Hugging Face's logo

S3S3
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
S3S3 commited on
Commit
e2eb123
•
1 Parent(s): 2960c85

Second Push

Browse files
Files changed (18) hide show
  1. SnowballTarget.onnx +2 -2
  2. SnowballTarget/SnowballTarget-149984.onnx +2 -2
  3. SnowballTarget/SnowballTarget-149984.pt +2 -2
  4. SnowballTarget/SnowballTarget-199984.onnx +2 -2
  5. SnowballTarget/SnowballTarget-199984.pt +2 -2
  6. SnowballTarget/SnowballTarget-200112.onnx +2 -2
  7. SnowballTarget/SnowballTarget-200112.pt +2 -2
  8. SnowballTarget/SnowballTarget-49936.onnx +2 -2
  9. SnowballTarget/SnowballTarget-49936.pt +2 -2
  10. SnowballTarget/SnowballTarget-99960.onnx +2 -2
  11. SnowballTarget/SnowballTarget-99960.pt +2 -2
  12. SnowballTarget/checkpoint.pt +2 -2
  13. SnowballTarget/events.out.tfevents.1687978421.09ea14c3188f.2509.0 +3 -0
  14. config.json +1 -1
  15. configuration.yaml +2 -2
  16. run_logs/Player-0.log +17 -17
  17. run_logs/timers.json +116 -116
  18. run_logs/training_status.json +12 -12
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e1531aafb8967423d73a4a6f61e85de5f27a44d99226e10d78354033bfefd6d
3
- size 2862900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc4ffbc42830fd947033a8812d67b4cf8e9a2d8c5f6a2cdbcf9a767f47b6cef3
3
+ size 1811844
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff58c15eb4122c7fcbf737b09900abd987929b24dc0eb91b6931fd7f1599e3d8
3
- size 2862900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3a1bcbfa03877700f05050fdcc067292c74daf4ac82cc9bf0c5509ee85965ce
3
+ size 1811844
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b1697db6b050de7051ac9cea02977dc212119eacebdfe99614a4fd5dec0b040
3
- size 17122012
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:772d8553524079e75cf8fcf39be7758d5cadbd7afdb88fef84185fde95883ee4
3
+ size 10814336
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e1531aafb8967423d73a4a6f61e85de5f27a44d99226e10d78354033bfefd6d
3
- size 2862900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc4ffbc42830fd947033a8812d67b4cf8e9a2d8c5f6a2cdbcf9a767f47b6cef3
3
+ size 1811844
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:331f7f5ff59fe0da99c184232e31324fe509afcfe7e566f43db67a64871d908f
3
- size 17122012
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:835344591e031a1d6b4bca1c4b70177b89eb8ef8bb78ed248535d87e1a065ab2
3
+ size 10814336
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e1531aafb8967423d73a4a6f61e85de5f27a44d99226e10d78354033bfefd6d
3
- size 2862900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc4ffbc42830fd947033a8812d67b4cf8e9a2d8c5f6a2cdbcf9a767f47b6cef3
3
+ size 1811844
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b2e067f573814b095abe911dfdd35c932e9e2e2f6a1494e5bf927e0f60dac2c
3
- size 17122012
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:114dd03263598f4047b32c5090b784cc0e3abab8b8dd4c0e09fac94e76414f19
3
+ size 10814336
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67216062e0ddd0bf7970316bb3004030767f88099fa2fa38543751588a234dbf
3
- size 2862900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c69ad1221df2625997697036bcf2accdcc7006c9a95a132a9ff38379029a504
3
+ size 1811844
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:035c86555849ce3af897fdffe8830fe2c640b5e3a6e34abcb3153a36668f5a69
3
- size 17122012
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5915c81049c3a38c8574eb1d48c49710bcbe1cab73f3e12f1cf1ea83eab48e2
3
+ size 10814336
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ac072bb9a506799321d2cd498a4e6bdc43e4f4ab405106a7ffbb825312834ef
3
- size 2862900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:956cba545220695604b5a26b53f9c533a7072e22c2d08fe46ab8084ba38b098a
3
+ size 1811844
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5741e699a62b6845ec3234c5d9cf3205c8a6478099ce4fcdc4a966361e9202aa
3
- size 17122012
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ca57e6aef780abb4c1621e7af0c7d3ce97d0a614e9982b9bd18877957cf2558
3
+ size 10814336
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b2e067f573814b095abe911dfdd35c932e9e2e2f6a1494e5bf927e0f60dac2c
3
- size 17122012
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:114dd03263598f4047b32c5090b784cc0e3abab8b8dd4c0e09fac94e76414f19
3
+ size 10814336
SnowballTarget/events.out.tfevents.1687978421.09ea14c3188f.2509.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cc8b9a4804358b7a9f0db069d3c61feaea83ecfc44a4bc4a50ae0d671ce0393
3
+ size 23686
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": 0.3, "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": 512, "num_layers": 3, "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, "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": 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": 512, "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, "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": false, "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: 0.3
11
  lambd: 0.95
12
  num_epoch: 3
13
  shared_critic: false
@@ -18,7 +18,7 @@ behaviors:
18
  network_settings:
19
  normalize: false
20
  hidden_units: 512
21
- num_layers: 3
22
  vis_encode_type: simple
23
  memory: null
24
  goal_conditioning_type: hyper
 
7
  buffer_size: 2048
8
  learning_rate: 0.0003
9
  beta: 0.005
10
+ epsilon: 0.2
11
  lambd: 0.95
12
  num_epoch: 3
13
  shared_critic: false
 
18
  network_settings:
19
  normalize: false
20
  hidden_units: 512
21
+ num_layers: 2
22
  vis_encode_type: simple
23
  memory: null
24
  goal_conditioning_type: hyper
run_logs/Player-0.log CHANGED
@@ -34,7 +34,7 @@ ALSA lib pcm.c:2642:(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 0.122 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: 0.640988 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]: 5370 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
@@ -169,23 +169,23 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 44
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 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]: 5462 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.6 MB
182
- Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 5462 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.8 MB
188
- Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
191
  Used Block Count 1
@@ -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]: 4738 frames, [64.0 KB-128.0 KB]: 724 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 67.3 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 5462 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]: 5462 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]: 5461 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]: 5462 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]: 5462 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 0.140 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: 0.826229 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]: 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
 
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
+ Peak main deferred allocation count 41
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
+ Peak Allocated memory 22.7 MB
182
+ Peak Large allocation bytes 16.0 MB
183
  [ALLOC_DEFAULT_THREAD]
184
+ Peak usage frame count: [1.0 MB-2.0 MB]: 5461 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
+ Peak Allocated memory 1.8 MB
188
+ Peak Large allocation bytes 0 B
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
191
  Used Block Count 1
 
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]: 5215 frames, [64.0 KB-128.0 KB]: 246 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
+ Peak Allocated memory 66.0 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
  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
  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
run_logs/timers.json CHANGED
@@ -2,15 +2,15 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.6898939609527588,
6
- "min": 0.6898939609527588,
7
- "max": 2.8428432941436768,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 6587.107421875,
12
- "min": 6587.107421875,
13
- "max": 29269.9140625,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.925793647766113,
30
- "min": 0.42682400345802307,
31
- "max": 12.925793647766113,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2520.52978515625,
36
- "min": 82.8038558959961,
37
- "max": 2609.18603515625,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,27 +50,27 @@
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06287666503539738,
54
- "min": 0.06286872372461491,
55
- "max": 0.07509244880887256,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.2515066601415895,
60
- "min": 0.2515066601415895,
61
- "max": 0.36130899074144984,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.18783418523768583,
66
- "min": 0.11626532201783038,
67
- "max": 0.28283206201067157,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.7513367409507433,
72
- "min": 0.4650612880713215,
73
- "max": 1.4141603100533577,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
@@ -86,15 +86,15 @@
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.10538800000000001,
90
- "min": 0.10538800000000001,
91
- "max": 0.29458799999999996,
92
  "count": 20
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.42155200000000004,
96
- "min": 0.42155200000000004,
97
- "max": 1.42344,
98
  "count": 20
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.295454545454547,
114
- "min": 3.477272727272727,
115
- "max": 25.581818181818182,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1113.0,
120
- "min": 153.0,
121
- "max": 1407.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.295454545454547,
126
- "min": 3.477272727272727,
127
- "max": 25.581818181818182,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1113.0,
132
- "min": 153.0,
133
- "max": 1407.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
@@ -148,7 +148,7 @@
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1687976990",
152
  "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
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",
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": "1687977505"
160
  },
161
- "total": 515.100137204,
162
  "count": 1,
163
- "self": 0.4377329630000304,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.06651589099999455,
167
  "count": 1,
168
- "self": 0.06651589099999455
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 514.59588835,
172
  "count": 1,
173
- "self": 0.601180354001599,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 4.074819574999992,
177
  "count": 1,
178
- "self": 4.074819574999992
179
  },
180
  "TrainerController.advance": {
181
- "total": 509.68795556899835,
182
- "count": 18204,
183
- "self": 0.30226531300286297,
184
  "children": {
185
  "env_step": {
186
- "total": 509.3856902559955,
187
- "count": 18204,
188
- "self": 369.7222382759936,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 139.37387276499953,
192
- "count": 18204,
193
- "self": 2.20729985100445,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 137.16657291399508,
197
- "count": 18204,
198
- "self": 137.16657291399508
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.28957921500233397,
204
- "count": 18204,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 512.8497969190022,
209
- "count": 18204,
210
  "is_parallel": true,
211
- "self": 243.93812406500683,
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": 0.005515208000019811,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.003946258999974361,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0015689490000454498,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0015689490000454498
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03829524599996148,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0005947939999373375,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0003967230000512245,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0003967230000512245
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03500709099995447,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03500709099995447
250
  },
251
  "steps_from_proto": {
252
- "total": 0.002296638000018447,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00039898600010701557,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0018976519999114316,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0018976519999114316
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 268.91167285399536,
271
- "count": 18203,
272
  "is_parallel": true,
273
- "self": 11.10540392698249,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.788907265005264,
277
- "count": 18203,
278
  "is_parallel": true,
279
- "self": 5.788907265005264
280
  },
281
  "communicator.exchange": {
282
- "total": 212.97306284601132,
283
- "count": 18203,
284
  "is_parallel": true,
285
- "self": 212.97306284601132
286
  },
287
  "steps_from_proto": {
288
- "total": 39.044298815996285,
289
- "count": 18203,
290
  "is_parallel": true,
291
- "self": 7.252153129955332,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 31.792145686040953,
295
- "count": 182030,
296
  "is_parallel": true,
297
- "self": 31.792145686040953
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00015713400000549882,
313
  "count": 1,
314
- "self": 0.00015713400000549882,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 505.5556305360388,
324
- "count": 493786,
325
  "is_parallel": true,
326
- "self": 11.381289546040591,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 277.827321448998,
330
- "count": 493786,
331
  "is_parallel": true,
332
- "self": 276.4878581389979,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 1.3394633100000988,
336
  "count": 4,
337
  "is_parallel": true,
338
- "self": 1.3394633100000988
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 216.34701954100018,
344
  "count": 90,
345
  "is_parallel": true,
346
- "self": 81.2667517859939,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 135.08026775500628,
350
  "count": 4587,
351
  "is_parallel": true,
352
- "self": 135.08026775500628
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.2317757179999944,
364
  "count": 1,
365
- "self": 0.0026028529999848615,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.22917286500000955,
369
  "count": 1,
370
- "self": 0.22917286500000955
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.9232625365257263,
6
+ "min": 0.9124116897583008,
7
+ "max": 2.8668861389160156,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 8815.310546875,
12
+ "min": 8815.310546875,
13
+ "max": 29328.24609375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.187472343444824,
30
+ "min": 0.5105000734329224,
31
+ "max": 13.24532413482666,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2571.55712890625,
36
+ "min": 99.0370101928711,
37
+ "max": 2715.29150390625,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.06454379617029118,
54
+ "min": 0.0620545835077863,
55
+ "max": 0.0754291734566305,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.25817518468116474,
60
+ "min": 0.2482183340311452,
61
+ "max": 0.37714586728315247,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.18730088615534352,
66
+ "min": 0.12477795054506072,
67
+ "max": 0.31081782263867996,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.7492035446213741,
72
+ "min": 0.49911180218024287,
73
+ "max": 1.5540891131933998,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
 
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10269400000000001,
90
+ "min": 0.10269400000000001,
91
+ "max": 0.19729400000000002,
92
  "count": 20
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.41077600000000003,
96
+ "min": 0.41077600000000003,
97
+ "max": 0.96172,
98
  "count": 20
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 26.09090909090909,
114
+ "min": 3.840909090909091,
115
+ "max": 26.09090909090909,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1148.0,
120
+ "min": 169.0,
121
+ "max": 1431.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 26.09090909090909,
126
+ "min": 3.840909090909091,
127
+ "max": 26.09090909090909,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1148.0,
132
+ "min": 169.0,
133
+ "max": 1431.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1687978419",
152
  "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
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",
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": "1687978894"
160
  },
161
+ "total": 474.58490468900004,
162
  "count": 1,
163
+ "self": 0.4234270669999205,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.057770368000092276,
167
  "count": 1,
168
+ "self": 0.057770368000092276
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 474.103707254,
172
  "count": 1,
173
+ "self": 0.5536030220060866,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 5.024420632999977,
177
  "count": 1,
178
+ "self": 5.024420632999977
179
  },
180
  "TrainerController.advance": {
181
+ "total": 468.3640790949937,
182
+ "count": 18201,
183
+ "self": 0.27081755199901636,
184
  "children": {
185
  "env_step": {
186
+ "total": 468.0932615429947,
187
+ "count": 18201,
188
+ "self": 343.64725767098787,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 124.17491943100367,
192
+ "count": 18201,
193
+ "self": 1.7423372780029922,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 122.43258215300068,
197
+ "count": 18201,
198
+ "self": 122.43258215300068
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.2710844410031541,
204
+ "count": 18201,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 472.57619871700183,
209
+ "count": 18201,
210
  "is_parallel": true,
211
+ "self": 223.28362600300625,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.002778692999982013,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.000696034999918993,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.00208265800006302,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.00208265800006302
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.05920776699997532,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006091449999985343,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0003388529999028833,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0003388529999028833
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.05590457300002072,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.05590457300002072
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0023551960000531835,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0004441500001348686,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.001911045999918315,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.001911045999918315
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 249.29257271399558,
271
+ "count": 18200,
272
  "is_parallel": true,
273
+ "self": 10.206684486009294,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.275958631004983,
277
+ "count": 18200,
278
  "is_parallel": true,
279
+ "self": 5.275958631004983
280
  },
281
  "communicator.exchange": {
282
+ "total": 198.3033843029947,
283
+ "count": 18200,
284
  "is_parallel": true,
285
+ "self": 198.3033843029947
286
  },
287
  "steps_from_proto": {
288
+ "total": 35.50654529398662,
289
+ "count": 18200,
290
  "is_parallel": true,
291
+ "self": 6.424576380962549,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 29.08196891302407,
295
+ "count": 182000,
296
  "is_parallel": true,
297
+ "self": 29.08196891302407
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.00011943700019401149,
313
  "count": 1,
314
+ "self": 0.00011943700019401149,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 464.6722021189745,
324
+ "count": 441474,
325
  "is_parallel": true,
326
+ "self": 9.882809476964212,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 254.56374857400976,
330
+ "count": 441474,
331
  "is_parallel": true,
332
+ "self": 252.5298654690099,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 2.033883104999859,
336
  "count": 4,
337
  "is_parallel": true,
338
+ "self": 2.033883104999859
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 200.22564406800052,
344
  "count": 90,
345
  "is_parallel": true,
346
+ "self": 81.32699043900186,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 118.89865362899866,
350
  "count": 4587,
351
  "is_parallel": true,
352
+ "self": 118.89865362899866
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.16148506700005782,
364
  "count": 1,
365
+ "self": 0.0016213010001138173,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.159863765999944,
369
  "count": 1,
370
+ "self": 0.159863765999944
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -4,8 +4,8 @@
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 17.545454545454547,
8
- "creation_time": 1687977119.7631407,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
@@ -13,8 +13,8 @@
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 23.09090909090909,
17
- "creation_time": 1687977248.8701425,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
@@ -22,8 +22,8 @@
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 23.818181818181817,
26
- "creation_time": 1687977376.5227125,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
@@ -31,8 +31,8 @@
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 25.181818181818183,
35
- "creation_time": 1687977504.638107,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
@@ -40,8 +40,8 @@
40
  {
41
  "steps": 200112,
42
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 25.181818181818183,
44
- "creation_time": 1687977504.8968256,
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
@@ -50,8 +50,8 @@
50
  "final_checkpoint": {
51
  "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 25.181818181818183,
54
- "creation_time": 1687977504.8968256,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
 
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 17.181818181818183,
8
+ "creation_time": 1687978544.8812995,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
 
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
+ "reward": 24.363636363636363,
17
+ "creation_time": 1687978663.6250787,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
 
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 25.09090909090909,
26
+ "creation_time": 1687978779.9512472,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
 
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 25.818181818181817,
35
+ "creation_time": 1687978893.9644508,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
 
40
  {
41
  "steps": 200112,
42
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
+ "reward": 25.818181818181817,
44
+ "creation_time": 1687978894.1471262,
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
 
50
  "final_checkpoint": {
51
  "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
+ "reward": 25.818181818181817,
54
+ "creation_time": 1687978894.1471262,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]