Hugging Face's logo

saurabh2086
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
 Metrics Community
saurabh2086 commited on
Commit
6bf16fd
·
1 Parent(s): 5ca069c

First Push

Browse files
Files changed (6) hide show
  1. SnowballTarget/events.out.tfevents.1691763671.d7be97b937fe.10919.0 +3 -0
  2. config.json +1 -1
  3. configuration.yaml +1 -1
  4. run_logs/Player-0.log +18 -18
  5. run_logs/timers.json +22 -321
  6. run_logs/training_status.json +11 -11
SnowballTarget/events.out.tfevents.1691763671.d7be97b937fe.10919.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0f393ce4ef70b4bf0a8f1bfd163fa32ee58875b27b9efc5c65ccc51f2f80936
3
+ size 1114
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": 2000000, "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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 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, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -38,7 +38,7 @@ behaviors:
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
- max_steps: 2000000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 200000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
run_logs/Player-0.log CHANGED
@@ -31,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
- - Completed reload, in 0.085 seconds
35
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -42,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
42
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
43
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
44
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
45
- UnloadTime: 0.622478 ms
46
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
47
  requesting resize 84 x 84
48
  Setting up 1 worker threads for Enlighten.
@@ -50,7 +50,7 @@ Memory Statistics:
50
  [ALLOC_TEMP_TLS] TLS Allocator
51
  StackAllocators :
52
  [ALLOC_TEMP_MAIN]
53
- Peak usage frame count: [8.0 KB-16.0 KB]: 7930 frames, [16.0 KB-32.0 KB]: 134 frames, [2.0 MB-4.0 MB]: 1 frames
54
  Initial Block Size 4.0 MB
55
  Current Block Size 4.0 MB
56
  Peak Allocated Bytes 2.0 MB
@@ -78,7 +78,7 @@ Memory Statistics:
78
  [ALLOC_TEMP_Job.Worker 0]
79
  Initial Block Size 256.0 KB
80
  Current Block Size 256.0 KB
81
- Peak Allocated Bytes 3.6 KB
82
  Overflow Count 0
83
  [ALLOC_TEMP_Background Job.Worker 10]
84
  Initial Block Size 32.0 KB
@@ -166,22 +166,22 @@ Memory Statistics:
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
- Peak main deferred allocation count 40
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
173
  Peak Allocated bytes 1.0 MB
174
  [ALLOC_DEFAULT_MAIN]
175
- Peak usage frame count: [4.0 MB-8.0 MB]: 8065 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
- Peak Allocated memory 7.5 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
- Peak usage frame count: [16.0 MB-32.0 MB]: 8065 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
- Peak Allocated memory 17.6 MB
185
  Peak Large allocation bytes 16.0 MB
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
@@ -195,7 +195,7 @@ Memory Statistics:
195
  Overflow Count (full) 0
196
  [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
197
  Initial Block Size 2.0 MB
198
- Used Block Count 2
199
  Overflow Count (too large) 0
200
  Overflow Count (full) 0
201
  [ALLOC_TEMP_JOB_ASYNC (Background)]
@@ -210,13 +210,13 @@ Memory Statistics:
210
  Used Block count 1
211
  Peak Allocated bytes 1.0 MB
212
  [ALLOC_GFX_MAIN]
213
- Peak usage frame count: [32.0 KB-64.0 KB]: 7877 frames, [64.0 KB-128.0 KB]: 188 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
- Peak Allocated memory 66.4 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
- Peak usage frame count: [32.0 KB-64.0 KB]: 8065 frames
220
  Requested Block Size 16.0 MB
221
  Peak Block count 1
222
  Peak Allocated memory 39.6 KB
@@ -228,13 +228,13 @@ Memory Statistics:
228
  Used Block count 1
229
  Peak Allocated bytes 1.0 MB
230
  [ALLOC_CACHEOBJECTS_MAIN]
231
- Peak usage frame count: [0.5 MB-1.0 MB]: 8065 frames
232
  Requested Block Size 4.0 MB
233
  Peak Block count 1
234
- Peak Allocated memory 0.6 MB
235
  Peak Large allocation bytes 0 B
236
  [ALLOC_CACHEOBJECTS_THREAD]
237
- Peak usage frame count: [0.5 MB-1.0 MB]: 8064 frames, [2.0 MB-4.0 MB]: 1 frames
238
  Requested Block Size 4.0 MB
239
  Peak Block count 1
240
  Peak Allocated memory 2.2 MB
@@ -246,13 +246,13 @@ Memory Statistics:
246
  Used Block count 1
247
  Peak Allocated bytes 1.0 MB
248
  [ALLOC_TYPETREE_MAIN]
249
- Peak usage frame count: [0-1.0 KB]: 8065 frames
250
  Requested Block Size 2.0 MB
251
  Peak Block count 1
252
  Peak Allocated memory 1.0 KB
253
  Peak Large allocation bytes 0 B
254
  [ALLOC_TYPETREE_THREAD]
255
- Peak usage frame count: [1.0 KB-2.0 KB]: 8065 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
 
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.081 seconds
35
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
42
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
43
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
44
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
45
+ UnloadTime: 0.693939 ms
46
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
47
  requesting resize 84 x 84
48
  Setting up 1 worker threads for Enlighten.
 
50
  [ALLOC_TEMP_TLS] TLS Allocator
51
  StackAllocators :
52
  [ALLOC_TEMP_MAIN]
53
+ Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames
54
  Initial Block Size 4.0 MB
55
  Current Block Size 4.0 MB
56
  Peak Allocated Bytes 2.0 MB
 
78
  [ALLOC_TEMP_Job.Worker 0]
79
  Initial Block Size 256.0 KB
80
  Current Block Size 256.0 KB
81
+ Peak Allocated Bytes 2.8 KB
82
  Overflow Count 0
83
  [ALLOC_TEMP_Background Job.Worker 10]
84
  Initial Block Size 32.0 KB
 
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
+ Peak main deferred allocation count 2
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
173
  Peak Allocated bytes 1.0 MB
174
  [ALLOC_DEFAULT_MAIN]
175
+ Peak usage frame count: [4.0 MB-8.0 MB]: 1 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 5.1 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 1 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.3 MB
185
  Peak Large allocation bytes 16.0 MB
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
 
195
  Overflow Count (full) 0
196
  [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
197
  Initial Block Size 2.0 MB
198
+ Used Block Count 1
199
  Overflow Count (too large) 0
200
  Overflow Count (full) 0
201
  [ALLOC_TEMP_JOB_ASYNC (Background)]
 
210
  Used Block count 1
211
  Peak Allocated bytes 1.0 MB
212
  [ALLOC_GFX_MAIN]
213
+ Peak usage frame count: [64.0 KB-128.0 KB]: 1 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 65.6 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 1 frames
220
  Requested Block Size 16.0 MB
221
  Peak Block count 1
222
  Peak Allocated memory 39.6 KB
 
228
  Used Block count 1
229
  Peak Allocated bytes 1.0 MB
230
  [ALLOC_CACHEOBJECTS_MAIN]
231
+ Peak usage frame count: [0.5 MB-1.0 MB]: 1 frames
232
  Requested Block Size 4.0 MB
233
  Peak Block count 1
234
+ Peak Allocated memory 0.5 MB
235
  Peak Large allocation bytes 0 B
236
  [ALLOC_CACHEOBJECTS_THREAD]
237
+ Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames
238
  Requested Block Size 4.0 MB
239
  Peak Block count 1
240
  Peak Allocated memory 2.2 MB
 
246
  Used Block count 1
247
  Peak Allocated bytes 1.0 MB
248
  [ALLOC_TYPETREE_MAIN]
249
+ Peak usage frame count: [0-1.0 KB]: 1 frames
250
  Requested Block Size 2.0 MB
251
  Peak Block count 1
252
  Peak Allocated memory 1.0 KB
253
  Peak Large allocation bytes 0 B
254
  [ALLOC_TYPETREE_THREAD]
255
+ Peak usage frame count: [1.0 KB-2.0 KB]: 1 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -1,154 +1,8 @@
1
  {
2
  "name": "root",
3
- "gauges": {
4
- "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.6814535856246948,
6
- "min": 0.6814535856246948,
7
- "max": 0.8547778725624084,
8
- "count": 29
9
- },
10
- "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 6881.318359375,
12
- "min": 5655.5341796875,
13
- "max": 8716.169921875,
14
- "count": 29
15
- },
16
- "SnowballTarget.Step.mean": {
17
- "value": 619968.0,
18
- "min": 339992.0,
19
- "max": 619968.0,
20
- "count": 29
21
- },
22
- "SnowballTarget.Step.sum": {
23
- "value": 619968.0,
24
- "min": 339992.0,
25
- "max": 619968.0,
26
- "count": 29
27
- },
28
- "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 13.845855712890625,
30
- "min": 13.041619300842285,
31
- "max": 13.940590858459473,
32
- "count": 29
33
- },
34
- "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2699.94189453125,
36
- "min": 2050.562255859375,
37
- "max": 2842.34765625,
38
- "count": 29
39
- },
40
- "SnowballTarget.Environment.EpisodeLength.mean": {
41
- "value": 199.0,
42
- "min": 199.0,
43
- "max": 199.0,
44
- "count": 29
45
- },
46
- "SnowballTarget.Environment.EpisodeLength.sum": {
47
- "value": 8756.0,
48
- "min": 6567.0,
49
- "max": 10945.0,
50
- "count": 29
51
- },
52
- "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06883341430568858,
54
- "min": 0.061409398668390576,
55
- "max": 0.07653619981290688,
56
- "count": 29
57
- },
58
- "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.2753336572227543,
60
- "min": 0.19969983496583368,
61
- "max": 0.37212890138399934,
62
- "count": 29
63
- },
64
- "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.16401895898960384,
66
- "min": 0.14817879348993301,
67
- "max": 0.20299030942659754,
68
- "count": 29
69
- },
70
- "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.6560758359584153,
72
- "min": 0.5721279685842056,
73
- "max": 1.0116964084844964,
74
- "count": 29
75
- },
76
- "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 0.0002077914307362,
78
- "min": 0.0002077914307362,
79
- "max": 0.00024953641682119997,
80
- "count": 29
81
- },
82
- "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 0.0008311657229448,
84
- "min": 0.0007486092504635999,
85
- "max": 0.0012410820863059998,
86
- "count": 29
87
- },
88
- "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.16926379999999996,
90
- "min": 0.16926379999999996,
91
- "max": 0.18317879999999997,
92
- "count": 29
93
- },
94
- "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.6770551999999999,
96
- "min": 0.5495363999999999,
97
- "max": 0.913694,
98
- "count": 29
99
- },
100
- "SnowballTarget.Policy.Beta.mean": {
101
- "value": 0.0034662636200000004,
102
- "min": 0.0034662636200000004,
103
- "max": 0.00416062212,
104
- "count": 29
105
- },
106
- "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.013865054480000001,
108
- "min": 0.01248186636,
109
- "max": 0.0206933306,
110
- "count": 29
111
- },
112
- "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 26.818181818181817,
114
- "min": 25.393939393939394,
115
- "max": 27.90909090909091,
116
- "count": 29
117
- },
118
- "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1180.0,
120
- "min": 838.0,
121
- "max": 1535.0,
122
- "count": 29
123
- },
124
- "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 26.818181818181817,
126
- "min": 25.393939393939394,
127
- "max": 27.90909090909091,
128
- "count": 29
129
- },
130
- "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1180.0,
132
- "min": 838.0,
133
- "max": 1535.0,
134
- "count": 29
135
- },
136
- "SnowballTarget.IsTraining.mean": {
137
- "value": 1.0,
138
- "min": 1.0,
139
- "max": 1.0,
140
- "count": 29
141
- },
142
- "SnowballTarget.IsTraining.sum": {
143
- "value": 1.0,
144
- "min": 1.0,
145
- "max": 1.0,
146
- "count": 29
147
- }
148
- },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1691762732",
152
  "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
153
  "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
154
  "mlagents_version": "0.31.0.dev0",
@@ -156,162 +10,31 @@
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
- "end_time_seconds": "1691763424"
160
  },
161
- "total": 691.1562118679999,
162
  "count": 1,
163
- "self": 0.19165880500008825,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.040674480999996376,
167
  "count": 1,
168
- "self": 0.040674480999996376
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 690.9238785819998,
172
  "count": 1,
173
- "self": 0.7746667669928229,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 4.768458852999856,
177
  "count": 1,
178
- "self": 4.768458852999856
179
- },
180
- "TrainerController.advance": {
181
- "total": 685.1484289820073,
182
- "count": 26883,
183
- "self": 0.40938644401512647,
184
- "children": {
185
- "env_step": {
186
- "total": 684.7390425379922,
187
- "count": 26883,
188
- "self": 501.09485180801903,
189
- "children": {
190
- "SubprocessEnvManager._take_step": {
191
- "total": 183.25357740800268,
192
- "count": 26883,
193
- "self": 2.5930174109821564,
194
- "children": {
195
- "TorchPolicy.evaluate": {
196
- "total": 180.66055999702053,
197
- "count": 26883,
198
- "self": 180.66055999702053
199
- }
200
- }
201
- },
202
- "workers": {
203
- "total": 0.39061332197047705,
204
- "count": 26882,
205
- "self": 0.0,
206
- "children": {
207
- "worker_root": {
208
- "total": 688.6164984210004,
209
- "count": 26882,
210
- "is_parallel": true,
211
- "self": 327.2182241660014,
212
- "children": {
213
- "run_training.setup": {
214
- "total": 0.0,
215
- "count": 0,
216
- "is_parallel": true,
217
- "self": 0.0,
218
- "children": {
219
- "steps_from_proto": {
220
- "total": 0.0018976139999722363,
221
- "count": 1,
222
- "is_parallel": true,
223
- "self": 0.0005470510002396622,
224
- "children": {
225
- "_process_rank_one_or_two_observation": {
226
- "total": 0.001350562999732574,
227
- "count": 10,
228
- "is_parallel": true,
229
- "self": 0.001350562999732574
230
- }
231
- }
232
- },
233
- "UnityEnvironment.step": {
234
- "total": 0.10005892699996366,
235
- "count": 1,
236
- "is_parallel": true,
237
- "self": 0.0006055829999240814,
238
- "children": {
239
- "UnityEnvironment._generate_step_input": {
240
- "total": 0.0004160969999702502,
241
- "count": 1,
242
- "is_parallel": true,
243
- "self": 0.0004160969999702502
244
- },
245
- "communicator.exchange": {
246
- "total": 0.09690805800005364,
247
- "count": 1,
248
- "is_parallel": true,
249
- "self": 0.09690805800005364
250
- },
251
- "steps_from_proto": {
252
- "total": 0.0021291890000156855,
253
- "count": 1,
254
- "is_parallel": true,
255
- "self": 0.0005352590001166391,
256
- "children": {
257
- "_process_rank_one_or_two_observation": {
258
- "total": 0.0015939299998990464,
259
- "count": 10,
260
- "is_parallel": true,
261
- "self": 0.0015939299998990464
262
- }
263
- }
264
- }
265
- }
266
- }
267
- }
268
- },
269
- "UnityEnvironment.step": {
270
- "total": 361.398274254999,
271
- "count": 26881,
272
- "is_parallel": true,
273
- "self": 15.187808961029532,
274
- "children": {
275
- "UnityEnvironment._generate_step_input": {
276
- "total": 7.747579405995566,
277
- "count": 26881,
278
- "is_parallel": true,
279
- "self": 7.747579405995566
280
- },
281
- "communicator.exchange": {
282
- "total": 286.4625555690027,
283
- "count": 26881,
284
- "is_parallel": true,
285
- "self": 286.4625555690027
286
- },
287
- "steps_from_proto": {
288
- "total": 52.00033031897124,
289
- "count": 26881,
290
- "is_parallel": true,
291
- "self": 9.399238461982577,
292
- "children": {
293
- "_process_rank_one_or_two_observation": {
294
- "total": 42.60109185698866,
295
- "count": 268810,
296
- "is_parallel": true,
297
- "self": 42.60109185698866
298
- }
299
- }
300
- }
301
- }
302
- }
303
- }
304
- }
305
- }
306
- }
307
- }
308
- }
309
- }
310
  },
311
  "trainer_threads": {
312
- "total": 3.8793999920017086e-05,
313
  "count": 1,
314
- "self": 3.8793999920017086e-05,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,38 +43,16 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 679.695424848828,
324
- "count": 617341,
325
  "is_parallel": true,
326
- "self": 13.997225713779017,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 366.7890243520476,
330
- "count": 617341,
331
- "is_parallel": true,
332
- "self": 364.96906045804826,
333
- "children": {
334
- "RLTrainer._checkpoint": {
335
- "total": 1.8199638939993292,
336
- "count": 6,
337
- "is_parallel": true,
338
- "self": 1.8199638939993292
339
- }
340
- }
341
- },
342
- "_update_policy": {
343
- "total": 298.9091747830014,
344
- "count": 134,
345
  "is_parallel": true,
346
- "self": 122.2720735650073,
347
- "children": {
348
- "TorchPPOOptimizer.update": {
349
- "total": 176.6371012179941,
350
- "count": 6831,
351
- "is_parallel": true,
352
- "self": 176.6371012179941
353
- }
354
- }
355
  }
356
  }
357
  }
@@ -360,14 +61,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.2322851859998991,
364
  "count": 1,
365
- "self": 0.002014968999901612,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.2302702169999975,
369
  "count": 1,
370
- "self": 0.2302702169999975
371
  }
372
  }
373
  }
 
1
  {
2
  "name": "root",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "metadata": {
4
  "timer_format_version": "0.1.0",
5
+ "start_time_seconds": "1691763670",
6
  "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
7
  "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
8
  "mlagents_version": "0.31.0.dev0",
 
10
  "communication_protocol_version": "1.5.0",
11
  "pytorch_version": "1.11.0+cu102",
12
  "numpy_version": "1.21.2",
13
+ "end_time_seconds": "1691763675"
14
  },
15
+ "total": 4.54144350200022,
16
  "count": 1,
17
+ "self": 0.4837207909999961,
18
  "children": {
19
  "run_training.setup": {
20
+ "total": 0.039598278000084974,
21
  "count": 1,
22
+ "self": 0.039598278000084974
23
  },
24
  "TrainerController.start_learning": {
25
+ "total": 4.018124433000139,
26
  "count": 1,
27
+ "self": 0.00029738000012002885,
28
  "children": {
29
  "TrainerController._reset_env": {
30
+ "total": 3.864147889999913,
31
  "count": 1,
32
+ "self": 3.864147889999913
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  },
34
  "trainer_threads": {
35
+ "total": 1.5902000086498447e-05,
36
  "count": 1,
37
+ "self": 1.5902000086498447e-05,
38
  "children": {
39
  "thread_root": {
40
  "total": 0.0,
 
43
  "self": 0.0,
44
  "children": {
45
  "trainer_advance": {
46
+ "total": 0.00020726299999296316,
47
+ "count": 1,
48
  "is_parallel": true,
49
+ "self": 1.5640000128769316e-05,
50
  "children": {
51
  "process_trajectory": {
52
+ "total": 0.00019162299986419384,
53
+ "count": 1,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54
  "is_parallel": true,
55
+ "self": 0.00019162299986419384
 
 
 
 
 
 
 
 
56
  }
57
  }
58
  }
 
61
  }
62
  },
63
  "TrainerController._save_models": {
64
+ "total": 0.1536632610000197,
65
  "count": 1,
66
+ "self": 0.0009966580000764225,
67
  "children": {
68
  "RLTrainer._checkpoint": {
69
+ "total": 0.15266660299994328,
70
  "count": 1,
71
+ "self": 0.15266660299994328
72
  }
73
  }
74
  }
run_logs/training_status.json CHANGED
@@ -1,15 +1,6 @@
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
4
- {
5
- "steps": 249944,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.onnx",
7
- "reward": 25.818181818181817,
8
- "creation_time": 1691762426.7397785,
9
- "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.pt"
11
- ]
12
- },
13
  {
14
  "steps": 299968,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
@@ -90,13 +81,22 @@
90
  "auxillary_file_paths": [
91
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-627616.pt"
92
  ]
 
 
 
 
 
 
 
 
 
93
  }
94
  ],
95
  "final_checkpoint": {
96
  "steps": 627616,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
- "reward": 27.727272727272727,
99
- "creation_time": 1691763423.8191903,
100
  "auxillary_file_paths": [
101
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-627616.pt"
102
  ]
 
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
 
 
 
 
 
 
 
 
 
4
  {
5
  "steps": 299968,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
 
81
  "auxillary_file_paths": [
82
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-627616.pt"
83
  ]
84
+ },
85
+ {
86
+ "steps": 627616,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-627616.onnx",
88
+ "reward": null,
89
+ "creation_time": 1691763674.8692813,
90
+ "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-627616.pt"
92
+ ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
  "steps": 627616,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": null,
99
+ "creation_time": 1691763674.8692813,
100
  "auxillary_file_paths": [
101
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-627616.pt"
102
  ]