inkasaras commited on
Commit
efcf543
1 Parent(s): 7a032aa

First Push

Browse files
README.md ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
12
+
13
+ ## Usage (with ML-Agents)
14
+ The Documentation: https://github.com/huggingface/ml-agents#get-started
15
+ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
16
+
17
+
18
+ ### Resume the training
19
+ ```
20
+ mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
21
+ ```
22
+ ### Watch your Agent play
23
+ You can watch your agent **playing directly in your browser:**.
24
+
25
+ 1. Go to https://huggingface.co/spaces/unity/ML-Agents-SnowballTarget
26
+ 2. Step 1: Find your model_id: inkasaras/ppo-SnowballTarget
27
+ 3. Step 2: Select your *.nn /*.onnx file
28
+ 4. Click on Watch the agent play 👀
29
+
SnowballTarget.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0438c442a5c3b6da49aa7bf6a9a0af11456fd5aae8c0ca0a910522087a1be7d0
3
+ size 646532
SnowballTarget/SnowballTarget-11576.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0438c442a5c3b6da49aa7bf6a9a0af11456fd5aae8c0ca0a910522087a1be7d0
3
+ size 646532
SnowballTarget/SnowballTarget-11576.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7173ef5a56630bd9fdd796d76d0f479cfee8bf869281bc8ef73c816e2ead414
3
+ size 3843968
SnowballTarget/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7173ef5a56630bd9fdd796d76d0f479cfee8bf869281bc8ef73c816e2ead414
3
+ size 3843968
SnowballTarget/events.out.tfevents.1679087846.f747f017bcf1.2117.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46e3b1d5427b59f5c8eb182e8ac98227c7eb5c5eddffa7d5209a4c7ed87ed707
3
+ size 6798
config.json ADDED
@@ -0,0 +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": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ default_settings: null
2
+ behaviors:
3
+ SnowballTarget:
4
+ trainer_type: ppo
5
+ hyperparameters:
6
+ batch_size: 128
7
+ buffer_size: 2048
8
+ learning_rate: 0.0003
9
+ beta: 0.005
10
+ epsilon: 0.2
11
+ lambd: 0.95
12
+ num_epoch: 3
13
+ shared_critic: false
14
+ learning_rate_schedule: linear
15
+ beta_schedule: linear
16
+ epsilon_schedule: linear
17
+ checkpoint_interval: 50000
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: 10
40
+ even_checkpoints: false
41
+ max_steps: 200000
42
+ time_horizon: 64
43
+ summary_freq: 10000
44
+ threaded: true
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
+ seed: -1
54
+ max_lifetime_restarts: 10
55
+ restarts_rate_limit_n: 1
56
+ restarts_rate_limit_period_s: 60
57
+ engine_settings:
58
+ width: 84
59
+ height: 84
60
+ quality_level: 5
61
+ time_scale: 20
62
+ target_frame_rate: -1
63
+ capture_frame_rate: 60
64
+ no_graphics: true
65
+ environment_parameters: null
66
+ checkpoint_settings:
67
+ run_id: SnowballTarget1
68
+ initialize_from: null
69
+ load_model: false
70
+ resume: false
71
+ force: false
72
+ train_model: false
73
+ inference: false
74
+ results_dir: results
75
+ torch_settings:
76
+ device: null
77
+ debug: false
run_logs/Player-0.log ADDED
@@ -0,0 +1,263 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ 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
11
+ GfxDevice: creating device client; threaded=0; jobified=0
12
+ NullGfxDevice:
13
+ Version: NULL 1.0 [1.0]
14
+ Renderer: Null Device
15
+ Vendor: Unity Technologies
16
+ ALSA lib confmisc.c:767:(parse_card) cannot find card '0'
17
+ ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
18
+ ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
19
+ ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
20
+ ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
21
+ ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
22
+ ALSA lib conf.c:5220:(snd_config_expand) Evaluate error: No such file or directory
23
+ ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
24
+ FMOD failed to initialize the output device.: "Error initializing output device. " (60)
25
+ 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
26
+ ALSA lib confmisc.c:767:(parse_card) cannot find card '0'
27
+ ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
28
+ ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
29
+ ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
30
+ ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
31
+ ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
32
+ ALSA lib conf.c:5220:(snd_config_expand) Evaluate error: No such file or directory
33
+ ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
34
+ FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
+ FMOD initialized on nosound output
36
+ Begin MonoManager ReloadAssembly
37
+ - Completed reload, in 0.082 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)
41
+ WARNING: Shader Unsupported: 'Standard' - All subshaders removed
42
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
43
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
44
+ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
45
+ WARNING: Shader Unsupported: 'Standard' - All subshaders removed
46
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
47
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
48
+ UnloadTime: 1.116642 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
+ GRPC Exception: Status(StatusCode=Cancelled, Detail="CANCELLED"). Disconnecting from trainer.
52
+ Setting up 1 worker threads for Enlighten.
53
+ Memory Statistics:
54
+ [ALLOC_TEMP_TLS] TLS Allocator
55
+ StackAllocators :
56
+ [ALLOC_TEMP_MAIN]
57
+ Peak usage frame count: [8.0 KB-16.0 KB]: 316 frames, [16.0 KB-32.0 KB]: 5 frames, [2.0 MB-4.0 MB]: 1 frames
58
+ Initial Block Size 4.0 MB
59
+ Current Block Size 4.0 MB
60
+ Peak Allocated Bytes 2.0 MB
61
+ Overflow Count 0
62
+ [ALLOC_TEMP_Loading.AsyncRead]
63
+ Initial Block Size 64.0 KB
64
+ Current Block Size 64.0 KB
65
+ Peak Allocated Bytes 198 B
66
+ Overflow Count 0
67
+ [ALLOC_TEMP_Loading.PreloadManager]
68
+ Initial Block Size 256.0 KB
69
+ Current Block Size 304.0 KB
70
+ Peak Allocated Bytes 228.9 KB
71
+ Overflow Count 4
72
+ [ALLOC_TEMP_Background Job.Worker 8]
73
+ Initial Block Size 32.0 KB
74
+ Current Block Size 32.0 KB
75
+ Peak Allocated Bytes 0 B
76
+ Overflow Count 0
77
+ [ALLOC_TEMP_Background Job.Worker 9]
78
+ Initial Block Size 32.0 KB
79
+ Current Block Size 32.0 KB
80
+ Peak Allocated Bytes 0 B
81
+ Overflow Count 0
82
+ [ALLOC_TEMP_Job.Worker 0]
83
+ Initial Block Size 256.0 KB
84
+ Current Block Size 256.0 KB
85
+ Peak Allocated Bytes 3.6 KB
86
+ Overflow Count 0
87
+ [ALLOC_TEMP_Background Job.Worker 10]
88
+ Initial Block Size 32.0 KB
89
+ Current Block Size 32.0 KB
90
+ Peak Allocated Bytes 0 B
91
+ Overflow Count 0
92
+ [ALLOC_TEMP_Background Job.Worker 14]
93
+ Initial Block Size 32.0 KB
94
+ Current Block Size 32.0 KB
95
+ Peak Allocated Bytes 0 B
96
+ Overflow Count 0
97
+ [ALLOC_TEMP_Background Job.Worker 6]
98
+ Initial Block Size 32.0 KB
99
+ Current Block Size 32.0 KB
100
+ Peak Allocated Bytes 0 B
101
+ Overflow Count 0
102
+ [ALLOC_TEMP_Background Job.Worker 12]
103
+ Initial Block Size 32.0 KB
104
+ Current Block Size 32.0 KB
105
+ Peak Allocated Bytes 0 B
106
+ Overflow Count 0
107
+ [ALLOC_TEMP_EnlightenWorker]
108
+ Initial Block Size 64.0 KB
109
+ Current Block Size 64.0 KB
110
+ Peak Allocated Bytes 0 B
111
+ Overflow Count 0
112
+ [ALLOC_TEMP_Background Job.Worker 15]
113
+ Initial Block Size 32.0 KB
114
+ Current Block Size 32.0 KB
115
+ Peak Allocated Bytes 0 B
116
+ Overflow Count 0
117
+ [ALLOC_TEMP_Background Job.Worker 1]
118
+ Initial Block Size 32.0 KB
119
+ Current Block Size 32.0 KB
120
+ Peak Allocated Bytes 0 B
121
+ Overflow Count 0
122
+ [ALLOC_TEMP_Background Job.Worker 2]
123
+ Initial Block Size 32.0 KB
124
+ Current Block Size 32.0 KB
125
+ Peak Allocated Bytes 0 B
126
+ Overflow Count 0
127
+ [ALLOC_TEMP_Background Job.Worker 7]
128
+ Initial Block Size 32.0 KB
129
+ Current Block Size 32.0 KB
130
+ Peak Allocated Bytes 0 B
131
+ Overflow Count 0
132
+ [ALLOC_TEMP_AssetGarbageCollectorHelper]
133
+ Initial Block Size 64.0 KB
134
+ Current Block Size 64.0 KB
135
+ Peak Allocated Bytes 0 B
136
+ Overflow Count 0
137
+ [ALLOC_TEMP_Background Job.Worker 5]
138
+ Initial Block Size 32.0 KB
139
+ Current Block Size 32.0 KB
140
+ Peak Allocated Bytes 0 B
141
+ Overflow Count 0
142
+ [ALLOC_TEMP_Background Job.Worker 13]
143
+ Initial Block Size 32.0 KB
144
+ Current Block Size 32.0 KB
145
+ Peak Allocated Bytes 0 B
146
+ Overflow Count 0
147
+ [ALLOC_TEMP_Background Job.Worker 11]
148
+ Initial Block Size 32.0 KB
149
+ Current Block Size 32.0 KB
150
+ Peak Allocated Bytes 0 B
151
+ Overflow Count 0
152
+ [ALLOC_TEMP_Background Job.Worker 3]
153
+ Initial Block Size 32.0 KB
154
+ Current Block Size 32.0 KB
155
+ Peak Allocated Bytes 0 B
156
+ Overflow Count 0
157
+ [ALLOC_TEMP_Background Job.Worker 0]
158
+ Initial Block Size 32.0 KB
159
+ Current Block Size 32.0 KB
160
+ Peak Allocated Bytes 0 B
161
+ Overflow Count 0
162
+ [ALLOC_TEMP_Background Job.Worker 4]
163
+ Initial Block Size 32.0 KB
164
+ Current Block Size 32.0 KB
165
+ Peak Allocated Bytes 0 B
166
+ Overflow Count 0
167
+ [ALLOC_TEMP_BatchDeleteObjects]
168
+ Initial Block Size 64.0 KB
169
+ Current Block Size 64.0 KB
170
+ Peak Allocated Bytes 0 B
171
+ Overflow Count 0
172
+ [ALLOC_DEFAULT] Dual Thread Allocator
173
+ Peak main deferred allocation count 34
174
+ [ALLOC_BUCKET]
175
+ Large Block size 4.0 MB
176
+ Used Block count 1
177
+ Peak Allocated bytes 1.0 MB
178
+ [ALLOC_DEFAULT_MAIN]
179
+ Peak usage frame count: [4.0 MB-8.0 MB]: 322 frames
180
+ Requested Block Size 16.0 MB
181
+ Peak Block count 1
182
+ Peak Allocated memory 5.4 MB
183
+ Peak Large allocation bytes 0 B
184
+ [ALLOC_DEFAULT_THREAD]
185
+ Peak usage frame count: [16.0 MB-32.0 MB]: 322 frames
186
+ Requested Block Size 16.0 MB
187
+ Peak Block count 1
188
+ Peak Allocated memory 17.7 MB
189
+ Peak Large allocation bytes 16.0 MB
190
+ [ALLOC_TEMP_JOB_1_FRAME]
191
+ Initial Block Size 2.0 MB
192
+ Used Block Count 1
193
+ Overflow Count (too large) 0
194
+ Overflow Count (full) 0
195
+ [ALLOC_TEMP_JOB_2_FRAMES]
196
+ Initial Block Size 2.0 MB
197
+ Used Block Count 1
198
+ Overflow Count (too large) 0
199
+ Overflow Count (full) 0
200
+ [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
201
+ Initial Block Size 2.0 MB
202
+ Used Block Count 2
203
+ Overflow Count (too large) 0
204
+ Overflow Count (full) 0
205
+ [ALLOC_TEMP_JOB_ASYNC (Background)]
206
+ Initial Block Size 1.0 MB
207
+ Used Block Count 3
208
+ Overflow Count (too large) 0
209
+ Overflow Count (full) 0
210
+ [ALLOC_GFX] Dual Thread Allocator
211
+ Peak main deferred allocation count 0
212
+ [ALLOC_BUCKET]
213
+ Large Block size 4.0 MB
214
+ Used Block count 1
215
+ Peak Allocated bytes 1.0 MB
216
+ [ALLOC_GFX_MAIN]
217
+ Peak usage frame count: [32.0 KB-64.0 KB]: 276 frames, [64.0 KB-128.0 KB]: 46 frames
218
+ Requested Block Size 16.0 MB
219
+ Peak Block count 1
220
+ Peak Allocated memory 65.6 KB
221
+ Peak Large allocation bytes 0 B
222
+ [ALLOC_GFX_THREAD]
223
+ Peak usage frame count: [32.0 KB-64.0 KB]: 322 frames
224
+ Requested Block Size 16.0 MB
225
+ Peak Block count 1
226
+ Peak Allocated memory 39.6 KB
227
+ Peak Large allocation bytes 0 B
228
+ [ALLOC_CACHEOBJECTS] Dual Thread Allocator
229
+ Peak main deferred allocation count 0
230
+ [ALLOC_BUCKET]
231
+ Large Block size 4.0 MB
232
+ Used Block count 1
233
+ Peak Allocated bytes 1.0 MB
234
+ [ALLOC_CACHEOBJECTS_MAIN]
235
+ Peak usage frame count: [0.5 MB-1.0 MB]: 322 frames
236
+ Requested Block Size 4.0 MB
237
+ Peak Block count 1
238
+ Peak Allocated memory 0.6 MB
239
+ Peak Large allocation bytes 0 B
240
+ [ALLOC_CACHEOBJECTS_THREAD]
241
+ Peak usage frame count: [0.5 MB-1.0 MB]: 321 frames, [2.0 MB-4.0 MB]: 1 frames
242
+ Requested Block Size 4.0 MB
243
+ Peak Block count 1
244
+ Peak Allocated memory 2.2 MB
245
+ Peak Large allocation bytes 0 B
246
+ [ALLOC_TYPETREE] Dual Thread Allocator
247
+ Peak main deferred allocation count 0
248
+ [ALLOC_BUCKET]
249
+ Large Block size 4.0 MB
250
+ Used Block count 1
251
+ Peak Allocated bytes 1.0 MB
252
+ [ALLOC_TYPETREE_MAIN]
253
+ Peak usage frame count: [0-1.0 KB]: 322 frames
254
+ Requested Block Size 2.0 MB
255
+ Peak Block count 1
256
+ Peak Allocated memory 1.0 KB
257
+ Peak Large allocation bytes 0 B
258
+ [ALLOC_TYPETREE_THREAD]
259
+ Peak usage frame count: [1.0 KB-2.0 KB]: 322 frames
260
+ Requested Block Size 2.0 MB
261
+ Peak Block count 1
262
+ Peak Allocated memory 1.7 KB
263
+ Peak Large allocation bytes 0 B
run_logs/timers.json ADDED
@@ -0,0 +1,369 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 2.867946147918701,
6
+ "min": 2.867946147918701,
7
+ "max": 2.867946147918701,
8
+ "count": 1
9
+ },
10
+ "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 29433.732421875,
12
+ "min": 29433.732421875,
13
+ "max": 29433.732421875,
14
+ "count": 1
15
+ },
16
+ "SnowballTarget.Step.mean": {
17
+ "value": 9952.0,
18
+ "min": 9952.0,
19
+ "max": 9952.0,
20
+ "count": 1
21
+ },
22
+ "SnowballTarget.Step.sum": {
23
+ "value": 9952.0,
24
+ "min": 9952.0,
25
+ "max": 9952.0,
26
+ "count": 1
27
+ },
28
+ "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 0.36501964926719666,
30
+ "min": 0.36501964926719666,
31
+ "max": 0.36501964926719666,
32
+ "count": 1
33
+ },
34
+ "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 70.81381225585938,
36
+ "min": 70.81381225585938,
37
+ "max": 70.81381225585938,
38
+ "count": 1
39
+ },
40
+ "SnowballTarget.Environment.EpisodeLength.mean": {
41
+ "value": 199.0,
42
+ "min": 199.0,
43
+ "max": 199.0,
44
+ "count": 1
45
+ },
46
+ "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 8756.0,
48
+ "min": 8756.0,
49
+ "max": 8756.0,
50
+ "count": 1
51
+ },
52
+ "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.06009695729764586,
54
+ "min": 0.06009695729764586,
55
+ "max": 0.06009695729764586,
56
+ "count": 1
57
+ },
58
+ "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.24038782919058344,
60
+ "min": 0.24038782919058344,
61
+ "max": 0.24038782919058344,
62
+ "count": 1
63
+ },
64
+ "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.11938250649209116,
66
+ "min": 0.11938250649209116,
67
+ "max": 0.11938250649209116,
68
+ "count": 1
69
+ },
70
+ "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.47753002596836464,
72
+ "min": 0.47753002596836464,
73
+ "max": 0.47753002596836464,
74
+ "count": 1
75
+ },
76
+ "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 0.000291882002706,
78
+ "min": 0.000291882002706,
79
+ "max": 0.000291882002706,
80
+ "count": 1
81
+ },
82
+ "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 0.001167528010824,
84
+ "min": 0.001167528010824,
85
+ "max": 0.001167528010824,
86
+ "count": 1
87
+ },
88
+ "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.19729400000000002,
90
+ "min": 0.19729400000000002,
91
+ "max": 0.19729400000000002,
92
+ "count": 1
93
+ },
94
+ "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.7891760000000001,
96
+ "min": 0.7891760000000001,
97
+ "max": 0.7891760000000001,
98
+ "count": 1
99
+ },
100
+ "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 0.0048649706,
102
+ "min": 0.0048649706,
103
+ "max": 0.0048649706,
104
+ "count": 1
105
+ },
106
+ "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.0194598824,
108
+ "min": 0.0194598824,
109
+ "max": 0.0194598824,
110
+ "count": 1
111
+ },
112
+ "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 3.6136363636363638,
114
+ "min": 3.6136363636363638,
115
+ "max": 3.6136363636363638,
116
+ "count": 1
117
+ },
118
+ "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 159.0,
120
+ "min": 159.0,
121
+ "max": 159.0,
122
+ "count": 1
123
+ },
124
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 3.6136363636363638,
126
+ "min": 3.6136363636363638,
127
+ "max": 3.6136363636363638,
128
+ "count": 1
129
+ },
130
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 159.0,
132
+ "min": 159.0,
133
+ "max": 159.0,
134
+ "count": 1
135
+ },
136
+ "SnowballTarget.IsTraining.mean": {
137
+ "value": 1.0,
138
+ "min": 1.0,
139
+ "max": 1.0,
140
+ "count": 1
141
+ },
142
+ "SnowballTarget.IsTraining.sum": {
143
+ "value": 1.0,
144
+ "min": 1.0,
145
+ "max": 1.0,
146
+ "count": 1
147
+ }
148
+ },
149
+ "metadata": {
150
+ "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1679087839",
152
+ "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
+ "mlagents_version": "0.31.0.dev0",
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": "1679087877"
160
+ },
161
+ "total": 37.19952396700006,
162
+ "count": 1,
163
+ "self": 0.18337441200009152,
164
+ "children": {
165
+ "run_training.setup": {
166
+ "total": 0.10661946999999827,
167
+ "count": 1,
168
+ "self": 0.10661946999999827
169
+ },
170
+ "TrainerController.start_learning": {
171
+ "total": 36.90953008499997,
172
+ "count": 1,
173
+ "self": 0.14344037400132947,
174
+ "children": {
175
+ "TrainerController._reset_env": {
176
+ "total": 10.20520952999999,
177
+ "count": 1,
178
+ "self": 10.20520952999999
179
+ },
180
+ "TrainerController.advance": {
181
+ "total": 26.113130139998702,
182
+ "count": 1073,
183
+ "self": 0.015438158999131701,
184
+ "children": {
185
+ "env_step": {
186
+ "total": 26.09769198099957,
187
+ "count": 1073,
188
+ "self": 19.096851784999217,
189
+ "children": {
190
+ "SubprocessEnvManager._take_step": {
191
+ "total": 6.985853050999594,
192
+ "count": 1073,
193
+ "self": 0.20996643500183154,
194
+ "children": {
195
+ "TorchPolicy.evaluate": {
196
+ "total": 6.775886615997763,
197
+ "count": 1073,
198
+ "self": 6.775886615997763
199
+ }
200
+ }
201
+ },
202
+ "workers": {
203
+ "total": 0.014987145000759483,
204
+ "count": 1072,
205
+ "self": 0.0,
206
+ "children": {
207
+ "worker_root": {
208
+ "total": 36.362026185999696,
209
+ "count": 1072,
210
+ "is_parallel": true,
211
+ "self": 22.53656574799936,
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": 0.00622794100002011,
221
+ "count": 1,
222
+ "is_parallel": true,
223
+ "self": 0.0047879080000825525,
224
+ "children": {
225
+ "_process_rank_one_or_two_observation": {
226
+ "total": 0.0014400329999375572,
227
+ "count": 10,
228
+ "is_parallel": true,
229
+ "self": 0.0014400329999375572
230
+ }
231
+ }
232
+ },
233
+ "UnityEnvironment.step": {
234
+ "total": 0.04782305899999528,
235
+ "count": 1,
236
+ "is_parallel": true,
237
+ "self": 0.0006204030000276362,
238
+ "children": {
239
+ "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00027903400001605405,
241
+ "count": 1,
242
+ "is_parallel": true,
243
+ "self": 0.00027903400001605405
244
+ },
245
+ "communicator.exchange": {
246
+ "total": 0.04514546299998301,
247
+ "count": 1,
248
+ "is_parallel": true,
249
+ "self": 0.04514546299998301
250
+ },
251
+ "steps_from_proto": {
252
+ "total": 0.001778158999968582,
253
+ "count": 1,
254
+ "is_parallel": true,
255
+ "self": 0.0003690989998972327,
256
+ "children": {
257
+ "_process_rank_one_or_two_observation": {
258
+ "total": 0.0014090600000713494,
259
+ "count": 10,
260
+ "is_parallel": true,
261
+ "self": 0.0014090600000713494
262
+ }
263
+ }
264
+ }
265
+ }
266
+ }
267
+ }
268
+ },
269
+ "UnityEnvironment.step": {
270
+ "total": 13.825460438000334,
271
+ "count": 1071,
272
+ "is_parallel": true,
273
+ "self": 0.5667811729985033,
274
+ "children": {
275
+ "UnityEnvironment._generate_step_input": {
276
+ "total": 0.30566426999985197,
277
+ "count": 1071,
278
+ "is_parallel": true,
279
+ "self": 0.30566426999985197
280
+ },
281
+ "communicator.exchange": {
282
+ "total": 11.150007539001876,
283
+ "count": 1071,
284
+ "is_parallel": true,
285
+ "self": 11.150007539001876
286
+ },
287
+ "steps_from_proto": {
288
+ "total": 1.8030074560001026,
289
+ "count": 1071,
290
+ "is_parallel": true,
291
+ "self": 0.3532421949989839,
292
+ "children": {
293
+ "_process_rank_one_or_two_observation": {
294
+ "total": 1.4497652610011187,
295
+ "count": 10710,
296
+ "is_parallel": true,
297
+ "self": 1.4497652610011187
298
+ }
299
+ }
300
+ }
301
+ }
302
+ }
303
+ }
304
+ }
305
+ }
306
+ }
307
+ }
308
+ }
309
+ }
310
+ },
311
+ "trainer_threads": {
312
+ "total": 0.00011445600000570266,
313
+ "count": 1,
314
+ "self": 0.00011445600000570266,
315
+ "children": {
316
+ "thread_root": {
317
+ "total": 0.0,
318
+ "count": 0,
319
+ "is_parallel": true,
320
+ "self": 0.0,
321
+ "children": {
322
+ "trainer_advance": {
323
+ "total": 26.023509298995577,
324
+ "count": 22192,
325
+ "is_parallel": true,
326
+ "self": 0.5657549129856534,
327
+ "children": {
328
+ "process_trajectory": {
329
+ "total": 14.718005123009846,
330
+ "count": 22192,
331
+ "is_parallel": true,
332
+ "self": 14.718005123009846
333
+ },
334
+ "_update_policy": {
335
+ "total": 10.739749263000078,
336
+ "count": 5,
337
+ "is_parallel": true,
338
+ "self": 3.8587524820004546,
339
+ "children": {
340
+ "TorchPPOOptimizer.update": {
341
+ "total": 6.880996780999624,
342
+ "count": 252,
343
+ "is_parallel": true,
344
+ "self": 6.880996780999624
345
+ }
346
+ }
347
+ }
348
+ }
349
+ }
350
+ }
351
+ }
352
+ }
353
+ },
354
+ "TrainerController._save_models": {
355
+ "total": 0.4476355849999436,
356
+ "count": 1,
357
+ "self": 0.001131046999944374,
358
+ "children": {
359
+ "RLTrainer._checkpoint": {
360
+ "total": 0.44650453799999923,
361
+ "count": 1,
362
+ "self": 0.44650453799999923
363
+ }
364
+ }
365
+ }
366
+ }
367
+ }
368
+ }
369
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "SnowballTarget": {
3
+ "checkpoints": [
4
+ {
5
+ "steps": 11576,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-11576.onnx",
7
+ "reward": 5.2727272727272725,
8
+ "creation_time": 1679087876.8157299,
9
+ "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-11576.pt"
11
+ ]
12
+ }
13
+ ],
14
+ "final_checkpoint": {
15
+ "steps": 11576,
16
+ "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
17
+ "reward": 5.2727272727272725,
18
+ "creation_time": 1679087876.8157299,
19
+ "auxillary_file_paths": [
20
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-11576.pt"
21
+ ]
22
+ }
23
+ },
24
+ "metadata": {
25
+ "stats_format_version": "0.3.0",
26
+ "mlagents_version": "0.31.0.dev0",
27
+ "torch_version": "1.11.0+cu102"
28
+ }
29
+ }