rishisim commited on
Commit
a71a5ef
1 Parent(s): cfd0ce2

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: rishisim/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 sha256:076163f50c98c3038663085568996f7220bdf59729de8a126fc80150c9495e03
3
+ size 650646
SnowballTarget/SnowballTarget-149984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c5b7c9937fe117a5187668c47404f1a36748638bc34f12c524168c11609b5a7
3
+ size 650646
SnowballTarget/SnowballTarget-149984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e76f501f07ab5f9da915fd91ba3aa094874319e60125483f79b9f1981eb1713e
3
+ size 3850075
SnowballTarget/SnowballTarget-199984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:076163f50c98c3038663085568996f7220bdf59729de8a126fc80150c9495e03
3
+ size 650646
SnowballTarget/SnowballTarget-199984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9b90fdea63ae23dadbee2f826165b472a249177fb5a521fefbc99f968efa173
3
+ size 3850075
SnowballTarget/SnowballTarget-200112.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:076163f50c98c3038663085568996f7220bdf59729de8a126fc80150c9495e03
3
+ size 650646
SnowballTarget/SnowballTarget-200112.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60bac5458dfd2b14b003cf18ee0a298412c3e6c2eb3e2b7bd7fe70b593641bf5
3
+ size 3850075
SnowballTarget/SnowballTarget-49936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad1d2e63ff703ebd6412c80c2f931ea8423173792f679bf35488cf69fc094dab
3
+ size 650646
SnowballTarget/SnowballTarget-49936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:837f65e5875feda4754ad0b1573b6c6887ae9b7a48452d4b2b025d2daa7617aa
3
+ size 3850000
SnowballTarget/SnowballTarget-99960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a34aa1fba7ea7ac90d4ea599072c495273860c9bf47390798e37114f673689c7
3
+ size 650646
SnowballTarget/SnowballTarget-99960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70b26bf3b676993c9741e1bcc3c9a2d6385ad4de9f70f383d3412268a27f5eaa
3
+ size 3850000
SnowballTarget/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a740577dc525a5acc9465bd7acee20512b77b23a9602679c5e2acfec13beb569
3
+ size 3849250
SnowballTarget/events.out.tfevents.1719684380.2ccb8b7361da.2576.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af39272468c5f58a27696ff6b0c1214a4b4ede38cd6b272830c7f2166e225b39
3
+ size 23768
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, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ 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: false
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 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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:855:(parse_card) cannot find card '0'
17
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
18
+ ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
19
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
20
+ ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
21
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
22
+ ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
23
+ ALSA lib pcm.c:2664:(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:855:(parse_card) cannot find card '0'
27
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
28
+ ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
29
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
30
+ ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
31
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
32
+ ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
33
+ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
+ FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
+ FMOD initialized on nosound output
36
+ Begin MonoManager ReloadAssembly
37
+ - Completed reload, in 0.088 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: 0.669634 ms
49
+ ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
50
+ requesting resize 84 x 84
51
+ Setting up 1 worker threads for Enlighten.
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]: 5369 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 198 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]
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]
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_Background Job.Worker 11]
147
+ Initial Block Size 32.0 KB
148
+ Current Block Size 32.0 KB
149
+ Peak Allocated Bytes 0 B
150
+ Overflow Count 0
151
+ [ALLOC_TEMP_Background Job.Worker 3]
152
+ Initial Block Size 32.0 KB
153
+ Current Block Size 32.0 KB
154
+ Peak Allocated Bytes 0 B
155
+ Overflow Count 0
156
+ [ALLOC_TEMP_Background Job.Worker 0]
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 4]
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_BatchDeleteObjects]
167
+ Initial Block Size 64.0 KB
168
+ Current Block Size 64.0 KB
169
+ Peak Allocated Bytes 0 B
170
+ Overflow Count 0
171
+ [ALLOC_DEFAULT] Dual Thread Allocator
172
+ Peak main deferred allocation count 40
173
+ [ALLOC_BUCKET]
174
+ Large Block size 4.0 MB
175
+ Used Block count 1
176
+ Peak Allocated bytes 1.0 MB
177
+ [ALLOC_DEFAULT_MAIN]
178
+ Peak usage frame count: [4.0 MB-8.0 MB]: 5461 frames
179
+ Requested Block Size 16.0 MB
180
+ Peak Block count 1
181
+ Peak Allocated memory 6.8 MB
182
+ Peak Large allocation bytes 0 B
183
+ [ALLOC_DEFAULT_THREAD]
184
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
185
+ Requested Block Size 16.0 MB
186
+ Peak Block count 1
187
+ Peak Allocated memory 17.8 MB
188
+ Peak Large allocation bytes 16.0 MB
189
+ [ALLOC_TEMP_JOB_1_FRAME]
190
+ Initial Block Size 2.0 MB
191
+ Used Block Count 1
192
+ Overflow Count (too large) 0
193
+ Overflow Count (full) 0
194
+ [ALLOC_TEMP_JOB_2_FRAMES]
195
+ Initial Block Size 2.0 MB
196
+ Used Block Count 1
197
+ Overflow Count (too large) 0
198
+ Overflow Count (full) 0
199
+ [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
200
+ Initial Block Size 2.0 MB
201
+ Used Block Count 2
202
+ Overflow Count (too large) 0
203
+ Overflow Count (full) 0
204
+ [ALLOC_TEMP_JOB_ASYNC (Background)]
205
+ Initial Block Size 1.0 MB
206
+ Used Block Count 3
207
+ Overflow Count (too large) 0
208
+ Overflow Count (full) 0
209
+ [ALLOC_GFX] Dual Thread Allocator
210
+ Peak main deferred allocation count 0
211
+ [ALLOC_BUCKET]
212
+ Large Block size 4.0 MB
213
+ Used Block count 1
214
+ Peak Allocated bytes 1.0 MB
215
+ [ALLOC_GFX_MAIN]
216
+ Peak usage frame count: [32.0 KB-64.0 KB]: 3266 frames, [64.0 KB-128.0 KB]: 2195 frames
217
+ Requested Block Size 16.0 MB
218
+ Peak Block count 1
219
+ Peak Allocated memory 67.7 KB
220
+ Peak Large allocation bytes 0 B
221
+ [ALLOC_GFX_THREAD]
222
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5461 frames
223
+ Requested Block Size 16.0 MB
224
+ Peak Block count 1
225
+ Peak Allocated memory 39.6 KB
226
+ Peak Large allocation bytes 0 B
227
+ [ALLOC_CACHEOBJECTS] Dual Thread Allocator
228
+ Peak main deferred allocation count 0
229
+ [ALLOC_BUCKET]
230
+ Large Block size 4.0 MB
231
+ Used Block count 1
232
+ Peak Allocated bytes 1.0 MB
233
+ [ALLOC_CACHEOBJECTS_MAIN]
234
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5461 frames
235
+ Requested Block Size 4.0 MB
236
+ Peak Block count 1
237
+ Peak Allocated memory 0.6 MB
238
+ Peak Large allocation bytes 0 B
239
+ [ALLOC_CACHEOBJECTS_THREAD]
240
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5460 frames, [2.0 MB-4.0 MB]: 1 frames
241
+ Requested Block Size 4.0 MB
242
+ Peak Block count 1
243
+ Peak Allocated memory 2.2 MB
244
+ Peak Large allocation bytes 0 B
245
+ [ALLOC_TYPETREE] Dual Thread Allocator
246
+ Peak main deferred allocation count 0
247
+ [ALLOC_BUCKET]
248
+ Large Block size 4.0 MB
249
+ Used Block count 1
250
+ Peak Allocated bytes 1.0 MB
251
+ [ALLOC_TYPETREE_MAIN]
252
+ Peak usage frame count: [0-1.0 KB]: 5461 frames
253
+ Requested Block Size 2.0 MB
254
+ Peak Block count 1
255
+ Peak Allocated memory 1.0 KB
256
+ Peak Large allocation bytes 0 B
257
+ [ALLOC_TYPETREE_THREAD]
258
+ Peak usage frame count: [1.0 KB-2.0 KB]: 5461 frames
259
+ Requested Block Size 2.0 MB
260
+ Peak Block count 1
261
+ Peak Allocated memory 1.7 KB
262
+ Peak Large allocation bytes 0 B
run_logs/timers.json ADDED
@@ -0,0 +1,377 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.9638962149620056,
6
+ "min": 0.9638962149620056,
7
+ "max": 2.8604817390441895,
8
+ "count": 20
9
+ },
10
+ "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 9203.28125,
12
+ "min": 9203.28125,
13
+ "max": 29294.193359375,
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": 11.765875816345215,
30
+ "min": 0.408211350440979,
31
+ "max": 11.765875816345215,
32
+ "count": 20
33
+ },
34
+ "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2294.345703125,
36
+ "min": 79.19300079345703,
37
+ "max": 2347.130859375,
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": 8756.0,
48
+ "min": 8756.0,
49
+ "max": 10945.0,
50
+ "count": 20
51
+ },
52
+ "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.07031828709937947,
54
+ "min": 0.06320318615482891,
55
+ "max": 0.07713230797161505,
56
+ "count": 20
57
+ },
58
+ "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.2812731483975179,
60
+ "min": 0.25281274461931563,
61
+ "max": 0.3702161867640112,
62
+ "count": 20
63
+ },
64
+ "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.18231537273409318,
66
+ "min": 0.11992926095548434,
67
+ "max": 0.27629638704306936,
68
+ "count": 20
69
+ },
70
+ "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.7292614909363727,
72
+ "min": 0.47971704382193736,
73
+ "max": 1.379825735209035,
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": 23.295454545454547,
114
+ "min": 3.6818181818181817,
115
+ "max": 23.295454545454547,
116
+ "count": 20
117
+ },
118
+ "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1025.0,
120
+ "min": 162.0,
121
+ "max": 1274.0,
122
+ "count": 20
123
+ },
124
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 23.295454545454547,
126
+ "min": 3.6818181818181817,
127
+ "max": 23.295454545454547,
128
+ "count": 20
129
+ },
130
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1025.0,
132
+ "min": 162.0,
133
+ "max": 1274.0,
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": "1719684379",
152
+ "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
+ "mlagents_version": "1.1.0.dev0",
155
+ "mlagents_envs_version": "1.1.0.dev0",
156
+ "communication_protocol_version": "1.5.0",
157
+ "pytorch_version": "2.3.0+cu121",
158
+ "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1719684840"
160
+ },
161
+ "total": 461.00508067199996,
162
+ "count": 1,
163
+ "self": 0.4420015840000815,
164
+ "children": {
165
+ "run_training.setup": {
166
+ "total": 0.05804815099997995,
167
+ "count": 1,
168
+ "self": 0.05804815099997995
169
+ },
170
+ "TrainerController.start_learning": {
171
+ "total": 460.5050309369999,
172
+ "count": 1,
173
+ "self": 0.5879718729955812,
174
+ "children": {
175
+ "TrainerController._reset_env": {
176
+ "total": 2.954511751000041,
177
+ "count": 1,
178
+ "self": 2.954511751000041
179
+ },
180
+ "TrainerController.advance": {
181
+ "total": 456.8746361640042,
182
+ "count": 18201,
183
+ "self": 0.29702686899292985,
184
+ "children": {
185
+ "env_step": {
186
+ "total": 456.57760929501126,
187
+ "count": 18201,
188
+ "self": 296.82794688501906,
189
+ "children": {
190
+ "SubprocessEnvManager._take_step": {
191
+ "total": 159.45893456599674,
192
+ "count": 18201,
193
+ "self": 1.5359172759950752,
194
+ "children": {
195
+ "TorchPolicy.evaluate": {
196
+ "total": 157.92301729000167,
197
+ "count": 18201,
198
+ "self": 157.92301729000167
199
+ }
200
+ }
201
+ },
202
+ "workers": {
203
+ "total": 0.29072784399545526,
204
+ "count": 18201,
205
+ "self": 0.0,
206
+ "children": {
207
+ "worker_root": {
208
+ "total": 459.2139670870007,
209
+ "count": 18201,
210
+ "is_parallel": true,
211
+ "self": 229.77925387199934,
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": 0.007047695999972348,
221
+ "count": 1,
222
+ "is_parallel": true,
223
+ "self": 0.00539912299984735,
224
+ "children": {
225
+ "_process_rank_one_or_two_observation": {
226
+ "total": 0.0016485730001249976,
227
+ "count": 10,
228
+ "is_parallel": true,
229
+ "self": 0.0016485730001249976
230
+ }
231
+ }
232
+ },
233
+ "UnityEnvironment.step": {
234
+ "total": 0.07892860700007986,
235
+ "count": 1,
236
+ "is_parallel": true,
237
+ "self": 0.0007180520001384139,
238
+ "children": {
239
+ "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00032995200001550984,
241
+ "count": 1,
242
+ "is_parallel": true,
243
+ "self": 0.00032995200001550984
244
+ },
245
+ "communicator.exchange": {
246
+ "total": 0.0759353649999639,
247
+ "count": 1,
248
+ "is_parallel": true,
249
+ "self": 0.0759353649999639
250
+ },
251
+ "steps_from_proto": {
252
+ "total": 0.0019452379999620462,
253
+ "count": 1,
254
+ "is_parallel": true,
255
+ "self": 0.0003668469997819557,
256
+ "children": {
257
+ "_process_rank_one_or_two_observation": {
258
+ "total": 0.0015783910001800905,
259
+ "count": 10,
260
+ "is_parallel": true,
261
+ "self": 0.0015783910001800905
262
+ }
263
+ }
264
+ }
265
+ }
266
+ }
267
+ }
268
+ },
269
+ "UnityEnvironment.step": {
270
+ "total": 229.43471321500135,
271
+ "count": 18200,
272
+ "is_parallel": true,
273
+ "self": 10.310564489004264,
274
+ "children": {
275
+ "UnityEnvironment._generate_step_input": {
276
+ "total": 5.333186343002922,
277
+ "count": 18200,
278
+ "is_parallel": true,
279
+ "self": 5.333186343002922
280
+ },
281
+ "communicator.exchange": {
282
+ "total": 180.02053162099685,
283
+ "count": 18200,
284
+ "is_parallel": true,
285
+ "self": 180.02053162099685
286
+ },
287
+ "steps_from_proto": {
288
+ "total": 33.77043076199732,
289
+ "count": 18200,
290
+ "is_parallel": true,
291
+ "self": 6.469620510989671,
292
+ "children": {
293
+ "_process_rank_one_or_two_observation": {
294
+ "total": 27.300810251007647,
295
+ "count": 182000,
296
+ "is_parallel": true,
297
+ "self": 27.300810251007647
298
+ }
299
+ }
300
+ }
301
+ }
302
+ }
303
+ }
304
+ }
305
+ }
306
+ }
307
+ }
308
+ }
309
+ }
310
+ },
311
+ "trainer_threads": {
312
+ "total": 0.00012859299999945506,
313
+ "count": 1,
314
+ "self": 0.00012859299999945506,
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": 451.18733111903225,
324
+ "count": 686288,
325
+ "is_parallel": true,
326
+ "self": 14.541220140073165,
327
+ "children": {
328
+ "process_trajectory": {
329
+ "total": 250.53824417395901,
330
+ "count": 686288,
331
+ "is_parallel": true,
332
+ "self": 249.88781816495896,
333
+ "children": {
334
+ "RLTrainer._checkpoint": {
335
+ "total": 0.6504260090000571,
336
+ "count": 4,
337
+ "is_parallel": true,
338
+ "self": 0.6504260090000571
339
+ }
340
+ }
341
+ },
342
+ "_update_policy": {
343
+ "total": 186.10786680500007,
344
+ "count": 90,
345
+ "is_parallel": true,
346
+ "self": 59.099555289003774,
347
+ "children": {
348
+ "TorchPPOOptimizer.update": {
349
+ "total": 127.0083115159963,
350
+ "count": 4587,
351
+ "is_parallel": true,
352
+ "self": 127.0083115159963
353
+ }
354
+ }
355
+ }
356
+ }
357
+ }
358
+ }
359
+ }
360
+ }
361
+ },
362
+ "TrainerController._save_models": {
363
+ "total": 0.08778255600009288,
364
+ "count": 1,
365
+ "self": 0.001138577000119767,
366
+ "children": {
367
+ "RLTrainer._checkpoint": {
368
+ "total": 0.08664397899997311,
369
+ "count": 1,
370
+ "self": 0.08664397899997311
371
+ }
372
+ }
373
+ }
374
+ }
375
+ }
376
+ }
377
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "SnowballTarget": {
3
+ "checkpoints": [
4
+ {
5
+ "steps": 49936,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 14.363636363636363,
8
+ "creation_time": 1719684504.2845008,
9
+ "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
+ ]
12
+ },
13
+ {
14
+ "steps": 99960,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
+ "reward": 20.0,
17
+ "creation_time": 1719684618.6710055,
18
+ "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 149984,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 22.454545454545453,
26
+ "creation_time": 1719684728.8893168,
27
+ "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
+ ]
30
+ },
31
+ {
32
+ "steps": 199984,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 22.363636363636363,
35
+ "creation_time": 1719684839.871251,
36
+ "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 200112,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
+ "reward": 22.363636363636363,
44
+ "creation_time": 1719684839.9863012,
45
+ "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
+ ]
48
+ }
49
+ ],
50
+ "final_checkpoint": {
51
+ "steps": 200112,
52
+ "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
+ "reward": 22.363636363636363,
54
+ "creation_time": 1719684839.9863012,
55
+ "auxillary_file_paths": [
56
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
+ ]
58
+ }
59
+ },
60
+ "metadata": {
61
+ "stats_format_version": "0.3.0",
62
+ "mlagents_version": "1.1.0.dev0",
63
+ "torch_version": "2.3.0+cu121"
64
+ }
65
+ }