,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 466.018485567889,
324
- "count": 337183,
325
  "is_parallel": true,
326
- "self": 8.372318065633408,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 191.2111121332523,
330
- "count": 337183,
331
  "is_parallel": true,
332
- "self": 190.76936693325115,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 0.4417452000011508,
336
- "count": 2,
337
  "is_parallel": true,
338
- "self": 0.4417452000011508
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 266.4350553690033,
344
- "count": 62,
345
  "is_parallel": true,
346
- "self": 64.28693799396979,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 202.1481173750335,
350
- "count": 16856,
351
  "is_parallel": true,
352
- "self": 202.1481173750335
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.13979923200076882,
364
  "count": 1,
365
- "self": 0.0010644770009093918,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.13873475499985943,
369
  "count": 1,
370
- "self": 0.13873475499985943
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.8269867897033691,
6
+ "min": 0.8269867897033691,
7
+ "max": 0.9335089921951294,
8
+ "count": 19
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 2419.763427734375,
12
+ "min": 2396.852783203125,
13
+ "max": 3123.6552734375,
14
+ "count": 19
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 695968.0,
18
+ "min": 641952.0,
19
+ "max": 695968.0,
20
+ "count": 19
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 695968.0,
24
+ "min": 641952.0,
25
+ "max": 695968.0,
26
+ "count": 19
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.61626148223877,
30
+ "min": 13.047503471374512,
31
+ "max": 13.61626148223877,
32
+ "count": 19
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 776.1268920898438,
36
+ "min": 652.3751831054688,
37
+ "max": 895.986572265625,
38
+ "count": 19
 
 
 
 
 
 
 
 
 
 
 
 
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 19
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 2189.0,
48
  "min": 2189.0,
49
  "max": 4378.0,
50
+ "count": 19
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.13553000770726237,
54
+ "min": 0.13298535847513235,
55
+ "max": 0.1471718256601461,
56
+ "count": 19
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.13553000770726237,
60
+ "min": 0.13298535847513235,
61
+ "max": 0.29079881485358783,
62
+ "count": 19
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.18688151538919875,
66
+ "min": 0.15523525421945927,
67
+ "max": 0.22956247679779634,
68
+ "count": 19
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.18688151538919875,
72
+ "min": 0.15523525421945927,
73
+ "max": 0.3873446764260092,
74
+ "count": 19
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 3.9645086784999994e-05,
78
+ "min": 3.9645086784999994e-05,
79
+ "max": 5.944508018500001e-05,
80
+ "count": 19
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 3.9645086784999994e-05,
84
+ "min": 3.9645086784999994e-05,
85
+ "max": 0.000113115162295,
86
+ "count": 19
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.1066075,
90
+ "min": 0.1066075,
91
+ "max": 0.10990750000000003,
92
+ "count": 19
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.1066075,
96
+ "min": 0.1066075,
97
+ "max": 0.2188525,
98
+ "count": 19
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 0.0006694285000000003,
102
+ "min": 0.0006694285000000003,
103
+ "max": 0.0009987685000000003,
104
+ "count": 19
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.0006694285000000003,
108
+ "min": 0.0006694285000000003,
109
+ "max": 0.0019014795000000001,
110
+ "count": 19
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 27.454545454545453,
114
+ "min": 25.0,
115
+ "max": 28.181818181818183,
116
+ "count": 19
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 302.0,
120
+ "min": 275.0,
121
+ "max": 593.0,
122
+ "count": 19
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 27.454545454545453,
126
+ "min": 25.0,
127
+ "max": 28.181818181818183,
128
+ "count": 19
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 302.0,
132
+ "min": 275.0,
133
+ "max": 593.0,
134
+ "count": 19
135
+ },
136
+ "SnowballTarget.IsTraining.mean": {
137
+ "value": 1.0,
138
+ "min": 1.0,
139
+ "max": 1.0,
140
+ "count": 19
141
+ },
142
+ "SnowballTarget.IsTraining.sum": {
143
+ "value": 1.0,
144
+ "min": 1.0,
145
+ "max": 1.0,
146
+ "count": 19
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1693978947",
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": "1693979158"
160
  },
161
+ "total": 211.02092578700012,
162
  "count": 1,
163
+ "self": 0.018357020999246743,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.07390263800061803,
167
  "count": 1,
168
+ "self": 0.07390263800061803
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 210.92866612800026,
172
  "count": 1,
173
+ "self": 1.1779065240234559,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 4.265004576999672,
177
  "count": 1,
178
+ "self": 4.265004576999672
179
  },
180
  "TrainerController.advance": {
181
+ "total": 204.99463040297633,
182
+ "count": 5441,
183
+ "self": 0.08851095295722189,
184
  "children": {
185
  "env_step": {
186
+ "total": 204.9061194500191,
187
+ "count": 5441,
188
+ "self": 168.68363656197744,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 36.13218995003717,
192
+ "count": 5441,
193
+ "self": 0.5195413160799944,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 35.61264863395718,
197
+ "count": 5441,
198
+ "self": 35.61264863395718
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.09029293800449523,
204
+ "count": 5440,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 209.0073403829938,
209
+ "count": 5440,
210
  "is_parallel": true,
211
+ "self": 131.6326236319901,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0029900400004407857,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0007589500019093975,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.002231089998531388,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.002231089998531388
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.0477105890004168,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.00046511100026691565,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00031342700003733626,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00031342700003733626
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.04470815000058792,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.04470815000058792
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0022239009995246306,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0004915930003335234,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0017323079991911072,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0017323079991911072
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 77.37471675100369,
271
+ "count": 5439,
272
  "is_parallel": true,
273
+ "self": 3.2437663199425515,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 1.706434640014777,
277
+ "count": 5439,
278
  "is_parallel": true,
279
+ "self": 1.706434640014777
280
  },
281
  "communicator.exchange": {
282
+ "total": 60.735583865048284,
283
+ "count": 5439,
284
  "is_parallel": true,
285
+ "self": 60.735583865048284
286
  },
287
  "steps_from_proto": {
288
+ "total": 11.688931925998077,
289
+ "count": 5439,
290
  "is_parallel": true,
291
+ "self": 2.154977962160956,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 9.53395396383712,
295
+ "count": 54390,
296
  "is_parallel": true,
297
+ "self": 9.53395396383712
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 5.1249000534880906e-05,
313
  "count": 1,
314
+ "self": 5.1249000534880906e-05,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 202.44106983704933,
324
+ "count": 122181,
325
  "is_parallel": true,
326
+ "self": 2.696010076071616,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 77.76067092297671,
330
+ "count": 122182,
331
  "is_parallel": true,
332
+ "self": 77.51726226397659,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 0.24340865900012432,
336
+ "count": 1,
337
  "is_parallel": true,
338
+ "self": 0.24340865900012432
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 121.984388838001,
344
+ "count": 26,
345
  "is_parallel": true,
346
+ "self": 26.60954659199706,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 95.37484224600394,
350
+ "count": 7125,
351
  "is_parallel": true,
352
+ "self": 95.37484224600394
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.49107337500026915,
364
  "count": 1,
365
+ "self": 0.010301417000846413,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.48077195799942274,
369
  "count": 1,
370
+ "self": 0.48077195799942274
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -2,103 +2,103 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 249976,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249976.onnx",
7
- "reward": 26.09090909090909,
8
- "creation_time": 1693976385.0726578,
9
  "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-249976.pt"
11
  ]
12
  },
13
  {
14
- "steps": 299936,
15
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299936.onnx",
16
- "reward": 26.181818181818183,
17
- "creation_time": 1693976554.5373092,
18
  "auxillary_file_paths": [
19
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-299936.pt"
20
  ]
21
  },
22
  {
23
- "steps": 300128,
24
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-300128.onnx",
25
- "reward": 26.181818181818183,
26
- "creation_time": 1693976554.7254746,
27
  "auxillary_file_paths": [
28
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-300128.pt"
29
  ]
30
  },
31
  {
32
- "steps": 349936,
33
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349936.onnx",
34
- "reward": 26.454545454545453,
35
- "creation_time": 1693977228.7585704,
36
  "auxillary_file_paths": [
37
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-349936.pt"
38
  ]
39
  },
40
  {
41
- "steps": 399960,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399960.onnx",
43
- "reward": 27.272727272727273,
44
- "creation_time": 1693977400.0036075,
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-399960.pt"
47
  ]
48
  },
49
  {
50
- "steps": 400536,
51
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-400536.onnx",
52
- "reward": 27.272727272727273,
53
- "creation_time": 1693977400.228383,
54
  "auxillary_file_paths": [
55
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-400536.pt"
56
  ]
57
  },
58
  {
59
- "steps": 400536,
60
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-400536.onnx",
61
  "reward": null,
62
- "creation_time": 1693977999.302544,
63
  "auxillary_file_paths": [
64
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-400536.pt"
65
  ]
66
  },
67
  {
68
- "steps": 449960,
69
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449960.onnx",
70
- "reward": 25.818181818181817,
71
- "creation_time": 1693978205.112506,
72
  "auxillary_file_paths": [
73
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-449960.pt"
74
  ]
75
  },
76
  {
77
- "steps": 499984,
78
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499984.onnx",
79
- "reward": 25.363636363636363,
80
- "creation_time": 1693978375.7889621,
81
  "auxillary_file_paths": [
82
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-499984.pt"
83
  ]
84
  },
85
  {
86
- "steps": 538344,
87
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-538344.onnx",
88
- "reward": 26.636363636363637,
89
- "creation_time": 1693978503.9991636,
90
  "auxillary_file_paths": [
91
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-538344.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
- "steps": 538344,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
- "reward": 26.636363636363637,
99
- "creation_time": 1693978503.9991636,
100
  "auxillary_file_paths": [
101
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-538344.pt"
102
  ]
103
  }
104
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 400536,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-400536.onnx",
7
+ "reward": null,
8
+ "creation_time": 1693977999.302544,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-400536.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 449960,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449960.onnx",
16
+ "reward": 25.818181818181817,
17
+ "creation_time": 1693978205.112506,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-449960.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 499984,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499984.onnx",
25
+ "reward": 25.363636363636363,
26
+ "creation_time": 1693978375.7889621,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-499984.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 538344,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-538344.onnx",
34
+ "reward": 26.636363636363637,
35
+ "creation_time": 1693978503.9991636,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-538344.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 549984,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-549984.onnx",
43
+ "reward": 16.09090909090909,
44
+ "creation_time": 1693978621.2882621,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-549984.pt"
47
  ]
48
  },
49
  {
50
+ "steps": 599944,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-599944.onnx",
52
+ "reward": 25.545454545454547,
53
+ "creation_time": 1693978799.258874,
54
  "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-599944.pt"
56
  ]
57
  },
58
  {
59
+ "steps": 608656,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-608656.onnx",
61
  "reward": null,
62
+ "creation_time": 1693978826.3748775,
63
  "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-608656.pt"
65
  ]
66
  },
67
  {
68
+ "steps": 639368,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-639368.onnx",
70
+ "reward": null,
71
+ "creation_time": 1693978942.8744838,
72
  "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-639368.pt"
74
  ]
75
  },
76
  {
77
+ "steps": 649960,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-649960.onnx",
79
+ "reward": 26.818181818181817,
80
+ "creation_time": 1693978988.5500982,
81
  "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-649960.pt"
83
  ]
84
  },
85
  {
86
+ "steps": 698680,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-698680.onnx",
88
+ "reward": null,
89
+ "creation_time": 1693979158.8977613,
90
  "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-698680.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 698680,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": null,
99
+ "creation_time": 1693979158.8977613,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-698680.pt"
102
  ]
103
  }
104
  },