Hugging Face's logo

Wajid333
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
Wajid333 commited on
Commit
bfac855
•
1 Parent(s): 637750c

First Push

Browse files
Files changed (18) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-149984.onnx +1 -1
  3. SnowballTarget/SnowballTarget-149984.pt +2 -2
  4. SnowballTarget/SnowballTarget-199984.onnx +1 -1
  5. SnowballTarget/SnowballTarget-199984.pt +2 -2
  6. SnowballTarget/SnowballTarget-200112.onnx +1 -1
  7. SnowballTarget/SnowballTarget-200112.pt +2 -2
  8. SnowballTarget/SnowballTarget-49936.onnx +1 -1
  9. SnowballTarget/SnowballTarget-49936.pt +2 -2
  10. SnowballTarget/SnowballTarget-99960.onnx +1 -1
  11. SnowballTarget/SnowballTarget-99960.pt +2 -2
  12. SnowballTarget/checkpoint.pt +2 -2
  13. SnowballTarget/events.out.tfevents.1706708936.529556144b8f.5049.0 +3 -0
  14. config.json +1 -1
  15. configuration.yaml +1 -1
  16. run_logs/Player-0.log +14 -14
  17. run_logs/timers.json +112 -112
  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 sha256:0a117d9e9905259230dc796f9055c6e9a9589934132f3d7f91715e9a38c8627b
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3988068bab56d3d2e06cacd313b6fab712ac7eb81bef60ce58755e8da3ab677a
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7b4981a489f9df14e2e916cb59ae7daf1c4eb343a64d1c62dd39b451230f4a0
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18a8dc78d20243c4cfb8f7563f9883df016e434d9153253430d8f1e3253bf3fe
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c23a66c3355e43a622cbd9a283ac8bfb866a54129c5b857a9fdeb62cf4423581
3
- size 3849115
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e27fb2b91341baf29d3055a852399b896566d73a4c0d26012739e5c9b91b0ad
3
+ size 3850075
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a117d9e9905259230dc796f9055c6e9a9589934132f3d7f91715e9a38c8627b
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3988068bab56d3d2e06cacd313b6fab712ac7eb81bef60ce58755e8da3ab677a
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf09a0d1b6771ea9bdc2ec49bb97c96aec08f3b13286e2d438f29874cecec410
3
- size 3849115
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4515a63980dbf42743f0620a10de1f26cef5565cdef2fd25dd829174de63346
3
+ size 3850075
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a117d9e9905259230dc796f9055c6e9a9589934132f3d7f91715e9a38c8627b
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3988068bab56d3d2e06cacd313b6fab712ac7eb81bef60ce58755e8da3ab677a
3
  size 650646
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9b9fe5a5950afeeffa3003272ed356cca341f55ad43df101f1f463bc75e8ad9
3
- size 3849115
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eec328f693bfd602406f21cafbe52d307ef053c409be05d18b2540c2a5010d8c
3
+ size 3850075
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4f0faa4c4a79932060e87799a76dd390486928e1bfc4478b3e19d9dca9b7d95
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fa0ab7eebf3693e787b07ea31f18199237eff141cc2eb19f1821cdb445dc369
3
  size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de3b9214b3b40a6ca76ea6e451853ee7401b13b911c51bf20674a55b7b165b14
3
- size 3849040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca6d68b200a379be947ef038b426b7e389345e52ff77e4dd38a8499dc032ba69
3
+ size 3850000
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:167ba2867575a9a196513ad9c59f5a1abc7fdee257e2f99700951ea0bce64530
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:543f2578ec00887fb7f361dbe5cfc1fcb572e37e38c8424b42f3750936d21cc5
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2f272b170475e157c5e2a37228c57023f395b756736c420826acc29026db47f
3
- size 3849040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67009e2659d51bfc4101efb0c596a8470b8faf5a43997bdcd6112cb62b5468cd
3
+ size 3850000
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:600e3437c33af8b2f777992be8abba54b0cff766e67f262be79aa370dcfdca13
3
- size 3848290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36b707247cd6b469f64ee0c8cdfe8d1f2739b543c6ae6f42467bc36b76313d8f
3
+ size 3849250
SnowballTarget/events.out.tfevents.1706708936.529556144b8f.5049.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f995126185ba3db427105e40999e67cad28f6eb254cba883ea0802b7a400eac
3
+ size 28361
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -66,7 +66,7 @@ engine_settings:
66
  no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
- run_id: SnowballTarget1
70
  initialize_from: null
71
  load_model: false
72
  resume: false
 
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
run_logs/Player-0.log CHANGED
@@ -34,7 +34,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
- - Completed reload, in 0.177 seconds
38
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -45,7 +45,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
45
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
46
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
47
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
48
- UnloadTime: 1.838133 ms
49
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
50
  requesting resize 84 x 84
51
  Setting up 1 worker threads for Enlighten.
@@ -53,7 +53,7 @@ Memory Statistics:
53
  [ALLOC_TEMP_TLS] TLS Allocator
54
  StackAllocators :
55
  [ALLOC_TEMP_MAIN]
56
- Peak usage frame count: [8.0 KB-16.0 KB]: 5369 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
57
  Initial Block Size 4.0 MB
58
  Current Block Size 4.0 MB
59
  Peak Allocated Bytes 2.0 MB
@@ -175,16 +175,16 @@ Memory Statistics:
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
- Peak usage frame count: [4.0 MB-8.0 MB]: 5461 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 7.1 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.3 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
@@ -213,13 +213,13 @@ Memory Statistics:
213
  Used Block count 1
214
  Peak Allocated bytes 1.0 MB
215
  [ALLOC_GFX_MAIN]
216
- Peak usage frame count: [32.0 KB-64.0 KB]: 4648 frames, [64.0 KB-128.0 KB]: 813 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 67.2 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 5461 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
@@ -231,13 +231,13 @@ Memory Statistics:
231
  Used Block count 1
232
  Peak Allocated bytes 1.0 MB
233
  [ALLOC_CACHEOBJECTS_MAIN]
234
- Peak usage frame count: [0.5 MB-1.0 MB]: 5461 frames
235
  Requested Block Size 4.0 MB
236
  Peak Block count 1
237
  Peak Allocated memory 0.6 MB
238
  Peak Large allocation bytes 0 B
239
  [ALLOC_CACHEOBJECTS_THREAD]
240
- Peak usage frame count: [0.5 MB-1.0 MB]: 5460 frames, [2.0 MB-4.0 MB]: 1 frames
241
  Requested Block Size 4.0 MB
242
  Peak Block count 1
243
  Peak Allocated memory 2.2 MB
@@ -249,13 +249,13 @@ Memory Statistics:
249
  Used Block count 1
250
  Peak Allocated bytes 1.0 MB
251
  [ALLOC_TYPETREE_MAIN]
252
- Peak usage frame count: [0-1.0 KB]: 5461 frames
253
  Requested Block Size 2.0 MB
254
  Peak Block count 1
255
  Peak Allocated memory 1.0 KB
256
  Peak Large allocation bytes 0 B
257
  [ALLOC_TYPETREE_THREAD]
258
- Peak usage frame count: [1.0 KB-2.0 KB]: 5461 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  Peak Allocated memory 1.7 KB
 
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
+ - Completed reload, in 0.096 seconds
38
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
45
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
46
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
47
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
48
+ UnloadTime: 0.751635 ms
49
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
50
  requesting resize 84 x 84
51
  Setting up 1 worker threads for Enlighten.
 
53
  [ALLOC_TEMP_TLS] TLS Allocator
54
  StackAllocators :
55
  [ALLOC_TEMP_MAIN]
56
+ Peak usage frame count: [8.0 KB-16.0 KB]: 5368 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
57
  Initial Block Size 4.0 MB
58
  Current Block Size 4.0 MB
59
  Peak Allocated Bytes 2.0 MB
 
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
+ Peak usage frame count: [4.0 MB-8.0 MB]: 5460 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
+ Peak Allocated memory 7.0 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5460 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
+ Peak Allocated memory 17.4 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
 
213
  Used Block count 1
214
  Peak Allocated bytes 1.0 MB
215
  [ALLOC_GFX_MAIN]
216
+ Peak usage frame count: [32.0 KB-64.0 KB]: 4831 frames, [64.0 KB-128.0 KB]: 629 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
+ Peak Allocated memory 66.4 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5460 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
 
231
  Used Block count 1
232
  Peak Allocated bytes 1.0 MB
233
  [ALLOC_CACHEOBJECTS_MAIN]
234
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5460 frames
235
  Requested Block Size 4.0 MB
236
  Peak Block count 1
237
  Peak Allocated memory 0.6 MB
238
  Peak Large allocation bytes 0 B
239
  [ALLOC_CACHEOBJECTS_THREAD]
240
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5459 frames, [2.0 MB-4.0 MB]: 1 frames
241
  Requested Block Size 4.0 MB
242
  Peak Block count 1
243
  Peak Allocated memory 2.2 MB
 
249
  Used Block count 1
250
  Peak Allocated bytes 1.0 MB
251
  [ALLOC_TYPETREE_MAIN]
252
+ Peak usage frame count: [0-1.0 KB]: 5460 frames
253
  Requested Block Size 2.0 MB
254
  Peak Block count 1
255
  Peak Allocated memory 1.0 KB
256
  Peak Large allocation bytes 0 B
257
  [ALLOC_TYPETREE_THREAD]
258
+ Peak usage frame count: [1.0 KB-2.0 KB]: 5460 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  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": 1.0671510696411133,
6
- "min": 1.0557539463043213,
7
- "max": 2.8721261024475098,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 10212.6357421875,
12
- "min": 10212.6357421875,
13
- "max": 29445.037109375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.501420021057129,
30
- "min": 0.35908225178718567,
31
- "max": 12.501420021057129,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2437.77685546875,
36
- "min": 69.66195678710938,
37
- "max": 2541.619140625,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,27 +50,27 @@
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.0684011133478135,
54
- "min": 0.06019873213959976,
55
- "max": 0.07373807844158044,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.273604453391254,
60
- "min": 0.24079492855839904,
61
- "max": 0.3686903922079022,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.2336552064208423,
66
- "min": 0.13049544141554803,
67
- "max": 0.2771460945699729,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.9346208256833692,
72
- "min": 0.5219817656621921,
73
- "max": 1.333038115326096,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 24.636363636363637,
114
- "min": 3.5454545454545454,
115
- "max": 24.836363636363636,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1084.0,
120
- "min": 156.0,
121
- "max": 1366.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 24.636363636363637,
126
- "min": 3.5454545454545454,
127
- "max": 24.836363636363636,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1084.0,
132
- "min": 156.0,
133
- "max": 1366.0,
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": "1706704908",
152
  "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
153
- "command_line_arguments": "/usr/local/bin/mlagents-learn /content/SnowballTarget --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.1.0.dev0",
155
  "mlagents_envs_version": "1.1.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.2.0+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1706705556"
160
  },
161
- "total": 648.1286294379997,
162
  "count": 1,
163
- "self": 0.6038745660007407,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.09402988399961032,
167
  "count": 1,
168
- "self": 0.09402988399961032
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 647.4307249879994,
172
  "count": 1,
173
- "self": 0.8831739979214035,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 5.652500455000336,
177
  "count": 1,
178
- "self": 5.652500455000336
179
  },
180
  "TrainerController.advance": {
181
- "total": 640.791398011077,
182
- "count": 18201,
183
- "self": 0.4594365610673776,
184
  "children": {
185
  "env_step": {
186
- "total": 640.3319614500097,
187
- "count": 18201,
188
- "self": 495.30910211603623,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 144.5699696059619,
192
- "count": 18201,
193
- "self": 2.7443479819621643,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 141.82562162399972,
197
- "count": 18201,
198
- "self": 141.82562162399972
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.4528897280115416,
204
- "count": 18201,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 645.1703953120123,
209
- "count": 18201,
210
  "is_parallel": true,
211
- "self": 302.2592878410569,
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": 0.008571221000238438,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.005413152000073751,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.003158069000164687,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.003158069000164687
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.05513717399935558,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0007876019990362693,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0005362820002119406,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0005362820002119406
244
  },
245
  "communicator.exchange": {
246
- "total": 0.051367320000281325,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.051367320000281325
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0024459699998260476,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00048566000168648316,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0019603099981395644,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0019603099981395644
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 342.91110747095536,
271
- "count": 18200,
272
  "is_parallel": true,
273
- "self": 15.658435675041801,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 8.258940915947278,
277
- "count": 18200,
278
  "is_parallel": true,
279
- "self": 8.258940915947278
280
  },
281
  "communicator.exchange": {
282
- "total": 271.5007502259996,
283
- "count": 18200,
284
  "is_parallel": true,
285
- "self": 271.5007502259996
286
  },
287
  "steps_from_proto": {
288
- "total": 47.4929806539667,
289
- "count": 18200,
290
  "is_parallel": true,
291
- "self": 9.666245327725846,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 37.82673532624085,
295
- "count": 182000,
296
  "is_parallel": true,
297
- "self": 37.82673532624085
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00033636700027273037,
313
  "count": 1,
314
- "self": 0.00033636700027273037,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 633.2058367510108,
324
- "count": 824519,
325
  "is_parallel": true,
326
- "self": 19.740536227875964,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 328.8676274411364,
330
- "count": 824519,
331
  "is_parallel": true,
332
- "self": 327.85980236913565,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 1.0078250720007418,
336
  "count": 4,
337
  "is_parallel": true,
338
- "self": 1.0078250720007418
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 284.59767308199844,
344
  "count": 90,
345
  "is_parallel": true,
346
- "self": 82.86512223002501,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 201.73255085197343,
350
- "count": 4587,
351
  "is_parallel": true,
352
- "self": 201.73255085197343
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.1033161570003358,
364
  "count": 1,
365
- "self": 0.0014259889994718833,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.10189016800086392,
369
  "count": 1,
370
- "self": 0.10189016800086392
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.8985287547111511,
6
+ "min": 0.8797258138656616,
7
+ "max": 2.854275703430176,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 8579.15234375,
12
+ "min": 8579.15234375,
13
+ "max": 29262.03515625,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 12.868033409118652,
30
+ "min": 0.3897717595100403,
31
+ "max": 12.868033409118652,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2509.2666015625,
36
+ "min": 75.61572265625,
37
+ "max": 2611.51904296875,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.06541426751062086,
54
+ "min": 0.06292996812730516,
55
+ "max": 0.07807722912705276,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.26165707004248345,
60
+ "min": 0.2599613550375901,
61
+ "max": 0.3734648721162789,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.21233359439408078,
66
+ "min": 0.1389858523525261,
67
+ "max": 0.2898073337826074,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.8493343775763231,
72
+ "min": 0.5559434094101044,
73
+ "max": 1.4490366689130372,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 25.454545454545453,
114
+ "min": 3.8636363636363638,
115
+ "max": 25.5,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1120.0,
120
+ "min": 170.0,
121
+ "max": 1393.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.454545454545453,
126
+ "min": 3.8636363636363638,
127
+ "max": 25.5,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1120.0,
132
+ "min": 170.0,
133
+ "max": 1393.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1706708935",
152
  "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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",
154
  "mlagents_version": "1.1.0.dev0",
155
  "mlagents_envs_version": "1.1.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.2.0+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1706709414"
160
  },
161
+ "total": 479.590365735,
162
  "count": 1,
163
+ "self": 0.4439867510000113,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.05832370500002071,
167
  "count": 1,
168
+ "self": 0.05832370500002071
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 479.08805527899995,
172
  "count": 1,
173
+ "self": 0.5992673630171339,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.4608356030000778,
177
  "count": 1,
178
+ "self": 3.4608356030000778
179
  },
180
  "TrainerController.advance": {
181
+ "total": 474.9304949529828,
182
+ "count": 18199,
183
+ "self": 0.29689831897417207,
184
  "children": {
185
  "env_step": {
186
+ "total": 474.63359663400865,
187
+ "count": 18199,
188
+ "self": 308.46675962504946,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 165.86239487998,
192
+ "count": 18199,
193
+ "self": 1.5786597369833544,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 164.28373514299665,
197
+ "count": 18199,
198
+ "self": 164.28373514299665
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.3044421289791899,
204
+ "count": 18199,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 477.80183805397974,
209
+ "count": 18199,
210
  "is_parallel": true,
211
+ "self": 239.2384881789692,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.00524941700018644,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0035291610004151153,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0017202559997713252,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0017202559997713252
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.041573670999923706,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0007353349999448255,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0003919480000149633,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0003919480000149633
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03820433200007756,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03820433200007756
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.002242055999886361,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00043376999974498176,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0018082860001413792,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0018082860001413792
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 238.56334987501054,
271
+ "count": 18198,
272
  "is_parallel": true,
273
+ "self": 11.06278494002413,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.589199743013523,
277
+ "count": 18198,
278
  "is_parallel": true,
279
+ "self": 5.589199743013523
280
  },
281
  "communicator.exchange": {
282
+ "total": 185.5602110319985,
283
+ "count": 18198,
284
  "is_parallel": true,
285
+ "self": 185.5602110319985
286
  },
287
  "steps_from_proto": {
288
+ "total": 36.351154159974385,
289
+ "count": 18198,
290
  "is_parallel": true,
291
+ "self": 6.733862152003212,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 29.617292007971173,
295
+ "count": 181980,
296
  "is_parallel": true,
297
+ "self": 29.617292007971173
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.00017663499988884723,
313
  "count": 1,
314
+ "self": 0.00017663499988884723,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 468.8638211619898,
324
+ "count": 706041,
325
  "is_parallel": true,
326
+ "self": 16.400347642005954,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 260.0813492669831,
330
+ "count": 706041,
331
  "is_parallel": true,
332
+ "self": 259.32911807198275,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 0.7522311950003768,
336
  "count": 4,
337
  "is_parallel": true,
338
+ "self": 0.7522311950003768
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 192.3821242530007,
344
  "count": 90,
345
  "is_parallel": true,
346
+ "self": 57.86339078400101,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 134.5187334689997,
350
+ "count": 4584,
351
  "is_parallel": true,
352
+ "self": 134.5187334689997
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.09728072500001872,
364
  "count": 1,
365
+ "self": 0.001361193000093408,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.09591953199992531,
369
  "count": 1,
370
+ "self": 0.09591953199992531
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -3,57 +3,57 @@
3
  "checkpoints": [
4
  {
5
  "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 13.090909090909092,
8
- "creation_time": 1706705074.18092,
9
  "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
12
  },
13
  {
14
  "steps": 99960,
15
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 20.727272727272727,
17
- "creation_time": 1706705232.447771,
18
  "auxillary_file_paths": [
19
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
21
  },
22
  {
23
  "steps": 149984,
24
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 23.90909090909091,
26
- "creation_time": 1706705396.727607,
27
  "auxillary_file_paths": [
28
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
30
  },
31
  {
32
  "steps": 199984,
33
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
  "reward": 25.90909090909091,
35
- "creation_time": 1706705555.4216428,
36
  "auxillary_file_paths": [
37
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
  "steps": 200112,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
  "reward": 25.90909090909091,
44
- "creation_time": 1706705555.5531268,
45
  "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
  "steps": 200112,
52
- "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
  "reward": 25.90909090909091,
54
- "creation_time": 1706705555.5531268,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
3
  "checkpoints": [
4
  {
5
  "steps": 49936,
6
+ "file_path": "results/SnowballTarget11/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 13.818181818181818,
8
+ "creation_time": 1706709062.335759,
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": 20.272727272727273,
17
+ "creation_time": 1706709179.0562487,
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": 24.0,
26
+ "creation_time": 1706709297.8832262,
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": 25.90909090909091,
35
+ "creation_time": 1706709414.3304794,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget11/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
  "steps": 200112,
42
+ "file_path": "results/SnowballTarget11/SnowballTarget/SnowballTarget-200112.onnx",
43
  "reward": 25.90909090909091,
44
+ "creation_time": 1706709414.4605224,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget11/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
  "steps": 200112,
52
+ "file_path": "results/SnowballTarget11/SnowballTarget.onnx",
53
  "reward": 25.90909090909091,
54
+ "creation_time": 1706709414.4605224,
55
  "auxillary_file_paths": [
56
+ "results/SnowballTarget11/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },