AlidarAsvarov commited on
Commit
9db6862
1 Parent(s): a4a0d64

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: AlidarAsvarov/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:cb905f8f8d0607fffe81b88cb0389e92dde981774d512a5fbd8fa44acacfdc87
3
+ size 645119
SnowballTarget/SnowballTarget-149984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a615f2c8564d19b2219e71cbd786e969569caa71abcff0d983d4b00b9e44a328
3
+ size 645119
SnowballTarget/SnowballTarget-149984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a96f0f0b2ca2f72ad889707a740b89b8149f6fc4dde2169c07b9a9ccfc54215
3
+ size 3845585
SnowballTarget/SnowballTarget-199984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb905f8f8d0607fffe81b88cb0389e92dde981774d512a5fbd8fa44acacfdc87
3
+ size 645119
SnowballTarget/SnowballTarget-199984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3c487199a517d75a64d64985c7df8c7a705bbf2f27ed3c7854672a65203dd20
3
+ size 3845585
SnowballTarget/SnowballTarget-200112.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb905f8f8d0607fffe81b88cb0389e92dde981774d512a5fbd8fa44acacfdc87
3
+ size 645119
SnowballTarget/SnowballTarget-200112.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:286971c6573c94e5a115d799d002224a326d0f81f13f23717951858258c24da4
3
+ size 3845585
SnowballTarget/SnowballTarget-49936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:354ef34474d8b993e27ee48e298604c2c2c4396c389824fb3b3d7ae0b9236020
3
+ size 645119
SnowballTarget/SnowballTarget-49936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99e294edff8f4cf6c85c4bd8fd7ff4b060efda1d4e87bfebb1f011b2ba58746d
3
+ size 3845585
SnowballTarget/SnowballTarget-99960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:634d851515cb9e7676d21c964185f973f42455ac1355385ad5b6717f20c3c518
3
+ size 645119
SnowballTarget/SnowballTarget-99960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1276ee515f95239e24f7de1febd61ca7884670212d448229be6c2b2d3e47a52c
3
+ size 3845585
SnowballTarget/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:286971c6573c94e5a115d799d002224a326d0f81f13f23717951858258c24da4
3
+ size 3845585
SnowballTarget/events.out.tfevents.1712869301.asvarov-mlressrv-0-0.7162.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab3ef623044d56899f19e4ee7f61bcd12cc264e834316eb1b659c7aab3f06ef9
3
+ size 19068
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, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 50000, "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": "SnowballTarget3", "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 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ learning_rate_schedule: linear
14
+ beta_schedule: linear
15
+ epsilon_schedule: linear
16
+ network_settings:
17
+ normalize: false
18
+ hidden_units: 256
19
+ num_layers: 2
20
+ vis_encode_type: simple
21
+ memory: null
22
+ goal_conditioning_type: hyper
23
+ deterministic: false
24
+ reward_signals:
25
+ extrinsic:
26
+ gamma: 0.99
27
+ strength: 1.0
28
+ network_settings:
29
+ normalize: false
30
+ hidden_units: 128
31
+ num_layers: 2
32
+ vis_encode_type: simple
33
+ memory: null
34
+ goal_conditioning_type: hyper
35
+ deterministic: false
36
+ init_path: null
37
+ keep_checkpoints: 10
38
+ checkpoint_interval: 50000
39
+ max_steps: 200000
40
+ time_horizon: 64
41
+ summary_freq: 10000
42
+ threaded: true
43
+ self_play: null
44
+ behavioral_cloning: null
45
+ env_settings:
46
+ env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
47
+ env_args: null
48
+ base_port: 5005
49
+ num_envs: 1
50
+ num_areas: 1
51
+ seed: -1
52
+ max_lifetime_restarts: 10
53
+ restarts_rate_limit_n: 1
54
+ restarts_rate_limit_period_s: 60
55
+ engine_settings:
56
+ width: 84
57
+ height: 84
58
+ quality_level: 5
59
+ time_scale: 20
60
+ target_frame_rate: -1
61
+ capture_frame_rate: 60
62
+ no_graphics: true
63
+ environment_parameters: null
64
+ checkpoint_settings:
65
+ run_id: SnowballTarget3
66
+ initialize_from: null
67
+ load_model: false
68
+ resume: false
69
+ force: false
70
+ train_model: false
71
+ inference: false
72
+ results_dir: results
73
+ torch_settings:
74
+ device: null
75
+ debug: false
run_logs/Player-0.log ADDED
@@ -0,0 +1,272 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Mono path[0] = '/workspace/local/asvarov/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
2
+ Mono config path = '/workspace/local/asvarov/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 /workspace/local/asvarov/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 0.076 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: 0.527483 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 2 worker threads for Enlighten.
52
+ 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]: 5371 frames, [16.0 KB-32.0 KB]: 91 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
60
+ Overflow Count 0
61
+ [ALLOC_TEMP_Loading.AsyncRead]
62
+ Initial Block Size 64.0 KB
63
+ Current Block Size 64.0 KB
64
+ Peak Allocated Bytes 230 B
65
+ Overflow Count 0
66
+ [ALLOC_TEMP_Loading.PreloadManager]
67
+ Initial Block Size 256.0 KB
68
+ Current Block Size 304.0 KB
69
+ Peak Allocated Bytes 228.9 KB
70
+ Overflow Count 4
71
+ [ALLOC_TEMP_Background Job.Worker 8]
72
+ Initial Block Size 32.0 KB
73
+ Current Block Size 32.0 KB
74
+ Peak Allocated Bytes 0 B
75
+ Overflow Count 0
76
+ [ALLOC_TEMP_Background Job.Worker 9]
77
+ Initial Block Size 32.0 KB
78
+ Current Block Size 32.0 KB
79
+ Peak Allocated Bytes 0 B
80
+ Overflow Count 0
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
88
+ Current Block Size 32.0 KB
89
+ Peak Allocated Bytes 0 B
90
+ Overflow Count 0
91
+ [ALLOC_TEMP_Background Job.Worker 14]
92
+ Initial Block Size 32.0 KB
93
+ Current Block Size 32.0 KB
94
+ Peak Allocated Bytes 0 B
95
+ Overflow Count 0
96
+ [ALLOC_TEMP_Background Job.Worker 6]
97
+ Initial Block Size 32.0 KB
98
+ Current Block Size 32.0 KB
99
+ Peak Allocated Bytes 0 B
100
+ Overflow Count 0
101
+ [ALLOC_TEMP_Background Job.Worker 12]
102
+ Initial Block Size 32.0 KB
103
+ Current Block Size 32.0 KB
104
+ Peak Allocated Bytes 0 B
105
+ Overflow Count 0
106
+ [ALLOC_TEMP_EnlightenWorker] x 2
107
+ Initial Block Size 64.0 KB
108
+ Current Block Size 64.0 KB
109
+ Peak Allocated Bytes 0 B
110
+ Overflow Count 0
111
+ [ALLOC_TEMP_Background Job.Worker 15]
112
+ Initial Block Size 32.0 KB
113
+ Current Block Size 32.0 KB
114
+ Peak Allocated Bytes 0 B
115
+ Overflow Count 0
116
+ [ALLOC_TEMP_Background Job.Worker 1]
117
+ Initial Block Size 32.0 KB
118
+ Current Block Size 32.0 KB
119
+ Peak Allocated Bytes 0 B
120
+ Overflow Count 0
121
+ [ALLOC_TEMP_Background Job.Worker 2]
122
+ Initial Block Size 32.0 KB
123
+ Current Block Size 32.0 KB
124
+ Peak Allocated Bytes 0 B
125
+ Overflow Count 0
126
+ [ALLOC_TEMP_Background Job.Worker 7]
127
+ Initial Block Size 32.0 KB
128
+ Current Block Size 32.0 KB
129
+ Peak Allocated Bytes 0 B
130
+ Overflow Count 0
131
+ [ALLOC_TEMP_AssetGarbageCollectorHelper] x 3
132
+ Initial Block Size 64.0 KB
133
+ Current Block Size 64.0 KB
134
+ Peak Allocated Bytes 0 B
135
+ Overflow Count 0
136
+ [ALLOC_TEMP_Background Job.Worker 5]
137
+ Initial Block Size 32.0 KB
138
+ Current Block Size 32.0 KB
139
+ Peak Allocated Bytes 0 B
140
+ Overflow Count 0
141
+ [ALLOC_TEMP_Background Job.Worker 13]
142
+ Initial Block Size 32.0 KB
143
+ Current Block Size 32.0 KB
144
+ Peak Allocated Bytes 0 B
145
+ Overflow Count 0
146
+ [ALLOC_TEMP_Job.Worker 1]
147
+ Initial Block Size 256.0 KB
148
+ Current Block Size 256.0 KB
149
+ Peak Allocated Bytes 3.6 KB
150
+ Overflow Count 0
151
+ [ALLOC_TEMP_Job.Worker 2]
152
+ Initial Block Size 256.0 KB
153
+ Current Block Size 256.0 KB
154
+ Peak Allocated Bytes 3.6 KB
155
+ Overflow Count 0
156
+ [ALLOC_TEMP_Background Job.Worker 3]
157
+ Initial Block Size 32.0 KB
158
+ Current Block Size 32.0 KB
159
+ Peak Allocated Bytes 0 B
160
+ Overflow Count 0
161
+ [ALLOC_TEMP_Background Job.Worker 11]
162
+ Initial Block Size 32.0 KB
163
+ Current Block Size 32.0 KB
164
+ Peak Allocated Bytes 0 B
165
+ Overflow Count 0
166
+ [ALLOC_TEMP_Background Job.Worker 0]
167
+ Initial Block Size 32.0 KB
168
+ Current Block Size 32.0 KB
169
+ Peak Allocated Bytes 0 B
170
+ Overflow Count 0
171
+ [ALLOC_TEMP_Background Job.Worker 4]
172
+ Initial Block Size 32.0 KB
173
+ Current Block Size 32.0 KB
174
+ Peak Allocated Bytes 0 B
175
+ Overflow Count 0
176
+ [ALLOC_TEMP_BatchDeleteObjects]
177
+ Initial Block Size 64.0 KB
178
+ Current Block Size 64.0 KB
179
+ Peak Allocated Bytes 0 B
180
+ Overflow Count 0
181
+ [ALLOC_DEFAULT] Dual Thread Allocator
182
+ Peak main deferred allocation count 44
183
+ [ALLOC_BUCKET]
184
+ Large Block size 4.0 MB
185
+ Used Block count 1
186
+ Peak Allocated bytes 1.0 MB
187
+ [ALLOC_DEFAULT_MAIN]
188
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5463 frames
189
+ Requested Block Size 16.0 MB
190
+ Peak Block count 1
191
+ Peak Allocated memory 22.7 MB
192
+ Peak Large allocation bytes 16.0 MB
193
+ [ALLOC_DEFAULT_THREAD]
194
+ Peak usage frame count: [1.0 MB-2.0 MB]: 5463 frames
195
+ Requested Block Size 16.0 MB
196
+ Peak Block count 1
197
+ Peak Allocated memory 1.7 MB
198
+ Peak Large allocation bytes 0 B
199
+ [ALLOC_TEMP_JOB_1_FRAME]
200
+ Initial Block Size 2.0 MB
201
+ Used Block Count 1
202
+ Overflow Count (too large) 0
203
+ Overflow Count (full) 0
204
+ [ALLOC_TEMP_JOB_2_FRAMES]
205
+ Initial Block Size 2.0 MB
206
+ Used Block Count 1
207
+ Overflow Count (too large) 0
208
+ Overflow Count (full) 0
209
+ [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
210
+ Initial Block Size 2.0 MB
211
+ Used Block Count 2
212
+ Overflow Count (too large) 0
213
+ Overflow Count (full) 0
214
+ [ALLOC_TEMP_JOB_ASYNC (Background)]
215
+ Initial Block Size 1.0 MB
216
+ Used Block Count 3
217
+ Overflow Count (too large) 0
218
+ Overflow Count (full) 0
219
+ [ALLOC_GFX] Dual Thread Allocator
220
+ Peak main deferred allocation count 0
221
+ [ALLOC_BUCKET]
222
+ Large Block size 4.0 MB
223
+ Used Block count 1
224
+ Peak Allocated bytes 1.0 MB
225
+ [ALLOC_GFX_MAIN]
226
+ Peak usage frame count: [32.0 KB-64.0 KB]: 4666 frames, [64.0 KB-128.0 KB]: 797 frames
227
+ Requested Block Size 16.0 MB
228
+ Peak Block count 1
229
+ Peak Allocated memory 67.2 KB
230
+ Peak Large allocation bytes 0 B
231
+ [ALLOC_GFX_THREAD]
232
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5463 frames
233
+ Requested Block Size 16.0 MB
234
+ Peak Block count 1
235
+ Peak Allocated memory 39.6 KB
236
+ Peak Large allocation bytes 0 B
237
+ [ALLOC_CACHEOBJECTS] Dual Thread Allocator
238
+ Peak main deferred allocation count 0
239
+ [ALLOC_BUCKET]
240
+ Large Block size 4.0 MB
241
+ Used Block count 1
242
+ Peak Allocated bytes 1.0 MB
243
+ [ALLOC_CACHEOBJECTS_MAIN]
244
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5463 frames
245
+ Requested Block Size 4.0 MB
246
+ Peak Block count 1
247
+ Peak Allocated memory 0.6 MB
248
+ Peak Large allocation bytes 0 B
249
+ [ALLOC_CACHEOBJECTS_THREAD]
250
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5462 frames, [2.0 MB-4.0 MB]: 1 frames
251
+ Requested Block Size 4.0 MB
252
+ Peak Block count 1
253
+ Peak Allocated memory 2.2 MB
254
+ Peak Large allocation bytes 0 B
255
+ [ALLOC_TYPETREE] Dual Thread Allocator
256
+ Peak main deferred allocation count 0
257
+ [ALLOC_BUCKET]
258
+ Large Block size 4.0 MB
259
+ Used Block count 1
260
+ Peak Allocated bytes 1.0 MB
261
+ [ALLOC_TYPETREE_MAIN]
262
+ Peak usage frame count: [0-1.0 KB]: 5463 frames
263
+ Requested Block Size 2.0 MB
264
+ Peak Block count 1
265
+ Peak Allocated memory 1.0 KB
266
+ Peak Large allocation bytes 0 B
267
+ [ALLOC_TYPETREE_THREAD]
268
+ Peak usage frame count: [1.0 KB-2.0 KB]: 5463 frames
269
+ Requested Block Size 2.0 MB
270
+ Peak Block count 1
271
+ Peak Allocated memory 1.7 KB
272
+ Peak Large allocation bytes 0 B
run_logs/timers.json ADDED
@@ -0,0 +1,384 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.9406658411026001,
6
+ "min": 0.9406658411026001,
7
+ "max": 2.859431266784668,
8
+ "count": 20
9
+ },
10
+ "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 9012.51953125,
12
+ "min": 9012.51953125,
13
+ "max": 29283.435546875,
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": 12.866596221923828,
30
+ "min": 0.5913612842559814,
31
+ "max": 12.866596221923828,
32
+ "count": 20
33
+ },
34
+ "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2508.986328125,
36
+ "min": 114.72409057617188,
37
+ "max": 2604.447509765625,
38
+ "count": 20
39
+ },
40
+ "SnowballTarget.Environment.EpisodeLength.mean": {
41
+ "value": 199.0,
42
+ "min": 199.0,
43
+ "max": 199.0,
44
+ "count": 20
45
+ },
46
+ "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 10945.0,
48
+ "min": 8756.0,
49
+ "max": 10945.0,
50
+ "count": 20
51
+ },
52
+ "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.06769860126608845,
54
+ "min": 0.06323129016285142,
55
+ "max": 0.07477617251832842,
56
+ "count": 20
57
+ },
58
+ "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.2707944050643538,
60
+ "min": 0.26373670181469516,
61
+ "max": 0.3738808625916421,
62
+ "count": 20
63
+ },
64
+ "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.19753696944783716,
66
+ "min": 0.13871130599485088,
67
+ "max": 0.2825576875139685,
68
+ "count": 20
69
+ },
70
+ "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.7901478777913487,
72
+ "min": 0.5548452239794035,
73
+ "max": 1.4127884375698425,
74
+ "count": 20
75
+ },
76
+ "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 8.082097306000005e-06,
78
+ "min": 8.082097306000005e-06,
79
+ "max": 0.000291882002706,
80
+ "count": 20
81
+ },
82
+ "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 3.232838922400002e-05,
84
+ "min": 3.232838922400002e-05,
85
+ "max": 0.00138516003828,
86
+ "count": 20
87
+ },
88
+ "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10269400000000001,
90
+ "min": 0.10269400000000001,
91
+ "max": 0.19729400000000002,
92
+ "count": 20
93
+ },
94
+ "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.41077600000000003,
96
+ "min": 0.41077600000000003,
97
+ "max": 0.96172,
98
+ "count": 20
99
+ },
100
+ "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 0.0001444306000000001,
102
+ "min": 0.0001444306000000001,
103
+ "max": 0.0048649706,
104
+ "count": 20
105
+ },
106
+ "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.0005777224000000004,
108
+ "min": 0.0005777224000000004,
109
+ "max": 0.023089828,
110
+ "count": 20
111
+ },
112
+ "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 25.272727272727273,
114
+ "min": 4.045454545454546,
115
+ "max": 25.618181818181817,
116
+ "count": 20
117
+ },
118
+ "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1112.0,
120
+ "min": 178.0,
121
+ "max": 1409.0,
122
+ "count": 20
123
+ },
124
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.272727272727273,
126
+ "min": 4.045454545454546,
127
+ "max": 25.618181818181817,
128
+ "count": 20
129
+ },
130
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1112.0,
132
+ "min": 178.0,
133
+ "max": 1409.0,
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": "1712869301",
152
+ "python_version": "3.8.10 (default, May 26 2023, 14:05:08) \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=SnowballTarget3 --no-graphics",
154
+ "mlagents_version": "0.29.0",
155
+ "mlagents_envs_version": "0.29.0",
156
+ "communication_protocol_version": "1.5.0",
157
+ "pytorch_version": "1.8.1+cu102",
158
+ "numpy_version": "1.23.4",
159
+ "end_time_seconds": "1712869632"
160
+ },
161
+ "total": 331.27188908308744,
162
+ "count": 1,
163
+ "self": 0.29966432601213455,
164
+ "children": {
165
+ "run_training.setup": {
166
+ "total": 0.026694340049289167,
167
+ "count": 1,
168
+ "self": 0.026694340049289167
169
+ },
170
+ "TrainerController.start_learning": {
171
+ "total": 330.945530417026,
172
+ "count": 1,
173
+ "self": 0.5151903696823865,
174
+ "children": {
175
+ "TrainerController._reset_env": {
176
+ "total": 3.76351429708302,
177
+ "count": 1,
178
+ "self": 3.76351429708302
179
+ },
180
+ "TrainerController.advance": {
181
+ "total": 326.5645244952757,
182
+ "count": 18207,
183
+ "self": 0.21954471815843135,
184
+ "children": {
185
+ "env_step": {
186
+ "total": 326.34497977711726,
187
+ "count": 18207,
188
+ "self": 218.17430781724397,
189
+ "children": {
190
+ "SubprocessEnvManager._take_step": {
191
+ "total": 107.95539848553017,
192
+ "count": 18207,
193
+ "self": 1.35900153813418,
194
+ "children": {
195
+ "TorchPolicy.evaluate": {
196
+ "total": 106.59639694739599,
197
+ "count": 18207,
198
+ "self": 31.65436023916118,
199
+ "children": {
200
+ "TorchPolicy.sample_actions": {
201
+ "total": 74.94203670823481,
202
+ "count": 18207,
203
+ "self": 74.94203670823481
204
+ }
205
+ }
206
+ }
207
+ }
208
+ },
209
+ "workers": {
210
+ "total": 0.21527347434312105,
211
+ "count": 18207,
212
+ "self": 0.0,
213
+ "children": {
214
+ "worker_root": {
215
+ "total": 330.19921584345866,
216
+ "count": 18207,
217
+ "is_parallel": true,
218
+ "self": 165.4418396137189,
219
+ "children": {
220
+ "run_training.setup": {
221
+ "total": 0.0,
222
+ "count": 0,
223
+ "is_parallel": true,
224
+ "self": 0.0,
225
+ "children": {
226
+ "steps_from_proto": {
227
+ "total": 0.00151283189188689,
228
+ "count": 1,
229
+ "is_parallel": true,
230
+ "self": 0.00046470598317682743,
231
+ "children": {
232
+ "_process_rank_one_or_two_observation": {
233
+ "total": 0.0010481259087100625,
234
+ "count": 10,
235
+ "is_parallel": true,
236
+ "self": 0.0010481259087100625
237
+ }
238
+ }
239
+ },
240
+ "UnityEnvironment.step": {
241
+ "total": 0.019593009958043694,
242
+ "count": 1,
243
+ "is_parallel": true,
244
+ "self": 0.0004387520020827651,
245
+ "children": {
246
+ "UnityEnvironment._generate_step_input": {
247
+ "total": 0.0002079169498756528,
248
+ "count": 1,
249
+ "is_parallel": true,
250
+ "self": 0.0002079169498756528
251
+ },
252
+ "communicator.exchange": {
253
+ "total": 0.018043130985461175,
254
+ "count": 1,
255
+ "is_parallel": true,
256
+ "self": 0.018043130985461175
257
+ },
258
+ "steps_from_proto": {
259
+ "total": 0.0009032100206241012,
260
+ "count": 1,
261
+ "is_parallel": true,
262
+ "self": 0.0002308730036020279,
263
+ "children": {
264
+ "_process_rank_one_or_two_observation": {
265
+ "total": 0.0006723370170220733,
266
+ "count": 10,
267
+ "is_parallel": true,
268
+ "self": 0.0006723370170220733
269
+ }
270
+ }
271
+ }
272
+ }
273
+ }
274
+ }
275
+ },
276
+ "UnityEnvironment.step": {
277
+ "total": 164.75737622973975,
278
+ "count": 18206,
279
+ "is_parallel": true,
280
+ "self": 5.954938965383917,
281
+ "children": {
282
+ "UnityEnvironment._generate_step_input": {
283
+ "total": 3.411784290568903,
284
+ "count": 18206,
285
+ "is_parallel": true,
286
+ "self": 3.411784290568903
287
+ },
288
+ "communicator.exchange": {
289
+ "total": 137.49556931504048,
290
+ "count": 18206,
291
+ "is_parallel": true,
292
+ "self": 137.49556931504048
293
+ },
294
+ "steps_from_proto": {
295
+ "total": 17.895083658746444,
296
+ "count": 18206,
297
+ "is_parallel": true,
298
+ "self": 4.384609971195459,
299
+ "children": {
300
+ "_process_rank_one_or_two_observation": {
301
+ "total": 13.510473687550984,
302
+ "count": 182060,
303
+ "is_parallel": true,
304
+ "self": 13.510473687550984
305
+ }
306
+ }
307
+ }
308
+ }
309
+ }
310
+ }
311
+ }
312
+ }
313
+ }
314
+ }
315
+ }
316
+ }
317
+ },
318
+ "trainer_threads": {
319
+ "total": 0.0001134839840233326,
320
+ "count": 1,
321
+ "self": 0.0001134839840233326,
322
+ "children": {
323
+ "thread_root": {
324
+ "total": 0.0,
325
+ "count": 0,
326
+ "is_parallel": true,
327
+ "self": 0.0,
328
+ "children": {
329
+ "trainer_advance": {
330
+ "total": 324.949653036776,
331
+ "count": 327692,
332
+ "is_parallel": true,
333
+ "self": 5.13197529874742,
334
+ "children": {
335
+ "process_trajectory": {
336
+ "total": 188.13790602760855,
337
+ "count": 327692,
338
+ "is_parallel": true,
339
+ "self": 187.52248082845472,
340
+ "children": {
341
+ "RLTrainer._checkpoint": {
342
+ "total": 0.6154251991538331,
343
+ "count": 4,
344
+ "is_parallel": true,
345
+ "self": 0.6154251991538331
346
+ }
347
+ }
348
+ },
349
+ "_update_policy": {
350
+ "total": 131.67977171042003,
351
+ "count": 90,
352
+ "is_parallel": true,
353
+ "self": 31.667786150355823,
354
+ "children": {
355
+ "TorchPPOOptimizer.update": {
356
+ "total": 100.0119855600642,
357
+ "count": 4587,
358
+ "is_parallel": true,
359
+ "self": 100.0119855600642
360
+ }
361
+ }
362
+ }
363
+ }
364
+ }
365
+ }
366
+ }
367
+ }
368
+ },
369
+ "TrainerController._save_models": {
370
+ "total": 0.10218777100089937,
371
+ "count": 1,
372
+ "self": 0.00062893598806113,
373
+ "children": {
374
+ "RLTrainer._checkpoint": {
375
+ "total": 0.10155883501283824,
376
+ "count": 1,
377
+ "self": 0.10155883501283824
378
+ }
379
+ }
380
+ }
381
+ }
382
+ }
383
+ }
384
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "SnowballTarget": {
3
+ "checkpoints": [
4
+ {
5
+ "steps": 49936,
6
+ "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 14.727272727272727,
8
+ "creation_time": 1712869387.6514652,
9
+ "auxillary_file_paths": [
10
+ "results/SnowballTarget3/SnowballTarget/SnowballTarget-49936.pt"
11
+ ]
12
+ },
13
+ {
14
+ "steps": 99960,
15
+ "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-99960.onnx",
16
+ "reward": 21.636363636363637,
17
+ "creation_time": 1712869468.8345532,
18
+ "auxillary_file_paths": [
19
+ "results/SnowballTarget3/SnowballTarget/SnowballTarget-99960.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 149984,
24
+ "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 25.545454545454547,
26
+ "creation_time": 1712869550.7825892,
27
+ "auxillary_file_paths": [
28
+ "results/SnowballTarget3/SnowballTarget/SnowballTarget-149984.pt"
29
+ ]
30
+ },
31
+ {
32
+ "steps": 199984,
33
+ "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 25.545454545454547,
35
+ "creation_time": 1712869631.91264,
36
+ "auxillary_file_paths": [
37
+ "results/SnowballTarget3/SnowballTarget/SnowballTarget-199984.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 200112,
42
+ "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-200112.onnx",
43
+ "reward": 25.545454545454547,
44
+ "creation_time": 1712869632.0354657,
45
+ "auxillary_file_paths": [
46
+ "results/SnowballTarget3/SnowballTarget/SnowballTarget-200112.pt"
47
+ ]
48
+ }
49
+ ],
50
+ "final_checkpoint": {
51
+ "steps": 200112,
52
+ "file_path": "results/SnowballTarget3/SnowballTarget.onnx",
53
+ "reward": 25.545454545454547,
54
+ "creation_time": 1712869632.0354657,
55
+ "auxillary_file_paths": [
56
+ "results/SnowballTarget3/SnowballTarget/SnowballTarget-200112.pt"
57
+ ]
58
+ }
59
+ },
60
+ "metadata": {
61
+ "stats_format_version": "0.3.0",
62
+ "mlagents_version": "0.29.0",
63
+ "torch_version": "1.8.1+cu102"
64
+ }
65
+ }