Hugging Face's logo

uddie6930
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
uddie6930 commited on
Commit
2d2412d
·
verified ·
1 Parent(s): 4b5364c

Second Push

Browse files
Files changed (6) hide show
  1. SnowballTarget/events.out.tfevents.1739107782.f8f55f8fb9b1.9341.0 +3 -0
  2. config.json +1 -1
  3. configuration.yaml +1 -1
  4. run_logs/Player-0.log +18 -21
  5. run_logs/timers.json +17 -325
  6. run_logs/training_status.json +11 -2
SnowballTarget/events.out.tfevents.1739107782.f8f55f8fb9b1.9341.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:084ffbdbb4f7078adca2f482b2f860c79d78ee11fd2436e4dde8597950bc216a
3
+ size 1115
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -69,7 +69,7 @@ checkpoint_settings:
69
  run_id: SnowballTarget1
70
  initialize_from: null
71
  load_model: false
72
- resume: false
73
  force: false
74
  train_model: false
75
  inference: false
 
69
  run_id: SnowballTarget1
70
  initialize_from: null
71
  load_model: false
72
+ resume: true
73
  force: false
74
  train_model: false
75
  inference: false
run_logs/Player-0.log CHANGED
@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
5
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
6
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
7
- Unable to load player prefs
8
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
9
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ 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 0.090 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 +42,7 @@ 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: 0.707086 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 +50,7 @@ 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]: 5367 frames, [16.0 KB-32.0 KB]: 90 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
@@ -81,7 +78,7 @@ Memory Statistics:
81
  [ALLOC_TEMP_Job.Worker 0]
82
  Initial Block Size 256.0 KB
83
  Current Block Size 256.0 KB
84
- Peak Allocated Bytes 3.6 KB
85
  Overflow Count 0
86
  [ALLOC_TEMP_Background Job.Worker 10]
87
  Initial Block Size 32.0 KB
@@ -169,22 +166,22 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 40
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]: 5458 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]: 5458 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
@@ -198,7 +195,7 @@ Memory Statistics:
198
  Overflow Count (full) 0
199
  [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
200
  Initial Block Size 2.0 MB
201
- Used Block Count 2
202
  Overflow Count (too large) 0
203
  Overflow Count (full) 0
204
  [ALLOC_TEMP_JOB_ASYNC (Background)]
@@ -213,13 +210,13 @@ 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]: 5282 frames, [64.0 KB-128.0 KB]: 176 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 66.3 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
@@ -231,13 +228,13 @@ 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]: 5458 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]: 5457 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 +246,13 @@ 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]: 5458 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]: 5458 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  Peak Allocated memory 1.7 KB
 
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
 
 
 
5
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
6
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
7
  Forcing GfxDevice: Null
 
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 0.086 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: 0.704866 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 3
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 4.6 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 17.7 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
@@ -1,358 +1,50 @@
1
  {
2
  "name": "root",
3
- "gauges": {
4
- "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.9171425104141235,
6
- "min": 0.9139718413352966,
7
- "max": 2.863654375076294,
8
- "count": 20
9
- },
10
- "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8716.5224609375,
12
- "min": 8716.5224609375,
13
- "max": 29232.18359375,
14
- "count": 20
15
- },
16
- "SnowballTarget.Step.mean": {
17
- "value": 199984.0,
18
- "min": 9952.0,
19
- "max": 199984.0,
20
- "count": 20
21
- },
22
- "SnowballTarget.Step.sum": {
23
- "value": 199984.0,
24
- "min": 9952.0,
25
- "max": 199984.0,
26
- "count": 20
27
- },
28
- "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 13.088171005249023,
30
- "min": 0.3354174494743347,
31
- "max": 13.17609691619873,
32
- "count": 20
33
- },
34
- "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2552.193359375,
36
- "min": 65.07098388671875,
37
- "max": 2682.166015625,
38
- "count": 20
39
- },
40
- "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.06620853255220688,
42
- "min": 0.06352830653526254,
43
- "max": 0.07263070908791669,
44
- "count": 20
45
- },
46
- "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.2648341302088275,
48
- "min": 0.2541835055282504,
49
- "max": 0.36315354543958345,
50
- "count": 20
51
- },
52
- "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.1973438203042629,
54
- "min": 0.1055590662199036,
55
- "max": 0.3688811693413585,
56
- "count": 20
57
- },
58
- "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.7893752812170516,
60
- "min": 0.4222362648796144,
61
- "max": 1.5794737786054611,
62
- "count": 20
63
- },
64
- "SnowballTarget.Policy.LearningRate.mean": {
65
- "value": 8.082097306000005e-06,
66
- "min": 8.082097306000005e-06,
67
- "max": 0.000291882002706,
68
- "count": 20
69
- },
70
- "SnowballTarget.Policy.LearningRate.sum": {
71
- "value": 3.232838922400002e-05,
72
- "min": 3.232838922400002e-05,
73
- "max": 0.00138516003828,
74
- "count": 20
75
- },
76
- "SnowballTarget.Policy.Epsilon.mean": {
77
- "value": 0.10269400000000001,
78
- "min": 0.10269400000000001,
79
- "max": 0.19729400000000002,
80
- "count": 20
81
- },
82
- "SnowballTarget.Policy.Epsilon.sum": {
83
- "value": 0.41077600000000003,
84
- "min": 0.41077600000000003,
85
- "max": 0.96172,
86
- "count": 20
87
- },
88
- "SnowballTarget.Policy.Beta.mean": {
89
- "value": 0.0001444306000000001,
90
- "min": 0.0001444306000000001,
91
- "max": 0.0048649706,
92
- "count": 20
93
- },
94
- "SnowballTarget.Policy.Beta.sum": {
95
- "value": 0.0005777224000000004,
96
- "min": 0.0005777224000000004,
97
- "max": 0.023089828,
98
- "count": 20
99
- },
100
- "SnowballTarget.Environment.EpisodeLength.mean": {
101
- "value": 199.0,
102
- "min": 199.0,
103
- "max": 199.0,
104
- "count": 20
105
- },
106
- "SnowballTarget.Environment.EpisodeLength.sum": {
107
- "value": 8756.0,
108
- "min": 8756.0,
109
- "max": 10945.0,
110
- "count": 20
111
- },
112
- "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.636363636363637,
114
- "min": 3.0454545454545454,
115
- "max": 26.436363636363637,
116
- "count": 20
117
- },
118
- "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1128.0,
120
- "min": 134.0,
121
- "max": 1454.0,
122
- "count": 20
123
- },
124
- "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.636363636363637,
126
- "min": 3.0454545454545454,
127
- "max": 26.436363636363637,
128
- "count": 20
129
- },
130
- "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1128.0,
132
- "min": 134.0,
133
- "max": 1454.0,
134
- "count": 20
135
- },
136
- "SnowballTarget.IsTraining.mean": {
137
- "value": 1.0,
138
- "min": 1.0,
139
- "max": 1.0,
140
- "count": 20
141
- },
142
- "SnowballTarget.IsTraining.sum": {
143
- "value": 1.0,
144
- "min": 1.0,
145
- "max": 1.0,
146
- "count": 20
147
- }
148
- },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1739106779",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
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": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.6.0+cu124",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1739107204"
160
  },
161
- "total": 424.15454121900007,
162
  "count": 1,
163
- "self": 0.4378308370000923,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.023105839999971067,
167
  "count": 1,
168
- "self": 0.023105839999971067
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 423.693604542,
172
  "count": 1,
173
- "self": 0.34073841399367666,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.039783832000012,
177
  "count": 1,
178
- "self": 3.039783832000012
179
- },
180
- "TrainerController.advance": {
181
- "total": 420.2260998330062,
182
- "count": 18192,
183
- "self": 0.35951644199508337,
184
- "children": {
185
- "env_step": {
186
- "total": 296.1959303170004,
187
- "count": 18192,
188
- "self": 224.90413683299016,
189
- "children": {
190
- "SubprocessEnvManager._take_step": {
191
- "total": 71.08918683801221,
192
- "count": 18192,
193
- "self": 1.2060324990059144,
194
- "children": {
195
- "TorchPolicy.evaluate": {
196
- "total": 69.8831543390063,
197
- "count": 18192,
198
- "self": 69.8831543390063
199
- }
200
- }
201
- },
202
- "workers": {
203
- "total": 0.20260664599800293,
204
- "count": 18192,
205
- "self": 0.0,
206
- "children": {
207
- "worker_root": {
208
- "total": 422.14387631300133,
209
- "count": 18192,
210
- "is_parallel": true,
211
- "self": 225.11183849499298,
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": 0.006146211999976003,
221
- "count": 1,
222
- "is_parallel": true,
223
- "self": 0.004600681999590961,
224
- "children": {
225
- "_process_rank_one_or_two_observation": {
226
- "total": 0.0015455300003850425,
227
- "count": 10,
228
- "is_parallel": true,
229
- "self": 0.0015455300003850425
230
- }
231
- }
232
- },
233
- "UnityEnvironment.step": {
234
- "total": 0.037275760999818885,
235
- "count": 1,
236
- "is_parallel": true,
237
- "self": 0.0005496329995366978,
238
- "children": {
239
- "UnityEnvironment._generate_step_input": {
240
- "total": 0.00037776700014546805,
241
- "count": 1,
242
- "is_parallel": true,
243
- "self": 0.00037776700014546805
244
- },
245
- "communicator.exchange": {
246
- "total": 0.034586056000080134,
247
- "count": 1,
248
- "is_parallel": true,
249
- "self": 0.034586056000080134
250
- },
251
- "steps_from_proto": {
252
- "total": 0.0017623050000565854,
253
- "count": 1,
254
- "is_parallel": true,
255
- "self": 0.0003327950003040314,
256
- "children": {
257
- "_process_rank_one_or_two_observation": {
258
- "total": 0.001429509999752554,
259
- "count": 10,
260
- "is_parallel": true,
261
- "self": 0.001429509999752554
262
- }
263
- }
264
- }
265
- }
266
- }
267
- }
268
- },
269
- "UnityEnvironment.step": {
270
- "total": 197.03203781800835,
271
- "count": 18191,
272
- "is_parallel": true,
273
- "self": 9.341055802030269,
274
- "children": {
275
- "UnityEnvironment._generate_step_input": {
276
- "total": 5.287824204993967,
277
- "count": 18191,
278
- "is_parallel": true,
279
- "self": 5.287824204993967
280
- },
281
- "communicator.exchange": {
282
- "total": 151.99524970498373,
283
- "count": 18191,
284
- "is_parallel": true,
285
- "self": 151.99524970498373
286
- },
287
- "steps_from_proto": {
288
- "total": 30.407908106000377,
289
- "count": 18191,
290
- "is_parallel": true,
291
- "self": 5.348283142966693,
292
- "children": {
293
- "_process_rank_one_or_two_observation": {
294
- "total": 25.059624963033684,
295
- "count": 181910,
296
- "is_parallel": true,
297
- "self": 25.059624963033684
298
- }
299
- }
300
- }
301
- }
302
- }
303
- }
304
- }
305
- }
306
- }
307
- }
308
- },
309
- "trainer_advance": {
310
- "total": 123.67065307401072,
311
- "count": 18192,
312
- "self": 0.39732166100657196,
313
- "children": {
314
- "process_trajectory": {
315
- "total": 26.8313124170038,
316
- "count": 18192,
317
- "self": 26.295496714003548,
318
- "children": {
319
- "RLTrainer._checkpoint": {
320
- "total": 0.535815703000253,
321
- "count": 4,
322
- "self": 0.535815703000253
323
- }
324
- }
325
- },
326
- "_update_policy": {
327
- "total": 96.44201899600034,
328
- "count": 90,
329
- "self": 38.65612696700555,
330
- "children": {
331
- "TorchPPOOptimizer.update": {
332
- "total": 57.785892028994795,
333
- "count": 4587,
334
- "self": 57.785892028994795
335
- }
336
- }
337
- }
338
- }
339
- }
340
- }
341
  },
342
  "trainer_threads": {
343
- "total": 9.600000794307562e-07,
344
  "count": 1,
345
- "self": 9.600000794307562e-07
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.08698150300006091,
349
  "count": 1,
350
- "self": 0.0008936159999848314,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.08608788700007608,
354
  "count": 1,
355
- "self": 0.08608788700007608
356
  }
357
  }
358
  }
 
1
  {
2
  "name": "root",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "metadata": {
4
  "timer_format_version": "0.1.0",
5
+ "start_time_seconds": "1739107782",
6
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
7
+ "command_line_arguments": "/usr/local/bin/mlagents-learn --resume ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
8
  "mlagents_version": "1.2.0.dev0",
9
  "mlagents_envs_version": "1.2.0.dev0",
10
  "communication_protocol_version": "1.5.0",
11
  "pytorch_version": "2.6.0+cu124",
12
  "numpy_version": "1.23.5",
13
+ "end_time_seconds": "1739107785"
14
  },
15
+ "total": 3.6425648360000196,
16
  "count": 1,
17
+ "self": 0.8001334569999017,
18
  "children": {
19
  "run_training.setup": {
20
+ "total": 0.022948951000216766,
21
  "count": 1,
22
+ "self": 0.022948951000216766
23
  },
24
  "TrainerController.start_learning": {
25
+ "total": 2.819482427999901,
26
  "count": 1,
27
+ "self": 0.00017423999997845385,
28
  "children": {
29
  "TrainerController._reset_env": {
30
+ "total": 2.503075215000081,
31
  "count": 1,
32
+ "self": 2.503075215000081
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  },
34
  "trainer_threads": {
35
+ "total": 1.4239999472920317e-06,
36
  "count": 1,
37
+ "self": 1.4239999472920317e-06
38
  },
39
  "TrainerController._save_models": {
40
+ "total": 0.3162315489998946,
41
  "count": 1,
42
+ "self": 0.0015873279999141232,
43
  "children": {
44
  "RLTrainer._checkpoint": {
45
+ "total": 0.31464422099998046,
46
  "count": 1,
47
+ "self": 0.31464422099998046
48
  }
49
  }
50
  }
run_logs/training_status.json CHANGED
@@ -45,13 +45,22 @@
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "final_checkpoint": {
51
  "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 25.545454545454547,
54
- "creation_time": 1739107203.5898087,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
 
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
48
+ },
49
+ {
50
+ "steps": 200112,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
52
+ "reward": null,
53
+ "creation_time": 1739107785.1119068,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
56
+ ]
57
  }
58
  ],
59
  "final_checkpoint": {
60
  "steps": 200112,
61
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
62
+ "reward": null,
63
+ "creation_time": 1739107785.1119068,
64
  "auxillary_file_paths": [
65
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
66
  ]