ra9hu commited on
Commit
b413fe8
1 Parent(s): 912fdb1

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: ra9hu/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:d4d4b35f16a58b0a2c23bce1a9922eaa69856748b5da5f805b613e7d9bf86203
3
+ size 650646
SnowballTarget/SnowballTarget-149984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55ce54a1b4cf4df77bda3a5b0b4a2bb74af6c69ed9b3a4a5da2c8c42179f22ab
3
+ size 650646
SnowballTarget/SnowballTarget-149984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0389f3308a5455576ae1e840da2c11393ab2f4076893f2f24c317f6c1aaae10e
3
+ size 3850075
SnowballTarget/SnowballTarget-199984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4d4b35f16a58b0a2c23bce1a9922eaa69856748b5da5f805b613e7d9bf86203
3
+ size 650646
SnowballTarget/SnowballTarget-199984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecf1506e0008e4bb0c1a94ad97e57545ef15d04ca54a871e4a0aeadf5e145a40
3
+ size 3850075
SnowballTarget/SnowballTarget-200112.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4d4b35f16a58b0a2c23bce1a9922eaa69856748b5da5f805b613e7d9bf86203
3
+ size 650646
SnowballTarget/SnowballTarget-200112.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e906f8d7d42cbf5a399465ca4ce0500d50cc275c05990990b307887928f43613
3
+ size 3850075
SnowballTarget/SnowballTarget-49936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:384dd1fbb703e311d23abf2ccfe31e1df6043c05907b4b556af15b9f59bdebe2
3
+ size 650646
SnowballTarget/SnowballTarget-49936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ee8d5986f22f0cd255012ffa7544e217c9bceb4d7be1bb8f9b039536a042342
3
+ size 3850000
SnowballTarget/SnowballTarget-99960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dac538828ef36801d4f1f5bf04cef57d8fecf965a4ed77a197ff86a7eff6d92a
3
+ size 650646
SnowballTarget/SnowballTarget-99960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:192dc831bba27ad954bb14e9f2e968741d0e3f5e101a45f45a9bd2f8cd43bae8
3
+ size 3850000
SnowballTarget/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1151d7fcc8e6e0074a4ef6d9eb2a7ddfb2a0a477fefd32e0ba1f2db409f60aa
3
+ size 3849250
SnowballTarget/events.out.tfevents.1717827566.Raghu-Laptop.18096.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87c75bc26564df6ee20e4b731031167326bb18765fb7a18e27eb6d868d1726b7
3
+ size 23734
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 +1,311 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Mono path[0] = '/home/raghu/DL/topics/RL/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
2
+ Mono config path = '/home/raghu/DL/topics/RL/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: /home/raghu/.config/unity3d/Hugging Face/SnowballTarget
6
+ Unable to load player prefs
7
+ Initialize engine version: 2021.3.14f1 (eee1884e7226)
8
+ [Subsystems] Discovering subsystems at path /home/raghu/DL/topics/RL/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
9
+ Forcing GfxDevice: Null
10
+ GfxDevice: creating device client; threaded=0; jobified=0
11
+ NullGfxDevice:
12
+ Version: NULL 1.0 [1.0]
13
+ Renderer: Null Device
14
+ Vendor: Unity Technologies
15
+ Begin MonoManager ReloadAssembly
16
+ - Completed reload, in 0.054 seconds
17
+ ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
18
+ ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
19
+ ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
20
+ WARNING: Shader Unsupported: 'Standard' - All subshaders removed
21
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
22
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
23
+ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
24
+ WARNING: Shader Unsupported: 'Standard' - All subshaders removed
25
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
26
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
27
+ UnloadTime: 0.380430 ms
28
+ ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
29
+ requesting resize 84 x 84
30
+ Setting up 8 worker threads for Enlighten.
31
+ Memory Statistics:
32
+ [ALLOC_TEMP_TLS] TLS Allocator
33
+ StackAllocators :
34
+ [ALLOC_TEMP_MAIN]
35
+ 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
36
+ Initial Block Size 4.0 MB
37
+ Current Block Size 4.0 MB
38
+ Peak Allocated Bytes 2.0 MB
39
+ Overflow Count 0
40
+ [ALLOC_TEMP_Loading.AsyncRead]
41
+ Initial Block Size 64.0 KB
42
+ Current Block Size 64.0 KB
43
+ Peak Allocated Bytes 230 B
44
+ Overflow Count 0
45
+ [ALLOC_TEMP_Loading.PreloadManager]
46
+ Initial Block Size 256.0 KB
47
+ Current Block Size 304.0 KB
48
+ Peak Allocated Bytes 228.9 KB
49
+ Overflow Count 4
50
+ [ALLOC_TEMP_Background Job.Worker 8]
51
+ Initial Block Size 32.0 KB
52
+ Current Block Size 32.0 KB
53
+ Peak Allocated Bytes 0 B
54
+ Overflow Count 0
55
+ [ALLOC_TEMP_Job.Worker 6]
56
+ Initial Block Size 256.0 KB
57
+ Current Block Size 256.0 KB
58
+ Peak Allocated Bytes 3.6 KB
59
+ Overflow Count 0
60
+ [ALLOC_TEMP_Job.Worker 0]
61
+ Initial Block Size 256.0 KB
62
+ Current Block Size 256.0 KB
63
+ Peak Allocated Bytes 3.6 KB
64
+ Overflow Count 0
65
+ [ALLOC_TEMP_Background Job.Worker 10]
66
+ Initial Block Size 32.0 KB
67
+ Current Block Size 32.0 KB
68
+ Peak Allocated Bytes 0 B
69
+ Overflow Count 0
70
+ [ALLOC_TEMP_Background Job.Worker 9]
71
+ Initial Block Size 32.0 KB
72
+ Current Block Size 32.0 KB
73
+ Peak Allocated Bytes 0 B
74
+ Overflow Count 0
75
+ [ALLOC_TEMP_Job.Worker 5]
76
+ Initial Block Size 256.0 KB
77
+ Current Block Size 256.0 KB
78
+ Peak Allocated Bytes 3.6 KB
79
+ Overflow Count 0
80
+ [ALLOC_TEMP_Background Job.Worker 14]
81
+ Initial Block Size 32.0 KB
82
+ Current Block Size 32.0 KB
83
+ Peak Allocated Bytes 0 B
84
+ Overflow Count 0
85
+ [ALLOC_TEMP_Background Job.Worker 6]
86
+ Initial Block Size 32.0 KB
87
+ Current Block Size 32.0 KB
88
+ Peak Allocated Bytes 0 B
89
+ Overflow Count 0
90
+ [ALLOC_TEMP_Job.Worker 4]
91
+ Initial Block Size 256.0 KB
92
+ Current Block Size 256.0 KB
93
+ Peak Allocated Bytes 3.6 KB
94
+ Overflow Count 0
95
+ [ALLOC_TEMP_Job.Worker 14]
96
+ Initial Block Size 256.0 KB
97
+ Current Block Size 256.0 KB
98
+ Peak Allocated Bytes 3.6 KB
99
+ Overflow Count 0
100
+ [ALLOC_TEMP_Job.Worker 3]
101
+ Initial Block Size 256.0 KB
102
+ Current Block Size 256.0 KB
103
+ Peak Allocated Bytes 3.6 KB
104
+ Overflow Count 0
105
+ [ALLOC_TEMP_Job.Worker 13]
106
+ Initial Block Size 256.0 KB
107
+ Current Block Size 256.0 KB
108
+ Peak Allocated Bytes 3.6 KB
109
+ Overflow Count 0
110
+ [ALLOC_TEMP_Background Job.Worker 12]
111
+ Initial Block Size 32.0 KB
112
+ Current Block Size 32.0 KB
113
+ Peak Allocated Bytes 0 B
114
+ Overflow Count 0
115
+ [ALLOC_TEMP_EnlightenWorker] x 8
116
+ Initial Block Size 64.0 KB
117
+ Current Block Size 64.0 KB
118
+ Peak Allocated Bytes 0 B
119
+ Overflow Count 0
120
+ [ALLOC_TEMP_Background Job.Worker 15]
121
+ Initial Block Size 32.0 KB
122
+ Current Block Size 32.0 KB
123
+ Peak Allocated Bytes 0 B
124
+ Overflow Count 0
125
+ [ALLOC_TEMP_Background Job.Worker 1]
126
+ Initial Block Size 32.0 KB
127
+ Current Block Size 32.0 KB
128
+ Peak Allocated Bytes 0 B
129
+ Overflow Count 0
130
+ [ALLOC_TEMP_Background Job.Worker 2]
131
+ Initial Block Size 32.0 KB
132
+ Current Block Size 32.0 KB
133
+ Peak Allocated Bytes 0 B
134
+ Overflow Count 0
135
+ [ALLOC_TEMP_Background Job.Worker 7]
136
+ Initial Block Size 32.0 KB
137
+ Current Block Size 32.0 KB
138
+ Peak Allocated Bytes 0 B
139
+ Overflow Count 0
140
+ [ALLOC_TEMP_AssetGarbageCollectorHelper] x 15
141
+ Initial Block Size 64.0 KB
142
+ Current Block Size 64.0 KB
143
+ Peak Allocated Bytes 0 B
144
+ Overflow Count 0
145
+ [ALLOC_TEMP_Background Job.Worker 5]
146
+ Initial Block Size 32.0 KB
147
+ Current Block Size 32.0 KB
148
+ Peak Allocated Bytes 0 B
149
+ Overflow Count 0
150
+ [ALLOC_TEMP_Job.Worker 9]
151
+ Initial Block Size 256.0 KB
152
+ Current Block Size 256.0 KB
153
+ Peak Allocated Bytes 3.6 KB
154
+ Overflow Count 0
155
+ [ALLOC_TEMP_Background Job.Worker 13]
156
+ Initial Block Size 32.0 KB
157
+ Current Block Size 32.0 KB
158
+ Peak Allocated Bytes 0 B
159
+ Overflow Count 0
160
+ [ALLOC_TEMP_Job.Worker 8]
161
+ Initial Block Size 256.0 KB
162
+ Current Block Size 256.0 KB
163
+ Peak Allocated Bytes 3.6 KB
164
+ Overflow Count 0
165
+ [ALLOC_TEMP_Job.Worker 7]
166
+ Initial Block Size 256.0 KB
167
+ Current Block Size 256.0 KB
168
+ Peak Allocated Bytes 3.6 KB
169
+ Overflow Count 0
170
+ [ALLOC_TEMP_Job.Worker 1]
171
+ Initial Block Size 256.0 KB
172
+ Current Block Size 256.0 KB
173
+ Peak Allocated Bytes 3.6 KB
174
+ Overflow Count 0
175
+ [ALLOC_TEMP_Job.Worker 2]
176
+ Initial Block Size 256.0 KB
177
+ Current Block Size 256.0 KB
178
+ Peak Allocated Bytes 3.6 KB
179
+ Overflow Count 0
180
+ [ALLOC_TEMP_Background Job.Worker 3]
181
+ Initial Block Size 32.0 KB
182
+ Current Block Size 32.0 KB
183
+ Peak Allocated Bytes 0 B
184
+ Overflow Count 0
185
+ [ALLOC_TEMP_Background Job.Worker 11]
186
+ Initial Block Size 32.0 KB
187
+ Current Block Size 32.0 KB
188
+ Peak Allocated Bytes 0 B
189
+ Overflow Count 0
190
+ [ALLOC_TEMP_Job.Worker 10]
191
+ Initial Block Size 256.0 KB
192
+ Current Block Size 256.0 KB
193
+ Peak Allocated Bytes 3.6 KB
194
+ Overflow Count 0
195
+ [ALLOC_TEMP_Background Job.Worker 0]
196
+ Initial Block Size 32.0 KB
197
+ Current Block Size 32.0 KB
198
+ Peak Allocated Bytes 0 B
199
+ Overflow Count 0
200
+ [ALLOC_TEMP_Job.Worker 11]
201
+ Initial Block Size 256.0 KB
202
+ Current Block Size 256.0 KB
203
+ Peak Allocated Bytes 3.6 KB
204
+ Overflow Count 0
205
+ [ALLOC_TEMP_Job.Worker 12]
206
+ Initial Block Size 256.0 KB
207
+ Current Block Size 256.0 KB
208
+ Peak Allocated Bytes 3.6 KB
209
+ Overflow Count 0
210
+ [ALLOC_TEMP_Background Job.Worker 4]
211
+ Initial Block Size 32.0 KB
212
+ Current Block Size 32.0 KB
213
+ Peak Allocated Bytes 0 B
214
+ Overflow Count 0
215
+ [ALLOC_TEMP_BatchDeleteObjects]
216
+ Initial Block Size 64.0 KB
217
+ Current Block Size 64.0 KB
218
+ Peak Allocated Bytes 0 B
219
+ Overflow Count 0
220
+ [ALLOC_DEFAULT] Dual Thread Allocator
221
+ Peak main deferred allocation count 41
222
+ [ALLOC_BUCKET]
223
+ Large Block size 4.0 MB
224
+ Used Block count 1
225
+ Peak Allocated bytes 1.0 MB
226
+ [ALLOC_DEFAULT_MAIN]
227
+ Peak usage frame count: [4.0 MB-8.0 MB]: 5461 frames
228
+ Requested Block Size 16.0 MB
229
+ Peak Block count 1
230
+ Peak Allocated memory 7.0 MB
231
+ Peak Large allocation bytes 0 B
232
+ [ALLOC_DEFAULT_THREAD]
233
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
234
+ Requested Block Size 16.0 MB
235
+ Peak Block count 1
236
+ Peak Allocated memory 17.5 MB
237
+ Peak Large allocation bytes 16.0 MB
238
+ [ALLOC_TEMP_JOB_1_FRAME]
239
+ Initial Block Size 2.0 MB
240
+ Used Block Count 1
241
+ Overflow Count (too large) 0
242
+ Overflow Count (full) 0
243
+ [ALLOC_TEMP_JOB_2_FRAMES]
244
+ Initial Block Size 2.0 MB
245
+ Used Block Count 1
246
+ Overflow Count (too large) 0
247
+ Overflow Count (full) 0
248
+ [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
249
+ Initial Block Size 2.0 MB
250
+ Used Block Count 2
251
+ Overflow Count (too large) 0
252
+ Overflow Count (full) 0
253
+ [ALLOC_TEMP_JOB_ASYNC (Background)]
254
+ Initial Block Size 1.0 MB
255
+ Used Block Count 3
256
+ Overflow Count (too large) 0
257
+ Overflow Count (full) 0
258
+ [ALLOC_GFX] Dual Thread Allocator
259
+ Peak main deferred allocation count 0
260
+ [ALLOC_BUCKET]
261
+ Large Block size 4.0 MB
262
+ Used Block count 1
263
+ Peak Allocated bytes 1.0 MB
264
+ [ALLOC_GFX_MAIN]
265
+ Peak usage frame count: [32.0 KB-64.0 KB]: 3543 frames, [64.0 KB-128.0 KB]: 1918 frames
266
+ Requested Block Size 16.0 MB
267
+ Peak Block count 1
268
+ Peak Allocated memory 67.7 KB
269
+ Peak Large allocation bytes 0 B
270
+ [ALLOC_GFX_THREAD]
271
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5461 frames
272
+ Requested Block Size 16.0 MB
273
+ Peak Block count 1
274
+ Peak Allocated memory 39.6 KB
275
+ Peak Large allocation bytes 0 B
276
+ [ALLOC_CACHEOBJECTS] Dual Thread Allocator
277
+ Peak main deferred allocation count 0
278
+ [ALLOC_BUCKET]
279
+ Large Block size 4.0 MB
280
+ Used Block count 1
281
+ Peak Allocated bytes 1.0 MB
282
+ [ALLOC_CACHEOBJECTS_MAIN]
283
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5461 frames
284
+ Requested Block Size 4.0 MB
285
+ Peak Block count 1
286
+ Peak Allocated memory 0.6 MB
287
+ Peak Large allocation bytes 0 B
288
+ [ALLOC_CACHEOBJECTS_THREAD]
289
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5460 frames, [2.0 MB-4.0 MB]: 1 frames
290
+ Requested Block Size 4.0 MB
291
+ Peak Block count 1
292
+ Peak Allocated memory 2.2 MB
293
+ Peak Large allocation bytes 0 B
294
+ [ALLOC_TYPETREE] Dual Thread Allocator
295
+ Peak main deferred allocation count 0
296
+ [ALLOC_BUCKET]
297
+ Large Block size 4.0 MB
298
+ Used Block count 1
299
+ Peak Allocated bytes 1.0 MB
300
+ [ALLOC_TYPETREE_MAIN]
301
+ Peak usage frame count: [0-1.0 KB]: 5461 frames
302
+ Requested Block Size 2.0 MB
303
+ Peak Block count 1
304
+ Peak Allocated memory 1.0 KB
305
+ Peak Large allocation bytes 0 B
306
+ [ALLOC_TYPETREE_THREAD]
307
+ Peak usage frame count: [1.0 KB-2.0 KB]: 5461 frames
308
+ Requested Block Size 2.0 MB
309
+ Peak Block count 1
310
+ Peak Allocated memory 1.7 KB
311
+ 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": 1.0279631614685059,
6
+ "min": 1.0279631614685059,
7
+ "max": 2.867321252822876,
8
+ "count": 20
9
+ },
10
+ "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 9826.2998046875,
12
+ "min": 9826.2998046875,
13
+ "max": 29395.77734375,
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": 11.7504243850708,
30
+ "min": 0.2524029016494751,
31
+ "max": 11.7504243850708,
32
+ "count": 20
33
+ },
34
+ "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2291.332763671875,
36
+ "min": 48.966163635253906,
37
+ "max": 2352.94287109375,
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": 0.0709494298588848,
54
+ "min": 0.06142763798138107,
55
+ "max": 0.07520414394584449,
56
+ "count": 20
57
+ },
58
+ "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.2837977194355392,
60
+ "min": 0.24571055192552427,
61
+ "max": 0.3760207197292224,
62
+ "count": 20
63
+ },
64
+ "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.20475001932651388,
66
+ "min": 0.1187521502393864,
67
+ "max": 0.26916437856122555,
68
+ "count": 20
69
+ },
70
+ "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.8190000773060555,
72
+ "min": 0.4750086009575456,
73
+ "max": 1.3458218928061279,
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": 24.045454545454547,
114
+ "min": 3.25,
115
+ "max": 24.045454545454547,
116
+ "count": 20
117
+ },
118
+ "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1058.0,
120
+ "min": 143.0,
121
+ "max": 1266.0,
122
+ "count": 20
123
+ },
124
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 24.045454545454547,
126
+ "min": 3.25,
127
+ "max": 24.045454545454547,
128
+ "count": 20
129
+ },
130
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1058.0,
132
+ "min": 143.0,
133
+ "max": 1266.0,
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": "1717827566",
152
+ "python_version": "3.10.14 (main, Mar 21 2024, 16:24:04) [GCC 11.2.0]",
153
+ "command_line_arguments": "/home/raghu/anaconda3/envs/rl/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": "1717827732"
160
+ },
161
+ "total": 166.1779586749999,
162
+ "count": 1,
163
+ "self": 0.16811870299898146,
164
+ "children": {
165
+ "run_training.setup": {
166
+ "total": 0.012018883000564529,
167
+ "count": 1,
168
+ "self": 0.012018883000564529
169
+ },
170
+ "TrainerController.start_learning": {
171
+ "total": 165.99782108900035,
172
+ "count": 1,
173
+ "self": 0.2624971379991621,
174
+ "children": {
175
+ "TrainerController._reset_env": {
176
+ "total": 1.2432652869993035,
177
+ "count": 1,
178
+ "self": 1.2432652869993035
179
+ },
180
+ "TrainerController.advance": {
181
+ "total": 164.44931308900232,
182
+ "count": 18203,
183
+ "self": 0.10917209904346237,
184
+ "children": {
185
+ "env_step": {
186
+ "total": 164.34014098995885,
187
+ "count": 18203,
188
+ "self": 116.99113025104634,
189
+ "children": {
190
+ "SubprocessEnvManager._take_step": {
191
+ "total": 47.221452809904804,
192
+ "count": 18203,
193
+ "self": 0.532330039018234,
194
+ "children": {
195
+ "TorchPolicy.evaluate": {
196
+ "total": 46.68912277088657,
197
+ "count": 18203,
198
+ "self": 46.68912277088657
199
+ }
200
+ }
201
+ },
202
+ "workers": {
203
+ "total": 0.12755792900770757,
204
+ "count": 18203,
205
+ "self": 0.0,
206
+ "children": {
207
+ "worker_root": {
208
+ "total": 165.70048179094556,
209
+ "count": 18203,
210
+ "is_parallel": true,
211
+ "self": 80.56517391897523,
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": 0.001716224000119837,
221
+ "count": 1,
222
+ "is_parallel": true,
223
+ "self": 0.0010312680005881703,
224
+ "children": {
225
+ "_process_rank_one_or_two_observation": {
226
+ "total": 0.0006849559995316667,
227
+ "count": 10,
228
+ "is_parallel": true,
229
+ "self": 0.0006849559995316667
230
+ }
231
+ }
232
+ },
233
+ "UnityEnvironment.step": {
234
+ "total": 0.0126091929996619,
235
+ "count": 1,
236
+ "is_parallel": true,
237
+ "self": 0.0001914710010169074,
238
+ "children": {
239
+ "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00019679899924085476,
241
+ "count": 1,
242
+ "is_parallel": true,
243
+ "self": 0.00019679899924085476
244
+ },
245
+ "communicator.exchange": {
246
+ "total": 0.011707337999723677,
247
+ "count": 1,
248
+ "is_parallel": true,
249
+ "self": 0.011707337999723677
250
+ },
251
+ "steps_from_proto": {
252
+ "total": 0.0005135849996804609,
253
+ "count": 1,
254
+ "is_parallel": true,
255
+ "self": 0.00011790200096584158,
256
+ "children": {
257
+ "_process_rank_one_or_two_observation": {
258
+ "total": 0.0003956829987146193,
259
+ "count": 10,
260
+ "is_parallel": true,
261
+ "self": 0.0003956829987146193
262
+ }
263
+ }
264
+ }
265
+ }
266
+ }
267
+ }
268
+ },
269
+ "UnityEnvironment.step": {
270
+ "total": 85.13530787197033,
271
+ "count": 18202,
272
+ "is_parallel": true,
273
+ "self": 3.840323996085317,
274
+ "children": {
275
+ "UnityEnvironment._generate_step_input": {
276
+ "total": 2.6529291919132447,
277
+ "count": 18202,
278
+ "is_parallel": true,
279
+ "self": 2.6529291919132447
280
+ },
281
+ "communicator.exchange": {
282
+ "total": 67.41352413199638,
283
+ "count": 18202,
284
+ "is_parallel": true,
285
+ "self": 67.41352413199638
286
+ },
287
+ "steps_from_proto": {
288
+ "total": 11.228530551975382,
289
+ "count": 18202,
290
+ "is_parallel": true,
291
+ "self": 2.0383672699608724,
292
+ "children": {
293
+ "_process_rank_one_or_two_observation": {
294
+ "total": 9.19016328201451,
295
+ "count": 182020,
296
+ "is_parallel": true,
297
+ "self": 9.19016328201451
298
+ }
299
+ }
300
+ }
301
+ }
302
+ }
303
+ }
304
+ }
305
+ }
306
+ }
307
+ }
308
+ }
309
+ }
310
+ },
311
+ "trainer_threads": {
312
+ "total": 0.00013606599986815127,
313
+ "count": 1,
314
+ "self": 0.00013606599986815127,
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": 164.11276653164896,
324
+ "count": 185808,
325
+ "is_parallel": true,
326
+ "self": 1.3819273636800062,
327
+ "children": {
328
+ "process_trajectory": {
329
+ "total": 90.07494031897022,
330
+ "count": 185808,
331
+ "is_parallel": true,
332
+ "self": 89.72843368097074,
333
+ "children": {
334
+ "RLTrainer._checkpoint": {
335
+ "total": 0.34650663799948234,
336
+ "count": 4,
337
+ "is_parallel": true,
338
+ "self": 0.34650663799948234
339
+ }
340
+ }
341
+ },
342
+ "_update_policy": {
343
+ "total": 72.65589884899873,
344
+ "count": 90,
345
+ "is_parallel": true,
346
+ "self": 16.892796432961404,
347
+ "children": {
348
+ "TorchPPOOptimizer.update": {
349
+ "total": 55.76310241603733,
350
+ "count": 4587,
351
+ "is_parallel": true,
352
+ "self": 55.76310241603733
353
+ }
354
+ }
355
+ }
356
+ }
357
+ }
358
+ }
359
+ }
360
+ }
361
+ },
362
+ "TrainerController._save_models": {
363
+ "total": 0.042609508999703394,
364
+ "count": 1,
365
+ "self": 0.0009175530003631138,
366
+ "children": {
367
+ "RLTrainer._checkpoint": {
368
+ "total": 0.04169195599934028,
369
+ "count": 1,
370
+ "self": 0.04169195599934028
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": 13.363636363636363,
8
+ "creation_time": 1717827610.3106282,
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": 1717827651.5889459,
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": 21.545454545454547,
26
+ "creation_time": 1717827692.3454957,
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": 23.545454545454547,
35
+ "creation_time": 1717827732.1932886,
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": 23.545454545454547,
44
+ "creation_time": 1717827732.2489643,
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": 23.545454545454547,
54
+ "creation_time": 1717827732.2489643,
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
+ }