Hugging Face's logo

BlackSwan1827
/
CubeChase

Reinforcement Learning
ml-agents
TensorBoard
ONNX
CubeChaseAgent
deep-reinforcement-learning
ML-Agents-CubeChaseAgent
Model card Files
xet
 Metrics Community
BlackSwan1827 commited on
Commit
aaa0c58
·
1 Parent(s): 50c0abb

Trained Model v1.3

Browse files
Files changed (10) hide show
  1. CubeChaseAgent.onnx +1 -1
  2. CubeChaseAgent/CubeChaseAgent-121672.onnx +3 -0
  3. CubeChaseAgent/CubeChaseAgent-121672.pt +3 -0
  4. CubeChaseAgent/checkpoint.pt +2 -2
  5. CubeChaseAgent/events.out.tfevents.1691414760.9d7388201558.1997.0 +3 -0
  6. config.json +1 -1
  7. configuration.yaml +1 -1
  8. run_logs/Player-0.log +20 -21
  9. run_logs/timers.json +162 -162
  10. run_logs/training_status.json +8 -8
CubeChaseAgent.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23a6f9e48182387337673e7c8d312ef50b43ea15c2dcd0e75f2df7e0bbc8ca27
3
  size 74450
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:132123c61c6642ea47f2aec25937dd215b1624220c63b7e0c525b0fd1f0dccf0
3
  size 74450
CubeChaseAgent/CubeChaseAgent-121672.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:132123c61c6642ea47f2aec25937dd215b1624220c63b7e0c525b0fd1f0dccf0
3
+ size 74450
CubeChaseAgent/CubeChaseAgent-121672.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59b6b37974677128fc9ffedaa2ca02b7ca0ad5e65835ef40847eada6e3d0ffa2
3
+ size 443355
CubeChaseAgent/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:416853c459b02cb0ac2792db719f9d9b2713dc40c95bec120a66edf2f803ee79
3
- size 443995
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59b6b37974677128fc9ffedaa2ca02b7ca0ad5e65835ef40847eada6e3d0ffa2
3
+ size 443355
CubeChaseAgent/events.out.tfevents.1691414760.9d7388201558.1997.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26ead0fe12af4b67b7ad32d685d0eaae11f5629a7a82b2cd17f967dc9236ed7a
3
+ size 65797
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"CubeChaseAgent": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 10, "buffer_size": 100, "learning_rate": 0.0003, "beta": 0.0005, "epsilon": 0.2, "lambd": 0.99, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "constant", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 128, "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": 5, "even_checkpoints": false, "max_steps": 500000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/CubeChase/CubeChase.x86_64", "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": "CubeChasev1.2", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"CubeChaseAgent": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 10, "buffer_size": 100, "learning_rate": 0.0003, "beta": 0.0005, "epsilon": 0.2, "lambd": 0.99, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "constant", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 128, "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": 5, "even_checkpoints": false, "max_steps": 500000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/CubeChase/CubeChase.x86_64", "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": "CubeChasev1.3", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -64,7 +64,7 @@ engine_settings:
64
  no_graphics: true
65
  environment_parameters: null
66
  checkpoint_settings:
67
- run_id: CubeChasev1.2
68
  initialize_from: null
69
  load_model: false
70
  resume: false
 
64
  no_graphics: true
65
  environment_parameters: null
66
  checkpoint_settings:
67
+ run_id: CubeChasev1.3
68
  initialize_from: null
69
  load_model: false
70
  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 0.098 seconds
38
  ERROR: Shader Hidden/Universal Render Pipeline/Blit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Hidden/Universal Render Pipeline/CopyDepth shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Hidden/Universal Render Pipeline/Sampling shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -74,15 +74,14 @@ ERROR: Shader Universal Render Pipeline/Lit shader is not supported on this GPU
74
  WARNING: Shader Unsupported: 'Universal Render Pipeline/Lit' - All subshaders removed
75
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
76
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
77
- UnloadTime: 0.646957 ms
78
  requesting resize 84 x 84
79
- GRPC Exception: Status(StatusCode=Cancelled, Detail="CANCELLED"). Disconnecting from trainer.
80
  Setting up 1 worker threads for Enlighten.
81
  Memory Statistics:
82
  [ALLOC_TEMP_TLS] TLS Allocator
83
  StackAllocators :
84
  [ALLOC_TEMP_MAIN]
85
- Peak usage frame count: [1.0 KB-2.0 KB]: 972 frames, [2.0 MB-4.0 MB]: 1 frames
86
  Initial Block Size 4.0 MB
87
  Current Block Size 4.0 MB
88
  Peak Allocated Bytes 2.3 MB
@@ -90,12 +89,12 @@ Memory Statistics:
90
  [ALLOC_TEMP_Loading.AsyncRead]
91
  Initial Block Size 64.0 KB
92
  Current Block Size 64.0 KB
93
- Peak Allocated Bytes 256 B
94
  Overflow Count 0
95
  [ALLOC_TEMP_Loading.PreloadManager]
96
  Initial Block Size 256.0 KB
97
  Current Block Size 256.0 KB
98
- Peak Allocated Bytes 141.2 KB
99
  Overflow Count 4
100
  [ALLOC_TEMP_Background Job.Worker 8]
101
  Initial Block Size 32.0 KB
@@ -202,18 +201,18 @@ Memory Statistics:
202
  [ALLOC_BUCKET]
203
  Large Block size 4.0 MB
204
  Used Block count 1
205
- Peak Allocated bytes 1.2 MB
206
  [ALLOC_DEFAULT_MAIN]
207
- Peak usage frame count: [16.0 MB-32.0 MB]: 973 frames
208
  Requested Block Size 16.0 MB
209
  Peak Block count 1
210
- Peak Allocated memory 20.8 MB
211
  Peak Large allocation bytes 16.0 MB
212
  [ALLOC_DEFAULT_THREAD]
213
- Peak usage frame count: [1.0 MB-2.0 MB]: 973 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
- Peak Allocated memory 1.4 MB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_TEMP_JOB_1_FRAME]
219
  Initial Block Size 2.0 MB
@@ -240,15 +239,15 @@ Memory Statistics:
240
  [ALLOC_BUCKET]
241
  Large Block size 4.0 MB
242
  Used Block count 1
243
- Peak Allocated bytes 1.2 MB
244
  [ALLOC_GFX_MAIN]
245
- Peak usage frame count: [32.0 KB-64.0 KB]: 972 frames, [64.0 KB-128.0 KB]: 1 frames
246
  Requested Block Size 16.0 MB
247
  Peak Block count 1
248
  Peak Allocated memory 65.7 KB
249
  Peak Large allocation bytes 0 B
250
  [ALLOC_GFX_THREAD]
251
- Peak usage frame count: [32.0 KB-64.0 KB]: 973 frames
252
  Requested Block Size 16.0 MB
253
  Peak Block count 1
254
  Peak Allocated memory 36.2 KB
@@ -258,33 +257,33 @@ Memory Statistics:
258
  [ALLOC_BUCKET]
259
  Large Block size 4.0 MB
260
  Used Block count 1
261
- Peak Allocated bytes 1.2 MB
262
  [ALLOC_CACHEOBJECTS_MAIN]
263
- Peak usage frame count: [1.0 MB-2.0 MB]: 972 frames, [4.0 MB-8.0 MB]: 1 frames
264
  Requested Block Size 4.0 MB
265
  Peak Block count 1
266
  Peak Allocated memory 5.8 MB
267
  Peak Large allocation bytes 2.5 MB
268
  [ALLOC_CACHEOBJECTS_THREAD]
269
- Peak usage frame count: [256.0 KB-0.5 MB]: 972 frames, [1.0 MB-2.0 MB]: 1 frames
270
  Requested Block Size 4.0 MB
271
  Peak Block count 1
272
- Peak Allocated memory 1.0 MB
273
  Peak Large allocation bytes 0 B
274
  [ALLOC_TYPETREE] Dual Thread Allocator
275
  Peak main deferred allocation count 0
276
  [ALLOC_BUCKET]
277
  Large Block size 4.0 MB
278
  Used Block count 1
279
- Peak Allocated bytes 1.2 MB
280
  [ALLOC_TYPETREE_MAIN]
281
- Peak usage frame count: [0-1.0 KB]: 973 frames
282
  Requested Block Size 2.0 MB
283
  Peak Block count 1
284
  Peak Allocated memory 1.1 KB
285
  Peak Large allocation bytes 0 B
286
  [ALLOC_TYPETREE_THREAD]
287
- Peak usage frame count: [0-1.0 KB]: 973 frames
288
  Requested Block Size 2.0 MB
289
  Peak Block count 0
290
  Peak Allocated memory 0 B
 
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 0.127 seconds
38
  ERROR: Shader Hidden/Universal Render Pipeline/Blit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Hidden/Universal Render Pipeline/CopyDepth shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Hidden/Universal Render Pipeline/Sampling shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
74
  WARNING: Shader Unsupported: 'Universal Render Pipeline/Lit' - All subshaders removed
75
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
76
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
77
+ UnloadTime: 1.082538 ms
78
  requesting resize 84 x 84
 
79
  Setting up 1 worker threads for Enlighten.
80
  Memory Statistics:
81
  [ALLOC_TEMP_TLS] TLS Allocator
82
  StackAllocators :
83
  [ALLOC_TEMP_MAIN]
84
+ Peak usage frame count: [2.0 KB-4.0 KB]: 731 frames, [2.0 MB-4.0 MB]: 1 frames
85
  Initial Block Size 4.0 MB
86
  Current Block Size 4.0 MB
87
  Peak Allocated Bytes 2.3 MB
 
89
  [ALLOC_TEMP_Loading.AsyncRead]
90
  Initial Block Size 64.0 KB
91
  Current Block Size 64.0 KB
92
+ Peak Allocated Bytes 240 B
93
  Overflow Count 0
94
  [ALLOC_TEMP_Loading.PreloadManager]
95
  Initial Block Size 256.0 KB
96
  Current Block Size 256.0 KB
97
+ Peak Allocated Bytes 157.5 KB
98
  Overflow Count 4
99
  [ALLOC_TEMP_Background Job.Worker 8]
100
  Initial Block Size 32.0 KB
 
201
  [ALLOC_BUCKET]
202
  Large Block size 4.0 MB
203
  Used Block count 1
204
+ Peak Allocated bytes 1.3 MB
205
  [ALLOC_DEFAULT_MAIN]
206
+ Peak usage frame count: [16.0 MB-32.0 MB]: 732 frames
207
  Requested Block Size 16.0 MB
208
  Peak Block count 1
209
+ Peak Allocated memory 21.0 MB
210
  Peak Large allocation bytes 16.0 MB
211
  [ALLOC_DEFAULT_THREAD]
212
+ Peak usage frame count: [1.0 MB-2.0 MB]: 732 frames
213
  Requested Block Size 16.0 MB
214
  Peak Block count 1
215
+ Peak Allocated memory 1.5 MB
216
  Peak Large allocation bytes 0 B
217
  [ALLOC_TEMP_JOB_1_FRAME]
218
  Initial Block Size 2.0 MB
 
239
  [ALLOC_BUCKET]
240
  Large Block size 4.0 MB
241
  Used Block count 1
242
+ Peak Allocated bytes 1.3 MB
243
  [ALLOC_GFX_MAIN]
244
+ Peak usage frame count: [32.0 KB-64.0 KB]: 731 frames, [64.0 KB-128.0 KB]: 1 frames
245
  Requested Block Size 16.0 MB
246
  Peak Block count 1
247
  Peak Allocated memory 65.7 KB
248
  Peak Large allocation bytes 0 B
249
  [ALLOC_GFX_THREAD]
250
+ Peak usage frame count: [32.0 KB-64.0 KB]: 732 frames
251
  Requested Block Size 16.0 MB
252
  Peak Block count 1
253
  Peak Allocated memory 36.2 KB
 
257
  [ALLOC_BUCKET]
258
  Large Block size 4.0 MB
259
  Used Block count 1
260
+ Peak Allocated bytes 1.3 MB
261
  [ALLOC_CACHEOBJECTS_MAIN]
262
+ Peak usage frame count: [1.0 MB-2.0 MB]: 731 frames, [4.0 MB-8.0 MB]: 1 frames
263
  Requested Block Size 4.0 MB
264
  Peak Block count 1
265
  Peak Allocated memory 5.8 MB
266
  Peak Large allocation bytes 2.5 MB
267
  [ALLOC_CACHEOBJECTS_THREAD]
268
+ Peak usage frame count: [0.5 MB-1.0 MB]: 731 frames, [1.0 MB-2.0 MB]: 1 frames
269
  Requested Block Size 4.0 MB
270
  Peak Block count 1
271
+ Peak Allocated memory 1.6 MB
272
  Peak Large allocation bytes 0 B
273
  [ALLOC_TYPETREE] Dual Thread Allocator
274
  Peak main deferred allocation count 0
275
  [ALLOC_BUCKET]
276
  Large Block size 4.0 MB
277
  Used Block count 1
278
+ Peak Allocated bytes 1.3 MB
279
  [ALLOC_TYPETREE_MAIN]
280
+ Peak usage frame count: [0-1.0 KB]: 732 frames
281
  Requested Block Size 2.0 MB
282
  Peak Block count 1
283
  Peak Allocated memory 1.1 KB
284
  Peak Large allocation bytes 0 B
285
  [ALLOC_TYPETREE_THREAD]
286
+ Peak usage frame count: [0-1.0 KB]: 732 frames
287
  Requested Block Size 2.0 MB
288
  Peak Block count 0
289
  Peak Allocated memory 0 B
run_logs/timers.json CHANGED
@@ -2,213 +2,213 @@
2
  "name": "root",
3
  "gauges": {
4
  "CubeChaseAgent.Policy.Entropy.mean": {
5
- "value": 1.3304638862609863,
6
- "min": 1.3304638862609863,
7
- "max": 1.4406789541244507,
8
- "count": 8
9
  },
10
  "CubeChaseAgent.Policy.Entropy.sum": {
11
- "value": 13371.162109375,
12
- "min": 13371.162109375,
13
- "max": 14743.5654296875,
14
- "count": 8
15
  },
16
  "CubeChaseAgent.Environment.EpisodeLength.mean": {
17
- "value": 2.8197408536585367,
18
- "min": 2.8197408536585367,
19
- "max": 12.106159895150721,
20
- "count": 8
21
  },
22
  "CubeChaseAgent.Environment.EpisodeLength.sum": {
23
- "value": 7399.0,
24
- "min": 7399.0,
25
- "max": 9237.0,
26
- "count": 8
27
  },
28
  "CubeChaseAgent.Step.mean": {
29
- "value": 79997.0,
30
- "min": 9990.0,
31
- "max": 79997.0,
32
- "count": 8
33
  },
34
  "CubeChaseAgent.Step.sum": {
35
- "value": 79997.0,
36
- "min": 9990.0,
37
- "max": 79997.0,
38
- "count": 8
39
  },
40
  "CubeChaseAgent.Policy.ExtrinsicValueEstimate.mean": {
41
- "value": 0.9831324219703674,
42
- "min": 0.43312692642211914,
43
- "max": 0.9832891821861267,
44
- "count": 8
45
  },
46
  "CubeChaseAgent.Policy.ExtrinsicValueEstimate.sum": {
47
- "value": 2575.806884765625,
48
- "min": 330.042724609375,
49
- "max": 2575.806884765625,
50
- "count": 8
51
  },
52
  "CubeChaseAgent.Environment.CumulativeReward.mean": {
53
- "value": 0.9977099236641221,
54
- "min": 0.5078740157480315,
55
- "max": 0.9992038216560509,
56
- "count": 8
57
  },
58
  "CubeChaseAgent.Environment.CumulativeReward.sum": {
59
- "value": 2614.0,
60
- "min": 387.0,
61
- "max": 2614.0,
62
- "count": 8
63
  },
64
  "CubeChaseAgent.Policy.ExtrinsicReward.mean": {
65
- "value": 0.9977099236641221,
66
- "min": 0.5078740157480315,
67
- "max": 0.9992038216560509,
68
- "count": 8
69
  },
70
  "CubeChaseAgent.Policy.ExtrinsicReward.sum": {
71
- "value": 2614.0,
72
- "min": 387.0,
73
- "max": 2614.0,
74
- "count": 8
75
  },
76
  "CubeChaseAgent.Losses.PolicyLoss.mean": {
77
- "value": 0.2412640100830578,
78
- "min": 0.2364040109031282,
79
- "max": 0.2443406546307238,
80
- "count": 8
81
  },
82
  "CubeChaseAgent.Losses.PolicyLoss.sum": {
83
- "value": 22.92008095789049,
84
- "min": 21.813553494995514,
85
- "max": 23.20331698343004,
86
- "count": 8
87
  },
88
  "CubeChaseAgent.Losses.ValueLoss.mean": {
89
- "value": 0.0026035018763841144,
90
- "min": 0.0011506950352082983,
91
- "max": 0.08874128673615443,
92
- "count": 8
93
  },
94
  "CubeChaseAgent.Losses.ValueLoss.sum": {
95
- "value": 0.24733267825649086,
96
- "min": 0.11046672337999663,
97
- "max": 7.986715806253899,
98
- "count": 8
99
  },
100
  "CubeChaseAgent.Policy.LearningRate.mean": {
101
- "value": 0.00025501817920447155,
102
- "min": 0.00025501817920447155,
103
- "max": 0.00029694244768585103,
104
- "count": 8
105
  },
106
  "CubeChaseAgent.Policy.LearningRate.sum": {
107
- "value": 0.0242267270244248,
108
- "min": 0.0242267270244248,
109
- "max": 0.0270760528746492,
110
- "count": 8
111
  },
112
  "CubeChaseAgent.Policy.Epsilon.mean": {
113
- "value": 0.18500605473684215,
114
- "min": 0.18500605473684215,
115
- "max": 0.19898081555555558,
116
- "count": 8
117
  },
118
  "CubeChaseAgent.Policy.Epsilon.sum": {
119
- "value": 17.575575200000003,
120
- "min": 17.575575200000003,
121
- "max": 18.5282962,
122
- "count": 8
123
  },
124
  "CubeChaseAgent.Policy.Beta.mean": {
125
  "value": 0.0005000000000000001,
126
  "min": 0.0005000000000000001,
127
  "max": 0.0005000000000000001,
128
- "count": 8
129
  },
130
  "CubeChaseAgent.Policy.Beta.sum": {
131
- "value": 0.047500000000000014,
132
- "min": 0.04500000000000001,
133
- "max": 0.048000000000000015,
134
- "count": 8
135
  },
136
  "CubeChaseAgent.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 8
141
  },
142
  "CubeChaseAgent.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 8
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1691412635",
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 ./ml-agents/config/ppo/CubeChase.yaml --env=./training-envs-executables/linux/CubeChase/CubeChase.x86_64 --run-id=CubeChasev1.2 --no-graphics --force",
154
  "mlagents_version": "0.31.0.dev0",
155
  "mlagents_envs_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": "1691412880"
160
  },
161
- "total": 245.83182224499996,
162
  "count": 1,
163
- "self": 0.4245115729999611,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.04349833100002343,
167
  "count": 1,
168
- "self": 0.04349833100002343
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 245.36381234099997,
172
  "count": 1,
173
- "self": 0.2728475159973982,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 6.391924240000037,
177
  "count": 1,
178
- "self": 6.391924240000037
179
  },
180
  "TrainerController.advance": {
181
- "total": 238.47294238400252,
182
- "count": 11102,
183
- "self": 0.22291748600707706,
184
  "children": {
185
  "env_step": {
186
- "total": 46.25549591399539,
187
- "count": 11102,
188
- "self": 44.18142690399924,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 1.9414303580004457,
192
- "count": 11102,
193
- "self": 0.2282176760034531,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 1.7132126819969926,
197
- "count": 1621,
198
- "self": 1.7132126819969926
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.13263865199570546,
204
- "count": 11101,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 244.76964477900037,
209
- "count": 11101,
210
  "is_parallel": true,
211
- "self": 212.69376319200012,
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": 0.0012042240000482707,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0002967720000697227,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.000907451999978548,
227
  "count": 2,
228
  "is_parallel": true,
229
- "self": 0.000907451999978548
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.04441783600003646,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.00019538599997304118,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0011486580000337199,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0011486580000337199
244
  },
245
  "communicator.exchange": {
246
- "total": 0.04265053000000307,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.04265053000000307
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0004232620000266252,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0001985210000157167,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.00022474100001090846,
259
  "count": 2,
260
  "is_parallel": true,
261
- "self": 0.00022474100001090846
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 32.075881587000254,
271
- "count": 11100,
272
  "is_parallel": true,
273
- "self": 1.7562732710036357,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 1.98411509000357,
277
- "count": 11100,
278
  "is_parallel": true,
279
- "self": 1.98411509000357
280
  },
281
  "communicator.exchange": {
282
- "total": 24.525806725998393,
283
- "count": 11100,
284
  "is_parallel": true,
285
- "self": 24.525806725998393
286
  },
287
  "steps_from_proto": {
288
- "total": 3.8096864999946547,
289
- "count": 11100,
290
  "is_parallel": true,
291
- "self": 1.7021175089816438,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 2.107568991013011,
295
- "count": 22200,
296
  "is_parallel": true,
297
- "self": 2.107568991013011
298
  }
299
  }
300
  }
@@ -307,24 +307,24 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 191.99452898400006,
311
- "count": 11101,
312
- "self": 0.25941598700370605,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 30.366022278994308,
316
- "count": 11101,
317
- "self": 30.366022278994308
318
  },
319
  "_update_policy": {
320
- "total": 161.36909071800204,
321
- "count": 763,
322
- "self": 16.34106925999839,
323
  "children": {
324
  "TorchPPOOptimizer.update": {
325
- "total": 145.02802145800365,
326
- "count": 23370,
327
- "self": 145.02802145800365
328
  }
329
  }
330
  }
@@ -333,19 +333,19 @@
333
  }
334
  },
335
  "trainer_threads": {
336
- "total": 1.247000000148546e-06,
337
  "count": 1,
338
- "self": 1.247000000148546e-06
339
  },
340
  "TrainerController._save_models": {
341
- "total": 0.22609695400001328,
342
  "count": 1,
343
- "self": 0.0005307090000314929,
344
  "children": {
345
  "RLTrainer._checkpoint": {
346
- "total": 0.2255662449999818,
347
  "count": 1,
348
- "self": 0.2255662449999818
349
  }
350
  }
351
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "CubeChaseAgent.Policy.Entropy.mean": {
5
+ "value": 1.3624736070632935,
6
+ "min": 1.3624736070632935,
7
+ "max": 1.426416277885437,
8
+ "count": 12
9
  },
10
  "CubeChaseAgent.Policy.Entropy.sum": {
11
+ "value": 13488.48828125,
12
+ "min": 13350.98828125,
13
+ "max": 16555.53515625,
14
+ "count": 12
15
  },
16
  "CubeChaseAgent.Environment.EpisodeLength.mean": {
17
+ "value": 5.258911819887429,
18
+ "min": 5.258911819887429,
19
+ "max": 26.4585635359116,
20
+ "count": 12
21
  },
22
  "CubeChaseAgent.Environment.EpisodeLength.sum": {
23
+ "value": 8409.0,
24
+ "min": 8409.0,
25
+ "max": 9599.0,
26
+ "count": 12
27
  },
28
  "CubeChaseAgent.Step.mean": {
29
+ "value": 119998.0,
30
+ "min": 9974.0,
31
+ "max": 119998.0,
32
+ "count": 12
33
  },
34
  "CubeChaseAgent.Step.sum": {
35
+ "value": 119998.0,
36
+ "min": 9974.0,
37
+ "max": 119998.0,
38
+ "count": 12
39
  },
40
  "CubeChaseAgent.Policy.ExtrinsicValueEstimate.mean": {
41
+ "value": 0.9679732918739319,
42
+ "min": 0.15101228654384613,
43
+ "max": 0.9679732918739319,
44
+ "count": 12
45
  },
46
  "CubeChaseAgent.Policy.ExtrinsicValueEstimate.sum": {
47
+ "value": 1546.8212890625,
48
+ "min": 55.119483947753906,
49
+ "max": 1546.8212890625,
50
+ "count": 12
51
  },
52
  "CubeChaseAgent.Environment.CumulativeReward.mean": {
53
+ "value": 0.9949937421777222,
54
+ "min": 0.20498614958448755,
55
+ "max": 0.9949937421777222,
56
+ "count": 12
57
  },
58
  "CubeChaseAgent.Environment.CumulativeReward.sum": {
59
+ "value": 1590.0,
60
+ "min": 74.0,
61
+ "max": 1590.0,
62
+ "count": 12
63
  },
64
  "CubeChaseAgent.Policy.ExtrinsicReward.mean": {
65
+ "value": 0.9949937421777222,
66
+ "min": 0.20498614958448755,
67
+ "max": 0.9949937421777222,
68
+ "count": 12
69
  },
70
  "CubeChaseAgent.Policy.ExtrinsicReward.sum": {
71
+ "value": 1590.0,
72
+ "min": 74.0,
73
+ "max": 1590.0,
74
+ "count": 12
75
  },
76
  "CubeChaseAgent.Losses.PolicyLoss.mean": {
77
+ "value": 0.24009240636568133,
78
+ "min": 0.2346602955969273,
79
+ "max": 0.24759637916873814,
80
+ "count": 12
81
  },
82
  "CubeChaseAgent.Losses.PolicyLoss.sum": {
83
+ "value": 22.088501385642683,
84
+ "min": 19.66620900576534,
85
+ "max": 22.539351797162563,
86
+ "count": 12
87
  },
88
  "CubeChaseAgent.Losses.ValueLoss.mean": {
89
+ "value": 0.004534491502782299,
90
+ "min": 0.004534491502782299,
91
+ "max": 0.09943730601449394,
92
+ "count": 12
93
  },
94
  "CubeChaseAgent.Losses.ValueLoss.sum": {
95
+ "value": 0.41717321825597153,
96
+ "min": 0.41717321825597153,
97
+ "max": 8.84992023528996,
98
+ "count": 12
99
  },
100
  "CubeChaseAgent.Policy.LearningRate.mean": {
101
+ "value": 0.00023097265126999355,
102
+ "min": 0.00023097265126999355,
103
+ "max": 0.00029695498620019013,
104
+ "count": 12
105
  },
106
  "CubeChaseAgent.Policy.LearningRate.sum": {
107
+ "value": 0.021249483916839406,
108
+ "min": 0.021249483916839406,
109
+ "max": 0.025365034644988595,
110
+ "count": 12
111
  },
112
  "CubeChaseAgent.Policy.Epsilon.mean": {
113
+ "value": 0.17699087608695654,
114
+ "min": 0.17699087608695654,
115
+ "max": 0.1989849950617284,
116
+ "count": 12
117
  },
118
  "CubeChaseAgent.Policy.Epsilon.sum": {
119
+ "value": 16.283160600000002,
120
+ "min": 16.1177846,
121
+ "max": 17.3550114,
122
+ "count": 12
123
  },
124
  "CubeChaseAgent.Policy.Beta.mean": {
125
  "value": 0.0005000000000000001,
126
  "min": 0.0005000000000000001,
127
  "max": 0.0005000000000000001,
128
+ "count": 12
129
  },
130
  "CubeChaseAgent.Policy.Beta.sum": {
131
+ "value": 0.04600000000000001,
132
+ "min": 0.04050000000000001,
133
+ "max": 0.046500000000000014,
134
+ "count": 12
135
  },
136
  "CubeChaseAgent.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 12
141
  },
142
  "CubeChaseAgent.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 12
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1691414757",
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 ./ml-agents/config/ppo/CubeChase.yaml --env=./training-envs-executables/linux/CubeChase/CubeChase.x86_64 --run-id=CubeChasev1.3 --no-graphics --force",
154
  "mlagents_version": "0.31.0.dev0",
155
  "mlagents_envs_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": "1691415061"
160
  },
161
+ "total": 304.81222622700005,
162
  "count": 1,
163
+ "self": 0.46280846799999154,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.0594958140000017,
167
  "count": 1,
168
+ "self": 0.0594958140000017
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 304.28992194500006,
172
  "count": 1,
173
+ "self": 0.382598396000958,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.227173139999991,
177
  "count": 1,
178
+ "self": 3.227173139999991
179
  },
180
  "TrainerController.advance": {
181
+ "total": 300.526569009999,
182
+ "count": 8204,
183
+ "self": 0.30370839101044567,
184
  "children": {
185
  "env_step": {
186
+ "total": 74.41745272699035,
187
+ "count": 8204,
188
+ "self": 72.32699915599204,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 1.9106632459952948,
192
+ "count": 8204,
193
+ "self": 0.34805083399578507,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 1.5626124119995097,
197
+ "count": 1220,
198
+ "self": 1.5626124119995097
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.17979032500301173,
204
+ "count": 8203,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 303.55578765400156,
209
+ "count": 8203,
210
  "is_parallel": true,
211
+ "self": 249.32149769899894,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0023363349999954153,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0005835759999968104,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0017527589999986048,
227
  "count": 2,
228
  "is_parallel": true,
229
+ "self": 0.0017527589999986048
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.04357546699998238,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0008867889999919498,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.002490550000004532,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.002490550000004532
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.038356634999956896,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.038356634999956896
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0018414930000290042,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00047727599996960635,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0013642170000593978,
259
  "count": 2,
260
  "is_parallel": true,
261
+ "self": 0.0013642170000593978
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 54.23428995500262,
271
+ "count": 8202,
272
  "is_parallel": true,
273
+ "self": 2.723056837997717,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 3.282884594002894,
277
+ "count": 8202,
278
  "is_parallel": true,
279
+ "self": 3.282884594002894
280
  },
281
  "communicator.exchange": {
282
+ "total": 42.81378735900262,
283
+ "count": 8202,
284
  "is_parallel": true,
285
+ "self": 42.81378735900262
286
  },
287
  "steps_from_proto": {
288
+ "total": 5.4145611639993945,
289
+ "count": 8202,
290
  "is_parallel": true,
291
+ "self": 2.0002190260005364,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 3.414342137998858,
295
+ "count": 16404,
296
  "is_parallel": true,
297
+ "self": 3.414342137998858
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 225.8054078919982,
311
+ "count": 8203,
312
+ "self": 0.4546590880020176,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 29.880287868995254,
316
+ "count": 8203,
317
+ "self": 29.880287868995254
318
  },
319
  "_update_policy": {
320
+ "total": 195.47046093500092,
321
+ "count": 1083,
322
+ "self": 32.75555481800484,
323
  "children": {
324
  "TorchPPOOptimizer.update": {
325
+ "total": 162.71490611699608,
326
+ "count": 35064,
327
+ "self": 162.71490611699608
328
  }
329
  }
330
  }
 
333
  }
334
  },
335
  "trainer_threads": {
336
+ "total": 1.627000074222451e-06,
337
  "count": 1,
338
+ "self": 1.627000074222451e-06
339
  },
340
  "TrainerController._save_models": {
341
+ "total": 0.15357977200005735,
342
  "count": 1,
343
+ "self": 0.006318809000049441,
344
  "children": {
345
  "RLTrainer._checkpoint": {
346
+ "total": 0.1472609630000079,
347
  "count": 1,
348
+ "self": 0.1472609630000079
349
  }
350
  }
351
  }
run_logs/training_status.json CHANGED
@@ -2,22 +2,22 @@
2
  "CubeChaseAgent": {
3
  "checkpoints": [
4
  {
5
- "steps": 80967,
6
- "file_path": "results/CubeChasev1.2/CubeChaseAgent/CubeChaseAgent-80967.onnx",
7
  "reward": 1.0,
8
- "creation_time": 1691412880.5270169,
9
  "auxillary_file_paths": [
10
- "results/CubeChasev1.2/CubeChaseAgent/CubeChaseAgent-80967.pt"
11
  ]
12
  }
13
  ],
14
  "final_checkpoint": {
15
- "steps": 80967,
16
- "file_path": "results/CubeChasev1.2/CubeChaseAgent.onnx",
17
  "reward": 1.0,
18
- "creation_time": 1691412880.5270169,
19
  "auxillary_file_paths": [
20
- "results/CubeChasev1.2/CubeChaseAgent/CubeChaseAgent-80967.pt"
21
  ]
22
  }
23
  },
 
2
  "CubeChaseAgent": {
3
  "checkpoints": [
4
  {
5
+ "steps": 121672,
6
+ "file_path": "results/CubeChasev1.3/CubeChaseAgent/CubeChaseAgent-121672.onnx",
7
  "reward": 1.0,
8
+ "creation_time": 1691415061.3471987,
9
  "auxillary_file_paths": [
10
+ "results/CubeChasev1.3/CubeChaseAgent/CubeChaseAgent-121672.pt"
11
  ]
12
  }
13
  ],
14
  "final_checkpoint": {
15
+ "steps": 121672,
16
+ "file_path": "results/CubeChasev1.3/CubeChaseAgent.onnx",
17
  "reward": 1.0,
18
+ "creation_time": 1691415061.3471987,
19
  "auxillary_file_paths": [
20
+ "results/CubeChasev1.3/CubeChaseAgent/CubeChaseAgent-121672.pt"
21
  ]
22
  }
23
  },