ShayanDarabi commited on
Commit
cbfd2a8
·
verified ·
1 Parent(s): fd05d78

First Push

Browse files
README.md ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: ml-agents
3
+ tags:
4
+ - SnowballTarget
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - ML-Agents-SnowballTarget
8
+ ---
9
+
10
+ # **ppo** Agent playing **SnowballTarget**
11
+ This is a trained model of a **ppo** agent playing **SnowballTarget**
12
+ using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
13
+
14
+ ## Usage (with ML-Agents)
15
+ The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
16
+
17
+ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
18
+ - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
19
+ browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
20
+ - A *longer tutorial* to understand how works ML-Agents:
21
+ https://huggingface.co/learn/deep-rl-course/unit5/introduction
22
+
23
+ ### Resume the training
24
+ ```bash
25
+ mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
26
+ ```
27
+
28
+ ### Watch your Agent play
29
+ You can watch your agent **playing directly in your browser**
30
+
31
+ 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
32
+ 2. Step 1: Find your model_id: ShayanDarabi/ppo-SnowballTarget
33
+ 3. Step 2: Select your *.nn /*.onnx file
34
+ 4. Click on Watch the agent play 👀
35
+
SnowballTarget.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbf60f4384ee216d0da874a2658489192a6adff4b670bfa342c141a03dd8835a
3
+ size 650646
SnowballTarget/SnowballTarget-17600.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:381999cd85f930d5e6ed33b3273c4d172ea1a280fde690f58ac5a14a6c5ff3c9
3
+ size 650646
SnowballTarget/SnowballTarget-17600.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc31787d693dfe9a9567a0b1d1ffb82a9899a50d6dc0a51faae53846a3e97267
3
+ size 3850487
SnowballTarget/SnowballTarget-400400.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbf60f4384ee216d0da874a2658489192a6adff4b670bfa342c141a03dd8835a
3
+ size 650646
SnowballTarget/SnowballTarget-400400.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3aa8050e45a560e710a41cb27fe87d30ecfb2c5cf96600ca63c0b715f46bba3
3
+ size 3850564
SnowballTarget/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c0282181599fdb93a4d8f12c893a981d175a7083cef656460a44268dda4e7b9
3
+ size 3849717
SnowballTarget/events.out.tfevents.1758145051.f4c333abcf12.14137.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c126b324c7b3a4dae05c3010fbc73a8393a96b31543f8da502e22a9b78ee8e6
3
+ size 13623
config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 256, "buffer_size": 8192, "learning_rate": 0.00025, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "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": 5, "even_checkpoints": false, "max_steps": 400000, "time_horizon": 128, "summary_freq": 50000, "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": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ default_settings: null
2
+ behaviors:
3
+ SnowballTarget:
4
+ trainer_type: ppo
5
+ hyperparameters:
6
+ batch_size: 256
7
+ buffer_size: 8192
8
+ learning_rate: 0.00025
9
+ beta: 0.01
10
+ epsilon: 0.2
11
+ lambd: 0.95
12
+ num_epoch: 3
13
+ shared_critic: false
14
+ learning_rate_schedule: linear
15
+ beta_schedule: linear
16
+ epsilon_schedule: linear
17
+ checkpoint_interval: 500000
18
+ network_settings:
19
+ normalize: false
20
+ hidden_units: 256
21
+ num_layers: 2
22
+ vis_encode_type: simple
23
+ memory: null
24
+ goal_conditioning_type: hyper
25
+ deterministic: false
26
+ reward_signals:
27
+ extrinsic:
28
+ gamma: 0.99
29
+ strength: 1.0
30
+ network_settings:
31
+ normalize: false
32
+ hidden_units: 128
33
+ num_layers: 2
34
+ vis_encode_type: simple
35
+ memory: null
36
+ goal_conditioning_type: hyper
37
+ deterministic: false
38
+ init_path: null
39
+ keep_checkpoints: 5
40
+ even_checkpoints: false
41
+ max_steps: 400000
42
+ time_horizon: 128
43
+ summary_freq: 50000
44
+ threaded: false
45
+ self_play: null
46
+ behavioral_cloning: null
47
+ env_settings:
48
+ env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
49
+ env_args: null
50
+ base_port: 5005
51
+ num_envs: 1
52
+ num_areas: 1
53
+ timeout_wait: 60
54
+ seed: -1
55
+ max_lifetime_restarts: 10
56
+ restarts_rate_limit_n: 1
57
+ restarts_rate_limit_period_s: 60
58
+ engine_settings:
59
+ width: 84
60
+ height: 84
61
+ quality_level: 5
62
+ time_scale: 20
63
+ target_frame_rate: -1
64
+ capture_frame_rate: 60
65
+ no_graphics: true
66
+ no_graphics_monitor: false
67
+ environment_parameters: null
68
+ checkpoint_settings:
69
+ run_id: SnowballTarget1
70
+ initialize_from: null
71
+ load_model: false
72
+ resume: false
73
+ force: true
74
+ train_model: false
75
+ inference: false
76
+ results_dir: results
77
+ torch_settings:
78
+ device: null
79
+ debug: false
run_logs/Player-0.log ADDED
@@ -0,0 +1,309 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
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
8
+ GfxDevice: creating device client; threaded=0; jobified=0
9
+ NullGfxDevice:
10
+ Version: NULL 1.0 [1.0]
11
+ Renderer: Null Device
12
+ Vendor: Unity Technologies
13
+ ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
14
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
15
+ ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
16
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
17
+ ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
18
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
19
+ ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
20
+ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
21
+ FMOD failed to initialize the output device.: "Error initializing output device. " (60)
22
+ Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
23
+ ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
24
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
25
+ ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
26
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
27
+ ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
28
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
29
+ ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
30
+ 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 0.086 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)
38
+ WARNING: Shader Unsupported: 'Standard' - All subshaders removed
39
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
40
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
41
+ ERROR: Shader Standard 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: 0.681657 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 6 worker threads for Enlighten.
49
+ 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]: 10737 frames, [16.0 KB-32.0 KB]: 182 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
57
+ Overflow Count 0
58
+ [ALLOC_TEMP_Loading.AsyncRead]
59
+ Initial Block Size 64.0 KB
60
+ Current Block Size 64.0 KB
61
+ Peak Allocated Bytes 198 B
62
+ Overflow Count 0
63
+ [ALLOC_TEMP_Loading.PreloadManager]
64
+ Initial Block Size 256.0 KB
65
+ Current Block Size 304.0 KB
66
+ Peak Allocated Bytes 228.9 KB
67
+ Overflow Count 4
68
+ [ALLOC_TEMP_Background Job.Worker 8]
69
+ Initial Block Size 32.0 KB
70
+ Current Block Size 32.0 KB
71
+ Peak Allocated Bytes 0 B
72
+ Overflow Count 0
73
+ [ALLOC_TEMP_Job.Worker 6]
74
+ Initial Block Size 256.0 KB
75
+ Current Block Size 256.0 KB
76
+ Peak Allocated Bytes 3.6 KB
77
+ Overflow Count 0
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
85
+ Current Block Size 32.0 KB
86
+ Peak Allocated Bytes 0 B
87
+ Overflow Count 0
88
+ [ALLOC_TEMP_Background Job.Worker 9]
89
+ Initial Block Size 32.0 KB
90
+ Current Block Size 32.0 KB
91
+ Peak Allocated Bytes 0 B
92
+ Overflow Count 0
93
+ [ALLOC_TEMP_Job.Worker 5]
94
+ Initial Block Size 256.0 KB
95
+ Current Block Size 256.0 KB
96
+ Peak Allocated Bytes 3.6 KB
97
+ Overflow Count 0
98
+ [ALLOC_TEMP_Background Job.Worker 14]
99
+ Initial Block Size 32.0 KB
100
+ Current Block Size 32.0 KB
101
+ Peak Allocated Bytes 0 B
102
+ Overflow Count 0
103
+ [ALLOC_TEMP_Background Job.Worker 6]
104
+ Initial Block Size 32.0 KB
105
+ Current Block Size 32.0 KB
106
+ Peak Allocated Bytes 0 B
107
+ Overflow Count 0
108
+ [ALLOC_TEMP_Job.Worker 4]
109
+ Initial Block Size 256.0 KB
110
+ Current Block Size 256.0 KB
111
+ Peak Allocated Bytes 3.6 KB
112
+ Overflow Count 0
113
+ [ALLOC_TEMP_Job.Worker 3]
114
+ Initial Block Size 256.0 KB
115
+ Current Block Size 256.0 KB
116
+ Peak Allocated Bytes 3.6 KB
117
+ Overflow Count 0
118
+ [ALLOC_TEMP_Background Job.Worker 12]
119
+ Initial Block Size 32.0 KB
120
+ Current Block Size 32.0 KB
121
+ Peak Allocated Bytes 0 B
122
+ Overflow Count 0
123
+ [ALLOC_TEMP_EnlightenWorker] x 6
124
+ Initial Block Size 64.0 KB
125
+ Current Block Size 64.0 KB
126
+ Peak Allocated Bytes 0 B
127
+ Overflow Count 0
128
+ [ALLOC_TEMP_Background Job.Worker 15]
129
+ Initial Block Size 32.0 KB
130
+ Current Block Size 32.0 KB
131
+ Peak Allocated Bytes 0 B
132
+ Overflow Count 0
133
+ [ALLOC_TEMP_Background Job.Worker 1]
134
+ Initial Block Size 32.0 KB
135
+ Current Block Size 32.0 KB
136
+ Peak Allocated Bytes 0 B
137
+ Overflow Count 0
138
+ [ALLOC_TEMP_Background Job.Worker 2]
139
+ Initial Block Size 32.0 KB
140
+ Current Block Size 32.0 KB
141
+ Peak Allocated Bytes 0 B
142
+ Overflow Count 0
143
+ [ALLOC_TEMP_Background Job.Worker 7]
144
+ Initial Block Size 32.0 KB
145
+ Current Block Size 32.0 KB
146
+ Peak Allocated Bytes 0 B
147
+ Overflow Count 0
148
+ [ALLOC_TEMP_AssetGarbageCollectorHelper] x 11
149
+ Initial Block Size 64.0 KB
150
+ Current Block Size 64.0 KB
151
+ Peak Allocated Bytes 0 B
152
+ Overflow Count 0
153
+ [ALLOC_TEMP_Background Job.Worker 5]
154
+ Initial Block Size 32.0 KB
155
+ Current Block Size 32.0 KB
156
+ Peak Allocated Bytes 0 B
157
+ Overflow Count 0
158
+ [ALLOC_TEMP_Job.Worker 9]
159
+ Initial Block Size 256.0 KB
160
+ Current Block Size 256.0 KB
161
+ Peak Allocated Bytes 3.6 KB
162
+ Overflow Count 0
163
+ [ALLOC_TEMP_Background Job.Worker 13]
164
+ Initial Block Size 32.0 KB
165
+ Current Block Size 32.0 KB
166
+ Peak Allocated Bytes 0 B
167
+ Overflow Count 0
168
+ [ALLOC_TEMP_Job.Worker 8]
169
+ Initial Block Size 256.0 KB
170
+ Current Block Size 256.0 KB
171
+ Peak Allocated Bytes 3.6 KB
172
+ Overflow Count 0
173
+ [ALLOC_TEMP_Job.Worker 7]
174
+ Initial Block Size 256.0 KB
175
+ Current Block Size 256.0 KB
176
+ Peak Allocated Bytes 3.6 KB
177
+ Overflow Count 0
178
+ [ALLOC_TEMP_Job.Worker 1]
179
+ Initial Block Size 256.0 KB
180
+ Current Block Size 256.0 KB
181
+ Peak Allocated Bytes 3.6 KB
182
+ Overflow Count 0
183
+ [ALLOC_TEMP_Job.Worker 2]
184
+ Initial Block Size 256.0 KB
185
+ Current Block Size 256.0 KB
186
+ Peak Allocated Bytes 3.6 KB
187
+ Overflow Count 0
188
+ [ALLOC_TEMP_Background Job.Worker 3]
189
+ Initial Block Size 32.0 KB
190
+ Current Block Size 32.0 KB
191
+ Peak Allocated Bytes 0 B
192
+ Overflow Count 0
193
+ [ALLOC_TEMP_Background Job.Worker 11]
194
+ Initial Block Size 32.0 KB
195
+ Current Block Size 32.0 KB
196
+ Peak Allocated Bytes 0 B
197
+ Overflow Count 0
198
+ [ALLOC_TEMP_Job.Worker 10]
199
+ Initial Block Size 256.0 KB
200
+ Current Block Size 256.0 KB
201
+ Peak Allocated Bytes 3.6 KB
202
+ Overflow Count 0
203
+ [ALLOC_TEMP_Background Job.Worker 0]
204
+ Initial Block Size 32.0 KB
205
+ Current Block Size 32.0 KB
206
+ Peak Allocated Bytes 0 B
207
+ Overflow Count 0
208
+ [ALLOC_TEMP_Background Job.Worker 4]
209
+ Initial Block Size 32.0 KB
210
+ Current Block Size 32.0 KB
211
+ Peak Allocated Bytes 0 B
212
+ Overflow Count 0
213
+ [ALLOC_TEMP_BatchDeleteObjects]
214
+ Initial Block Size 64.0 KB
215
+ Current Block Size 64.0 KB
216
+ Peak Allocated Bytes 0 B
217
+ Overflow Count 0
218
+ [ALLOC_DEFAULT] Dual Thread Allocator
219
+ Peak main deferred allocation count 37
220
+ [ALLOC_BUCKET]
221
+ Large Block size 4.0 MB
222
+ Used Block count 1
223
+ Peak Allocated bytes 1.0 MB
224
+ [ALLOC_DEFAULT_MAIN]
225
+ Peak usage frame count: [4.0 MB-8.0 MB]: 10920 frames
226
+ Requested Block Size 16.0 MB
227
+ Peak Block count 1
228
+ Peak Allocated memory 8.9 MB
229
+ Peak Large allocation bytes 0 B
230
+ [ALLOC_DEFAULT_THREAD]
231
+ Peak usage frame count: [16.0 MB-32.0 MB]: 10920 frames
232
+ Requested Block Size 16.0 MB
233
+ Peak Block count 1
234
+ Peak Allocated memory 17.6 MB
235
+ Peak Large allocation bytes 16.0 MB
236
+ [ALLOC_TEMP_JOB_1_FRAME]
237
+ Initial Block Size 2.0 MB
238
+ Used Block Count 1
239
+ Overflow Count (too large) 0
240
+ Overflow Count (full) 0
241
+ [ALLOC_TEMP_JOB_2_FRAMES]
242
+ Initial Block Size 2.0 MB
243
+ Used Block Count 1
244
+ Overflow Count (too large) 0
245
+ Overflow Count (full) 0
246
+ [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
247
+ Initial Block Size 2.0 MB
248
+ Used Block Count 2
249
+ Overflow Count (too large) 0
250
+ Overflow Count (full) 0
251
+ [ALLOC_TEMP_JOB_ASYNC (Background)]
252
+ Initial Block Size 1.0 MB
253
+ Used Block Count 3
254
+ Overflow Count (too large) 0
255
+ Overflow Count (full) 0
256
+ [ALLOC_GFX] Dual Thread Allocator
257
+ Peak main deferred allocation count 0
258
+ [ALLOC_BUCKET]
259
+ Large Block size 4.0 MB
260
+ Used Block count 1
261
+ Peak Allocated bytes 1.0 MB
262
+ [ALLOC_GFX_MAIN]
263
+ Peak usage frame count: [32.0 KB-64.0 KB]: 10065 frames, [64.0 KB-128.0 KB]: 855 frames
264
+ Requested Block Size 16.0 MB
265
+ Peak Block count 1
266
+ Peak Allocated memory 66.4 KB
267
+ Peak Large allocation bytes 0 B
268
+ [ALLOC_GFX_THREAD]
269
+ Peak usage frame count: [32.0 KB-64.0 KB]: 10920 frames
270
+ Requested Block Size 16.0 MB
271
+ Peak Block count 1
272
+ Peak Allocated memory 39.6 KB
273
+ Peak Large allocation bytes 0 B
274
+ [ALLOC_CACHEOBJECTS] 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 1.0 MB
280
+ [ALLOC_CACHEOBJECTS_MAIN]
281
+ Peak usage frame count: [0.5 MB-1.0 MB]: 10920 frames
282
+ Requested Block Size 4.0 MB
283
+ Peak Block count 1
284
+ Peak Allocated memory 0.6 MB
285
+ Peak Large allocation bytes 0 B
286
+ [ALLOC_CACHEOBJECTS_THREAD]
287
+ Peak usage frame count: [0.5 MB-1.0 MB]: 10919 frames, [2.0 MB-4.0 MB]: 1 frames
288
+ Requested Block Size 4.0 MB
289
+ Peak Block count 1
290
+ Peak Allocated memory 2.2 MB
291
+ Peak Large allocation bytes 0 B
292
+ [ALLOC_TYPETREE] Dual Thread Allocator
293
+ Peak main deferred allocation count 0
294
+ [ALLOC_BUCKET]
295
+ Large Block size 4.0 MB
296
+ Used Block count 1
297
+ Peak Allocated bytes 1.0 MB
298
+ [ALLOC_TYPETREE_MAIN]
299
+ Peak usage frame count: [0-1.0 KB]: 10920 frames
300
+ Requested Block Size 2.0 MB
301
+ Peak Block count 1
302
+ Peak Allocated memory 1.0 KB
303
+ Peak Large allocation bytes 0 B
304
+ [ALLOC_TYPETREE_THREAD]
305
+ Peak usage frame count: [1.0 KB-2.0 KB]: 10920 frames
306
+ Requested Block Size 2.0 MB
307
+ Peak Block count 1
308
+ Peak Allocated memory 1.7 KB
309
+ Peak Large allocation bytes 0 B
run_logs/timers.json ADDED
@@ -0,0 +1,355 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 1.209212303161621,
6
+ "min": 1.209212303161621,
7
+ "max": 2.8242242336273193,
8
+ "count": 8
9
+ },
10
+ "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 59483.5703125,
12
+ "min": 59483.5703125,
13
+ "max": 142905.75,
14
+ "count": 8
15
+ },
16
+ "SnowballTarget.Step.mean": {
17
+ "value": 399968.0,
18
+ "min": 49952.0,
19
+ "max": 399968.0,
20
+ "count": 8
21
+ },
22
+ "SnowballTarget.Step.sum": {
23
+ "value": 399968.0,
24
+ "min": 49952.0,
25
+ "max": 399968.0,
26
+ "count": 8
27
+ },
28
+ "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 11.875980377197266,
30
+ "min": 0.6528778672218323,
31
+ "max": 11.875980377197266,
32
+ "count": 8
33
+ },
34
+ "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 5926.1142578125,
36
+ "min": 324.48028564453125,
37
+ "max": 5926.1142578125,
38
+ "count": 8
39
+ },
40
+ "SnowballTarget.Environment.EpisodeLength.mean": {
41
+ "value": 199.0,
42
+ "min": 199.0,
43
+ "max": 199.0,
44
+ "count": 8
45
+ },
46
+ "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 50347.0,
48
+ "min": 48158.0,
49
+ "max": 50347.0,
50
+ "count": 8
51
+ },
52
+ "SnowballTarget.Environment.CumulativeReward.mean": {
53
+ "value": 24.805668016194332,
54
+ "min": 5.131147540983607,
55
+ "max": 24.805668016194332,
56
+ "count": 8
57
+ },
58
+ "SnowballTarget.Environment.CumulativeReward.sum": {
59
+ "value": 6127.0,
60
+ "min": 1252.0,
61
+ "max": 6127.0,
62
+ "count": 8
63
+ },
64
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
+ "value": 24.805668016194332,
66
+ "min": 5.131147540983607,
67
+ "max": 24.805668016194332,
68
+ "count": 8
69
+ },
70
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
+ "value": 6127.0,
72
+ "min": 1252.0,
73
+ "max": 6127.0,
74
+ "count": 8
75
+ },
76
+ "SnowballTarget.Losses.PolicyLoss.mean": {
77
+ "value": 0.04958774980433663,
78
+ "min": 0.0474208151068298,
79
+ "max": 0.05259989834922439,
80
+ "count": 8
81
+ },
82
+ "SnowballTarget.Losses.PolicyLoss.sum": {
83
+ "value": 0.2975264988260198,
84
+ "min": 0.2516684853641588,
85
+ "max": 0.2975264988260198,
86
+ "count": 8
87
+ },
88
+ "SnowballTarget.Losses.ValueLoss.mean": {
89
+ "value": 0.23279210964059519,
90
+ "min": 0.1735464586492847,
91
+ "max": 0.3095150000714009,
92
+ "count": 8
93
+ },
94
+ "SnowballTarget.Losses.ValueLoss.sum": {
95
+ "value": 1.3967526578435712,
96
+ "min": 0.8677322932464234,
97
+ "max": 1.8570900004284057,
98
+ "count": 8
99
+ },
100
+ "SnowballTarget.Policy.LearningRate.mean": {
101
+ "value": 1.6250093500000004e-05,
102
+ "min": 1.6250093500000004e-05,
103
+ "max": 0.00023350000660000004,
104
+ "count": 8
105
+ },
106
+ "SnowballTarget.Policy.LearningRate.sum": {
107
+ "value": 9.750056100000003e-05,
108
+ "min": 9.750056100000003e-05,
109
+ "max": 0.0012195001122,
110
+ "count": 8
111
+ },
112
+ "SnowballTarget.Policy.Epsilon.mean": {
113
+ "value": 0.1065,
114
+ "min": 0.1065,
115
+ "max": 0.1934,
116
+ "count": 8
117
+ },
118
+ "SnowballTarget.Policy.Epsilon.sum": {
119
+ "value": 0.639,
120
+ "min": 0.5930000000000001,
121
+ "max": 1.0878,
122
+ "count": 8
123
+ },
124
+ "SnowballTarget.Policy.Beta.mean": {
125
+ "value": 0.00065935,
126
+ "min": 0.00065935,
127
+ "max": 0.00934066,
128
+ "count": 8
129
+ },
130
+ "SnowballTarget.Policy.Beta.sum": {
131
+ "value": 0.0039561,
132
+ "min": 0.0039561,
133
+ "max": 0.04879121999999999,
134
+ "count": 8
135
+ },
136
+ "SnowballTarget.IsTraining.mean": {
137
+ "value": 1.0,
138
+ "min": 1.0,
139
+ "max": 1.0,
140
+ "count": 8
141
+ },
142
+ "SnowballTarget.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": "1758145051",
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 --force",
154
+ "mlagents_version": "1.1.0",
155
+ "mlagents_envs_version": "1.1.0",
156
+ "communication_protocol_version": "1.5.0",
157
+ "pytorch_version": "2.8.0+cu128",
158
+ "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1758145728"
160
+ },
161
+ "total": 677.4436931350001,
162
+ "count": 1,
163
+ "self": 0.32109526099975483,
164
+ "children": {
165
+ "run_training.setup": {
166
+ "total": 0.026454711000042153,
167
+ "count": 1,
168
+ "self": 0.026454711000042153
169
+ },
170
+ "TrainerController.start_learning": {
171
+ "total": 677.0961431630003,
172
+ "count": 1,
173
+ "self": 0.6332221040242985,
174
+ "children": {
175
+ "TrainerController._reset_env": {
176
+ "total": 1.9476772569996683,
177
+ "count": 1,
178
+ "self": 1.9476772569996683
179
+ },
180
+ "TrainerController.advance": {
181
+ "total": 674.4041693889767,
182
+ "count": 36400,
183
+ "self": 0.6272513990229527,
184
+ "children": {
185
+ "env_step": {
186
+ "total": 508.21731679997174,
187
+ "count": 36400,
188
+ "self": 381.10785631494036,
189
+ "children": {
190
+ "SubprocessEnvManager._take_step": {
191
+ "total": 126.708802362999,
192
+ "count": 36400,
193
+ "self": 2.2649682640167157,
194
+ "children": {
195
+ "TorchPolicy.evaluate": {
196
+ "total": 124.44383409898228,
197
+ "count": 36400,
198
+ "self": 124.44383409898228
199
+ }
200
+ }
201
+ },
202
+ "workers": {
203
+ "total": 0.4006581220323824,
204
+ "count": 36400,
205
+ "self": 0.0,
206
+ "children": {
207
+ "worker_root": {
208
+ "total": 675.8870114989945,
209
+ "count": 36400,
210
+ "is_parallel": true,
211
+ "self": 339.12555576698423,
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": 0.0020347529998616665,
221
+ "count": 1,
222
+ "is_parallel": true,
223
+ "self": 0.0006430769994949515,
224
+ "children": {
225
+ "_process_rank_one_or_two_observation": {
226
+ "total": 0.001391676000366715,
227
+ "count": 10,
228
+ "is_parallel": true,
229
+ "self": 0.001391676000366715
230
+ }
231
+ }
232
+ },
233
+ "UnityEnvironment.step": {
234
+ "total": 0.02611853799999153,
235
+ "count": 1,
236
+ "is_parallel": true,
237
+ "self": 0.0003562830002010742,
238
+ "children": {
239
+ "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0002890020000450022,
241
+ "count": 1,
242
+ "is_parallel": true,
243
+ "self": 0.0002890020000450022
244
+ },
245
+ "communicator.exchange": {
246
+ "total": 0.02425154799993834,
247
+ "count": 1,
248
+ "is_parallel": true,
249
+ "self": 0.02425154799993834
250
+ },
251
+ "steps_from_proto": {
252
+ "total": 0.0012217049998071161,
253
+ "count": 1,
254
+ "is_parallel": true,
255
+ "self": 0.0002494999998816638,
256
+ "children": {
257
+ "_process_rank_one_or_two_observation": {
258
+ "total": 0.0009722049999254523,
259
+ "count": 10,
260
+ "is_parallel": true,
261
+ "self": 0.0009722049999254523
262
+ }
263
+ }
264
+ }
265
+ }
266
+ }
267
+ }
268
+ },
269
+ "UnityEnvironment.step": {
270
+ "total": 336.7614557320103,
271
+ "count": 36399,
272
+ "is_parallel": true,
273
+ "self": 11.670995255972684,
274
+ "children": {
275
+ "UnityEnvironment._generate_step_input": {
276
+ "total": 6.499668004979867,
277
+ "count": 36399,
278
+ "is_parallel": true,
279
+ "self": 6.499668004979867
280
+ },
281
+ "communicator.exchange": {
282
+ "total": 279.07402830503634,
283
+ "count": 36399,
284
+ "is_parallel": true,
285
+ "self": 279.07402830503634
286
+ },
287
+ "steps_from_proto": {
288
+ "total": 39.5167641660214,
289
+ "count": 36399,
290
+ "is_parallel": true,
291
+ "self": 7.585900557974128,
292
+ "children": {
293
+ "_process_rank_one_or_two_observation": {
294
+ "total": 31.930863608047275,
295
+ "count": 363990,
296
+ "is_parallel": true,
297
+ "self": 31.930863608047275
298
+ }
299
+ }
300
+ }
301
+ }
302
+ }
303
+ }
304
+ }
305
+ }
306
+ }
307
+ }
308
+ },
309
+ "trainer_advance": {
310
+ "total": 165.559601189982,
311
+ "count": 36400,
312
+ "self": 0.8393168810180214,
313
+ "children": {
314
+ "process_trajectory": {
315
+ "total": 37.85711024496686,
316
+ "count": 36400,
317
+ "self": 37.85711024496686
318
+ },
319
+ "_update_policy": {
320
+ "total": 126.86317406399712,
321
+ "count": 45,
322
+ "self": 71.88893897100843,
323
+ "children": {
324
+ "TorchPPOOptimizer.update": {
325
+ "total": 54.97423509298869,
326
+ "count": 4590,
327
+ "self": 54.97423509298869
328
+ }
329
+ }
330
+ }
331
+ }
332
+ }
333
+ }
334
+ },
335
+ "trainer_threads": {
336
+ "total": 1.0249996194033884e-06,
337
+ "count": 1,
338
+ "self": 1.0249996194033884e-06
339
+ },
340
+ "TrainerController._save_models": {
341
+ "total": 0.11107338800002253,
342
+ "count": 1,
343
+ "self": 0.0010064709999824117,
344
+ "children": {
345
+ "RLTrainer._checkpoint": {
346
+ "total": 0.11006691700004012,
347
+ "count": 1,
348
+ "self": 0.11006691700004012
349
+ }
350
+ }
351
+ }
352
+ }
353
+ }
354
+ }
355
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "SnowballTarget": {
3
+ "checkpoints": [
4
+ {
5
+ "steps": 400400,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-400400.onnx",
7
+ "reward": 25.454545454545453,
8
+ "creation_time": 1758145728.4173408,
9
+ "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-400400.pt"
11
+ ]
12
+ }
13
+ ],
14
+ "final_checkpoint": {
15
+ "steps": 400400,
16
+ "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
17
+ "reward": 25.454545454545453,
18
+ "creation_time": 1758145728.4173408,
19
+ "auxillary_file_paths": [
20
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-400400.pt"
21
+ ]
22
+ }
23
+ },
24
+ "metadata": {
25
+ "stats_format_version": "0.3.0",
26
+ "mlagents_version": "1.1.0",
27
+ "torch_version": "2.8.0+cu128"
28
+ }
29
+ }