jrauch4 commited on
Commit
b056ea8
1 Parent(s): 6cc9e5f

SnowballTarget - first try

Browse files
README.md ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - unity-ml-agents
5
+ - ml-agents
6
+ - deep-reinforcement-learning
7
+ - reinforcement-learning
8
+ - ML-Agents-SnowballTarget
9
+ library_name: ml-agents
10
+ ---
11
+
12
+ # **ppo** Agent playing **SnowballTarget**
13
+ This is a trained model of a **ppo** agent playing **SnowballTarget** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
14
+
15
+ ## Usage (with ML-Agents)
16
+ The Documentation: https://github.com/huggingface/ml-agents#get-started
17
+ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
18
+
19
+
20
+ ### Resume the training
21
+ ```
22
+ mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
23
+ ```
24
+ ### Watch your Agent play
25
+ You can watch your agent **playing directly in your browser:**.
26
+
27
+ 1. Go to https://huggingface.co/spaces/unity/ML-Agents-SnowballTarget
28
+ 2. Step 1: Write your model_id: jrauch4/ppo-SnowballTarget
29
+ 3. Step 2: Select your *.nn /*.onnx file
30
+ 4. Click on Watch the agent play 👀
31
+
SnowballTarget.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb5d4c7d4a5e8c0f00c74cd60fa4c2508eb0659607e4948deb15832e1ccacac8
3
+ size 645119
SnowballTarget/SnowballTarget-125592.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:215bbdd5e692ee7ade626e82e19035a135ed39176e60b1646eff782d3776b5fe
3
+ size 645119
SnowballTarget/SnowballTarget-125592.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dcbbb66c41f20d93074c389f74b55a5d9793c58108fc2e065736bba1c8a66d4
3
+ size 3845312
SnowballTarget/SnowballTarget-1408.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:579bc1cc9e4a5129349a0d054364ea21bcd896a384f0af181b2dee8a9d89d73f
3
+ size 645119
SnowballTarget/SnowballTarget-1408.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bac96f70de7d9f346bd05cfd0425a8509aed910bb20046d77b4d27f6654409b3
3
+ size 1285728
SnowballTarget/SnowballTarget-149984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08c63aa2b5c0f419c3f54dc809b1e01c0125d35504601e68a8c24ad1e95b7497
3
+ size 645119
SnowballTarget/SnowballTarget-149984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:046f4a0d0165a428ad06d0e2add83306a36b114fe2aaf01932ac011c5199da55
3
+ size 3845312
SnowballTarget/SnowballTarget-199984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb5d4c7d4a5e8c0f00c74cd60fa4c2508eb0659607e4948deb15832e1ccacac8
3
+ size 645119
SnowballTarget/SnowballTarget-199984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daa970b63d53b6592c74c7a462271950b80d7bf0a86cb2c6e3babfe0aee34984
3
+ size 3845312
SnowballTarget/SnowballTarget-200368.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb5d4c7d4a5e8c0f00c74cd60fa4c2508eb0659607e4948deb15832e1ccacac8
3
+ size 645119
SnowballTarget/SnowballTarget-200368.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60d8e0cc10c9f41f330802cf4f8a2958a4678e6494c19f9da0ea611b3a981dd4
3
+ size 3845312
SnowballTarget/SnowballTarget-49936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06f89b74c62b4cef4c7c8ea8b0620a4d18df79e6582564dd0e45a748952c8f57
3
+ size 645119
SnowballTarget/SnowballTarget-49936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a854d81907d5b5dc9263059b3db9bc4d34151fd470ebc1602f00fb45d95a3e88
3
+ size 3845312
SnowballTarget/SnowballTarget-99960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c25cd4e017767ce894ddcbeab83b28091712adadcfd253932fa03ae33f1aa73b
3
+ size 645119
SnowballTarget/SnowballTarget-99960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c4e5bc31668c596264d68a59ebf9fe0a286df4e18e75b5bab6a8fd145fee488
3
+ size 3845312
SnowballTarget/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60d8e0cc10c9f41f330802cf4f8a2958a4678e6494c19f9da0ea611b3a981dd4
3
+ size 3845312
SnowballTarget/events.out.tfevents.1673952243.8a42fd845b75.5303.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a2d93e8ef2b487acb168530b260605856c427043786026d41e43b8e934e3fa9
3
+ size 17301
SnowballTarget/events.out.tfevents.1673952569.8a42fd845b75.6872.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18bc4029a11f0ebbd87f73b7aed687fa9099fed276f9dfcba52bcebcfb968157
3
+ size 7737
config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 4096, "learning_rate": 0.0005, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 5, "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": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": true, "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: 4096
8
+ learning_rate: 0.0005
9
+ beta: 0.005
10
+ epsilon: 0.2
11
+ lambd: 0.95
12
+ num_epoch: 5
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: SnowballTarget1
66
+ initialize_from: null
67
+ load_model: false
68
+ resume: true
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 +1,259 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
2
+ Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
+ Preloaded 'lib_burst_generated.so'
4
+ Preloaded 'libgrpc_csharp_ext.x64.so'
5
+ Initialize engine version: 2021.3.14f1 (eee1884e7226)
6
+ [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
7
+ Forcing GfxDevice: Null
8
+ GfxDevice: creating device client; threaded=0; jobified=0
9
+ NullGfxDevice:
10
+ Version: NULL 1.0 [1.0]
11
+ Renderer: Null Device
12
+ Vendor: Unity Technologies
13
+ ALSA lib confmisc.c:767:(parse_card) cannot find card '0'
14
+ ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
15
+ ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
16
+ ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
17
+ ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
18
+ ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
19
+ ALSA lib conf.c:5007:(snd_config_expand) Evaluate error: No such file or directory
20
+ ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM default
21
+ FMOD failed to initialize the output device.: "Error initializing output device. " (60)
22
+ Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
23
+ ALSA lib confmisc.c:767:(parse_card) cannot find card '0'
24
+ ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
25
+ ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
26
+ ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
27
+ ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
28
+ ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
29
+ ALSA lib conf.c:5007:(snd_config_expand) Evaluate error: No such file or directory
30
+ ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM default
31
+ FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
+ FMOD initialized on nosound output
33
+ Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.073 seconds
35
+ ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
+ ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
+ ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
38
+ WARNING: Shader Unsupported: 'Standard' - All subshaders removed
39
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
40
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
41
+ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
42
+ WARNING: Shader Unsupported: 'Standard' - All subshaders removed
43
+ WARNING: Shader Did you use #pragma only_renderers and omit this platform?
44
+ WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
45
+ UnloadTime: 0.618724 ms
46
+ ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
47
+ requesting resize 84 x 84
48
+ Setting up 1 worker threads for Enlighten.
49
+ Memory Statistics:
50
+ [ALLOC_TEMP_TLS] TLS Allocator
51
+ StackAllocators :
52
+ [ALLOC_TEMP_MAIN]
53
+ Peak usage frame count: [8.0 KB-16.0 KB]: 2006 frames, [16.0 KB-32.0 KB]: 34 frames, [2.0 MB-4.0 MB]: 1 frames
54
+ Initial Block Size 4.0 MB
55
+ Current Block Size 4.0 MB
56
+ Peak Allocated Bytes 2.0 MB
57
+ Overflow Count 0
58
+ [ALLOC_TEMP_Loading.AsyncRead]
59
+ Initial Block Size 64.0 KB
60
+ Current Block Size 64.0 KB
61
+ Peak Allocated Bytes 198 B
62
+ Overflow Count 0
63
+ [ALLOC_TEMP_Loading.PreloadManager]
64
+ Initial Block Size 256.0 KB
65
+ Current Block Size 304.0 KB
66
+ Peak Allocated Bytes 228.9 KB
67
+ Overflow Count 4
68
+ [ALLOC_TEMP_Background Job.Worker 8]
69
+ Initial Block Size 32.0 KB
70
+ Current Block Size 32.0 KB
71
+ Peak Allocated Bytes 0 B
72
+ Overflow Count 0
73
+ [ALLOC_TEMP_Background Job.Worker 9]
74
+ Initial Block Size 32.0 KB
75
+ Current Block Size 32.0 KB
76
+ Peak Allocated Bytes 0 B
77
+ Overflow Count 0
78
+ [ALLOC_TEMP_Job.Worker 0]
79
+ Initial Block Size 256.0 KB
80
+ Current Block Size 256.0 KB
81
+ Peak Allocated Bytes 3.6 KB
82
+ Overflow Count 0
83
+ [ALLOC_TEMP_Background Job.Worker 10]
84
+ Initial Block Size 32.0 KB
85
+ Current Block Size 32.0 KB
86
+ Peak Allocated Bytes 0 B
87
+ Overflow Count 0
88
+ [ALLOC_TEMP_Background Job.Worker 14]
89
+ Initial Block Size 32.0 KB
90
+ Current Block Size 32.0 KB
91
+ Peak Allocated Bytes 0 B
92
+ Overflow Count 0
93
+ [ALLOC_TEMP_Background Job.Worker 6]
94
+ Initial Block Size 32.0 KB
95
+ Current Block Size 32.0 KB
96
+ Peak Allocated Bytes 0 B
97
+ Overflow Count 0
98
+ [ALLOC_TEMP_Background Job.Worker 12]
99
+ Initial Block Size 32.0 KB
100
+ Current Block Size 32.0 KB
101
+ Peak Allocated Bytes 0 B
102
+ Overflow Count 0
103
+ [ALLOC_TEMP_EnlightenWorker]
104
+ Initial Block Size 64.0 KB
105
+ Current Block Size 64.0 KB
106
+ Peak Allocated Bytes 0 B
107
+ Overflow Count 0
108
+ [ALLOC_TEMP_Background Job.Worker 15]
109
+ Initial Block Size 32.0 KB
110
+ Current Block Size 32.0 KB
111
+ Peak Allocated Bytes 0 B
112
+ Overflow Count 0
113
+ [ALLOC_TEMP_Background Job.Worker 1]
114
+ Initial Block Size 32.0 KB
115
+ Current Block Size 32.0 KB
116
+ Peak Allocated Bytes 0 B
117
+ Overflow Count 0
118
+ [ALLOC_TEMP_Background Job.Worker 2]
119
+ Initial Block Size 32.0 KB
120
+ Current Block Size 32.0 KB
121
+ Peak Allocated Bytes 0 B
122
+ Overflow Count 0
123
+ [ALLOC_TEMP_Background Job.Worker 7]
124
+ Initial Block Size 32.0 KB
125
+ Current Block Size 32.0 KB
126
+ Peak Allocated Bytes 0 B
127
+ Overflow Count 0
128
+ [ALLOC_TEMP_AssetGarbageCollectorHelper]
129
+ Initial Block Size 64.0 KB
130
+ Current Block Size 64.0 KB
131
+ Peak Allocated Bytes 0 B
132
+ Overflow Count 0
133
+ [ALLOC_TEMP_Background Job.Worker 5]
134
+ Initial Block Size 32.0 KB
135
+ Current Block Size 32.0 KB
136
+ Peak Allocated Bytes 0 B
137
+ Overflow Count 0
138
+ [ALLOC_TEMP_Background Job.Worker 13]
139
+ Initial Block Size 32.0 KB
140
+ Current Block Size 32.0 KB
141
+ Peak Allocated Bytes 0 B
142
+ Overflow Count 0
143
+ [ALLOC_TEMP_Background Job.Worker 11]
144
+ Initial Block Size 32.0 KB
145
+ Current Block Size 32.0 KB
146
+ Peak Allocated Bytes 0 B
147
+ Overflow Count 0
148
+ [ALLOC_TEMP_Background Job.Worker 3]
149
+ Initial Block Size 32.0 KB
150
+ Current Block Size 32.0 KB
151
+ Peak Allocated Bytes 0 B
152
+ Overflow Count 0
153
+ [ALLOC_TEMP_Background Job.Worker 0]
154
+ Initial Block Size 32.0 KB
155
+ Current Block Size 32.0 KB
156
+ Peak Allocated Bytes 0 B
157
+ Overflow Count 0
158
+ [ALLOC_TEMP_Background Job.Worker 4]
159
+ Initial Block Size 32.0 KB
160
+ Current Block Size 32.0 KB
161
+ Peak Allocated Bytes 0 B
162
+ Overflow Count 0
163
+ [ALLOC_TEMP_BatchDeleteObjects]
164
+ Initial Block Size 64.0 KB
165
+ Current Block Size 64.0 KB
166
+ Peak Allocated Bytes 0 B
167
+ Overflow Count 0
168
+ [ALLOC_DEFAULT] Dual Thread Allocator
169
+ Peak main deferred allocation count 33
170
+ [ALLOC_BUCKET]
171
+ Large Block size 4.0 MB
172
+ Used Block count 1
173
+ Peak Allocated bytes 0.9 MB
174
+ [ALLOC_DEFAULT_MAIN]
175
+ Peak usage frame count: [4.0 MB-8.0 MB]: 2041 frames
176
+ Requested Block Size 16.0 MB
177
+ Peak Block count 1
178
+ Peak Allocated memory 5.6 MB
179
+ Peak Large allocation bytes 0 B
180
+ [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 2041 frames
182
+ Requested Block Size 16.0 MB
183
+ Peak Block count 1
184
+ Peak Allocated memory 17.8 MB
185
+ Peak Large allocation bytes 16.0 MB
186
+ [ALLOC_TEMP_JOB_1_FRAME]
187
+ Initial Block Size 2.0 MB
188
+ Used Block Count 1
189
+ Overflow Count (too large) 0
190
+ Overflow Count (full) 0
191
+ [ALLOC_TEMP_JOB_2_FRAMES]
192
+ Initial Block Size 2.0 MB
193
+ Used Block Count 1
194
+ Overflow Count (too large) 0
195
+ Overflow Count (full) 0
196
+ [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
197
+ Initial Block Size 2.0 MB
198
+ Used Block Count 2
199
+ Overflow Count (too large) 0
200
+ Overflow Count (full) 0
201
+ [ALLOC_TEMP_JOB_ASYNC (Background)]
202
+ Initial Block Size 1.0 MB
203
+ Used Block Count 3
204
+ Overflow Count (too large) 0
205
+ Overflow Count (full) 0
206
+ [ALLOC_GFX] Dual Thread Allocator
207
+ Peak main deferred allocation count 0
208
+ [ALLOC_BUCKET]
209
+ Large Block size 4.0 MB
210
+ Used Block count 1
211
+ Peak Allocated bytes 0.9 MB
212
+ [ALLOC_GFX_MAIN]
213
+ Peak usage frame count: [32.0 KB-64.0 KB]: 1993 frames, [64.0 KB-128.0 KB]: 48 frames
214
+ Requested Block Size 16.0 MB
215
+ Peak Block count 1
216
+ Peak Allocated memory 65.6 KB
217
+ Peak Large allocation bytes 0 B
218
+ [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 2041 frames
220
+ Requested Block Size 16.0 MB
221
+ Peak Block count 1
222
+ Peak Allocated memory 39.6 KB
223
+ Peak Large allocation bytes 0 B
224
+ [ALLOC_CACHEOBJECTS] Dual Thread Allocator
225
+ Peak main deferred allocation count 0
226
+ [ALLOC_BUCKET]
227
+ Large Block size 4.0 MB
228
+ Used Block count 1
229
+ Peak Allocated bytes 0.9 MB
230
+ [ALLOC_CACHEOBJECTS_MAIN]
231
+ Peak usage frame count: [0.5 MB-1.0 MB]: 2041 frames
232
+ Requested Block Size 4.0 MB
233
+ Peak Block count 1
234
+ Peak Allocated memory 0.6 MB
235
+ Peak Large allocation bytes 0 B
236
+ [ALLOC_CACHEOBJECTS_THREAD]
237
+ Peak usage frame count: [0.5 MB-1.0 MB]: 2040 frames, [2.0 MB-4.0 MB]: 1 frames
238
+ Requested Block Size 4.0 MB
239
+ Peak Block count 1
240
+ Peak Allocated memory 2.2 MB
241
+ Peak Large allocation bytes 0 B
242
+ [ALLOC_TYPETREE] Dual Thread Allocator
243
+ Peak main deferred allocation count 0
244
+ [ALLOC_BUCKET]
245
+ Large Block size 4.0 MB
246
+ Used Block count 1
247
+ Peak Allocated bytes 0.9 MB
248
+ [ALLOC_TYPETREE_MAIN]
249
+ Peak usage frame count: [0-1.0 KB]: 2041 frames
250
+ Requested Block Size 2.0 MB
251
+ Peak Block count 1
252
+ Peak Allocated memory 1.0 KB
253
+ Peak Large allocation bytes 0 B
254
+ [ALLOC_TYPETREE_THREAD]
255
+ Peak usage frame count: [1.0 KB-2.0 KB]: 2041 frames
256
+ Requested Block Size 2.0 MB
257
+ Peak Block count 1
258
+ Peak Allocated memory 1.7 KB
259
+ 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": 1.328168511390686,
6
+ "min": 1.328168511390686,
7
+ "max": 1.6884623765945435,
8
+ "count": 8
9
+ },
10
+ "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 13543.333984375,
12
+ "min": 8617.912109375,
13
+ "max": 16077.0927734375,
14
+ "count": 8
15
+ },
16
+ "SnowballTarget.Step.mean": {
17
+ "value": 199984.0,
18
+ "min": 129992.0,
19
+ "max": 199984.0,
20
+ "count": 8
21
+ },
22
+ "SnowballTarget.Step.sum": {
23
+ "value": 199984.0,
24
+ "min": 129992.0,
25
+ "max": 199984.0,
26
+ "count": 8
27
+ },
28
+ "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 12.007621765136719,
30
+ "min": 9.204183578491211,
31
+ "max": 12.007621765136719,
32
+ "count": 8
33
+ },
34
+ "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2341.486328125,
36
+ "min": 736.334716796875,
37
+ "max": 2408.5126953125,
38
+ "count": 8
39
+ },
40
+ "SnowballTarget.Environment.EpisodeLength.mean": {
41
+ "value": 199.0,
42
+ "min": 199.0,
43
+ "max": 199.0,
44
+ "count": 8
45
+ },
46
+ "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 8756.0,
48
+ "min": 4378.0,
49
+ "max": 10945.0,
50
+ "count": 8
51
+ },
52
+ "SnowballTarget.Environment.CumulativeReward.mean": {
53
+ "value": 24.90909090909091,
54
+ "min": 22.26923076923077,
55
+ "max": 25.09090909090909,
56
+ "count": 8
57
+ },
58
+ "SnowballTarget.Environment.CumulativeReward.sum": {
59
+ "value": 1096.0,
60
+ "min": 315.0,
61
+ "max": 1380.0,
62
+ "count": 8
63
+ },
64
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
+ "value": 24.90909090909091,
66
+ "min": 22.26923076923077,
67
+ "max": 25.09090909090909,
68
+ "count": 8
69
+ },
70
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
+ "value": 1096.0,
72
+ "min": 315.0,
73
+ "max": 1380.0,
74
+ "count": 8
75
+ },
76
+ "SnowballTarget.Losses.PolicyLoss.mean": {
77
+ "value": 0.0660925427240299,
78
+ "min": 0.06426675086982096,
79
+ "max": 0.07081947505842917,
80
+ "count": 8
81
+ },
82
+ "SnowballTarget.Losses.PolicyLoss.sum": {
83
+ "value": 0.1321850854480598,
84
+ "min": 0.06426675086982096,
85
+ "max": 0.21118983861661572,
86
+ "count": 8
87
+ },
88
+ "SnowballTarget.Losses.ValueLoss.mean": {
89
+ "value": 0.20692843010320383,
90
+ "min": 0.20692843010320383,
91
+ "max": 0.24697394416187748,
92
+ "count": 8
93
+ },
94
+ "SnowballTarget.Losses.ValueLoss.sum": {
95
+ "value": 0.41385686020640766,
96
+ "min": 0.24697394416187748,
97
+ "max": 0.7215860576314084,
98
+ "count": 8
99
+ },
100
+ "SnowballTarget.Policy.LearningRate.mean": {
101
+ "value": 1.5580096883999985e-05,
102
+ "min": 1.5580096883999985e-05,
103
+ "max": 0.00017508006498399996,
104
+ "count": 8
105
+ },
106
+ "SnowballTarget.Policy.LearningRate.sum": {
107
+ "value": 3.116019376799997e-05,
108
+ "min": 3.116019376799997e-05,
109
+ "max": 0.00031716013656799994,
110
+ "count": 8
111
+ },
112
+ "SnowballTarget.Policy.Epsilon.mean": {
113
+ "value": 0.10311599999999999,
114
+ "min": 0.10311599999999999,
115
+ "max": 0.13501600000000002,
116
+ "count": 8
117
+ },
118
+ "SnowballTarget.Policy.Epsilon.sum": {
119
+ "value": 0.20623199999999997,
120
+ "min": 0.13501600000000002,
121
+ "max": 0.35224799999999995,
122
+ "count": 8
123
+ },
124
+ "SnowballTarget.Policy.Beta.mean": {
125
+ "value": 0.00016548839999999982,
126
+ "min": 0.00016548839999999982,
127
+ "max": 0.0017572984000000002,
128
+ "count": 8
129
+ },
130
+ "SnowballTarget.Policy.Beta.sum": {
131
+ "value": 0.00033097679999999965,
132
+ "min": 0.00033097679999999965,
133
+ "max": 0.0031852568000000003,
134
+ "count": 8
135
+ },
136
+ "SnowballTarget.IsTraining.mean": {
137
+ "value": 1.0,
138
+ "min": 1.0,
139
+ "max": 1.0,
140
+ "count": 8
141
+ },
142
+ "SnowballTarget.IsTraining.sum": {
143
+ "value": 1.0,
144
+ "min": 1.0,
145
+ "max": 1.0,
146
+ "count": 8
147
+ }
148
+ },
149
+ "metadata": {
150
+ "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1673952566",
152
+ "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
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 --resume",
154
+ "mlagents_version": "0.29.0.dev0",
155
+ "mlagents_envs_version": "0.29.0.dev0",
156
+ "communication_protocol_version": "1.5.0",
157
+ "pytorch_version": "1.8.1+cu102",
158
+ "numpy_version": "1.21.6",
159
+ "end_time_seconds": "1673952749"
160
+ },
161
+ "total": 183.44327956799998,
162
+ "count": 1,
163
+ "self": 0.38690096899995297,
164
+ "children": {
165
+ "run_training.setup": {
166
+ "total": 0.11145493399999395,
167
+ "count": 1,
168
+ "self": 0.11145493399999395
169
+ },
170
+ "TrainerController.start_learning": {
171
+ "total": 182.94492366500003,
172
+ "count": 1,
173
+ "self": 0.21657700199239116,
174
+ "children": {
175
+ "TrainerController._reset_env": {
176
+ "total": 6.098904782999853,
177
+ "count": 1,
178
+ "self": 6.098904782999853
179
+ },
180
+ "TrainerController.advance": {
181
+ "total": 176.50930990300776,
182
+ "count": 6802,
183
+ "self": 0.10504824200597795,
184
+ "children": {
185
+ "env_step": {
186
+ "total": 176.40426166100178,
187
+ "count": 6802,
188
+ "self": 128.7467460399805,
189
+ "children": {
190
+ "SubprocessEnvManager._take_step": {
191
+ "total": 47.54695558100752,
192
+ "count": 6802,
193
+ "self": 0.506306558009328,
194
+ "children": {
195
+ "TorchPolicy.evaluate": {
196
+ "total": 47.040649022998196,
197
+ "count": 6802,
198
+ "self": 10.416061452002168,
199
+ "children": {
200
+ "TorchPolicy.sample_actions": {
201
+ "total": 36.62458757099603,
202
+ "count": 6802,
203
+ "self": 36.62458757099603
204
+ }
205
+ }
206
+ }
207
+ }
208
+ },
209
+ "workers": {
210
+ "total": 0.11056004001375186,
211
+ "count": 6802,
212
+ "self": 0.0,
213
+ "children": {
214
+ "worker_root": {
215
+ "total": 182.45991812600755,
216
+ "count": 6802,
217
+ "is_parallel": true,
218
+ "self": 99.34957993200283,
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": 0.0017766769999525422,
228
+ "count": 1,
229
+ "is_parallel": true,
230
+ "self": 0.0005972249998649204,
231
+ "children": {
232
+ "_process_rank_one_or_two_observation": {
233
+ "total": 0.0011794520000876219,
234
+ "count": 10,
235
+ "is_parallel": true,
236
+ "self": 0.0011794520000876219
237
+ }
238
+ }
239
+ },
240
+ "UnityEnvironment.step": {
241
+ "total": 0.04119560999993155,
242
+ "count": 1,
243
+ "is_parallel": true,
244
+ "self": 0.0005442609999590786,
245
+ "children": {
246
+ "UnityEnvironment._generate_step_input": {
247
+ "total": 0.0003620250001858949,
248
+ "count": 1,
249
+ "is_parallel": true,
250
+ "self": 0.0003620250001858949
251
+ },
252
+ "communicator.exchange": {
253
+ "total": 0.03838651499995649,
254
+ "count": 1,
255
+ "is_parallel": true,
256
+ "self": 0.03838651499995649
257
+ },
258
+ "steps_from_proto": {
259
+ "total": 0.0019028089998300857,
260
+ "count": 1,
261
+ "is_parallel": true,
262
+ "self": 0.0004959179996149032,
263
+ "children": {
264
+ "_process_rank_one_or_two_observation": {
265
+ "total": 0.0014068910002151824,
266
+ "count": 10,
267
+ "is_parallel": true,
268
+ "self": 0.0014068910002151824
269
+ }
270
+ }
271
+ }
272
+ }
273
+ }
274
+ }
275
+ },
276
+ "UnityEnvironment.step": {
277
+ "total": 83.11033819400473,
278
+ "count": 6801,
279
+ "is_parallel": true,
280
+ "self": 3.0566140609896593,
281
+ "children": {
282
+ "UnityEnvironment._generate_step_input": {
283
+ "total": 1.8816506050081898,
284
+ "count": 6801,
285
+ "is_parallel": true,
286
+ "self": 1.8816506050081898
287
+ },
288
+ "communicator.exchange": {
289
+ "total": 67.01576045099796,
290
+ "count": 6801,
291
+ "is_parallel": true,
292
+ "self": 67.01576045099796
293
+ },
294
+ "steps_from_proto": {
295
+ "total": 11.156313077008917,
296
+ "count": 6801,
297
+ "is_parallel": true,
298
+ "self": 2.3903602610273538,
299
+ "children": {
300
+ "_process_rank_one_or_two_observation": {
301
+ "total": 8.765952815981564,
302
+ "count": 68010,
303
+ "is_parallel": true,
304
+ "self": 8.765952815981564
305
+ }
306
+ }
307
+ }
308
+ }
309
+ }
310
+ }
311
+ }
312
+ }
313
+ }
314
+ }
315
+ }
316
+ }
317
+ },
318
+ "trainer_threads": {
319
+ "total": 4.488800004764926e-05,
320
+ "count": 1,
321
+ "self": 4.488800004764926e-05,
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": 175.15293219802106,
331
+ "count": 160925,
332
+ "is_parallel": true,
333
+ "self": 4.2363684649897095,
334
+ "children": {
335
+ "process_trajectory": {
336
+ "total": 110.09657355303102,
337
+ "count": 160925,
338
+ "is_parallel": true,
339
+ "self": 109.6392081670308,
340
+ "children": {
341
+ "RLTrainer._checkpoint": {
342
+ "total": 0.4573653860002196,
343
+ "count": 2,
344
+ "is_parallel": true,
345
+ "self": 0.4573653860002196
346
+ }
347
+ }
348
+ },
349
+ "_update_policy": {
350
+ "total": 60.81999018000033,
351
+ "count": 16,
352
+ "is_parallel": true,
353
+ "self": 24.29063101199381,
354
+ "children": {
355
+ "TorchPPOOptimizer.update": {
356
+ "total": 36.52935916800652,
357
+ "count": 2715,
358
+ "is_parallel": true,
359
+ "self": 36.52935916800652
360
+ }
361
+ }
362
+ }
363
+ }
364
+ }
365
+ }
366
+ }
367
+ }
368
+ },
369
+ "TrainerController._save_models": {
370
+ "total": 0.12008708899998055,
371
+ "count": 1,
372
+ "self": 0.0010848530000657775,
373
+ "children": {
374
+ "RLTrainer._checkpoint": {
375
+ "total": 0.11900223599991477,
376
+ "count": 1,
377
+ "self": 0.11900223599991477
378
+ }
379
+ }
380
+ }
381
+ }
382
+ }
383
+ }
384
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "SnowballTarget": {
3
+ "checkpoints": [
4
+ {
5
+ "steps": 49936,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 12.272727272727273,
8
+ "creation_time": 1673952364.9932427,
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": 20.363636363636363,
17
+ "creation_time": 1673952484.5346525,
18
+ "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 126104,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-125592.onnx",
25
+ "reward": 22.318181818181817,
26
+ "creation_time": 1673952546.7718027,
27
+ "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-125592.pt"
29
+ ]
30
+ },
31
+ {
32
+ "steps": 149984,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
34
+ "reward": 24.136363636363637,
35
+ "creation_time": 1673952631.1833293,
36
+ "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 199984,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
43
+ "reward": 24.636363636363637,
44
+ "creation_time": 1673952749.3621132,
45
+ "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 200368,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200368.onnx",
52
+ "reward": 24.636363636363637,
53
+ "creation_time": 1673952749.5381525,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200368.pt"
56
+ ]
57
+ }
58
+ ],
59
+ "final_checkpoint": {
60
+ "steps": 200368,
61
+ "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
62
+ "reward": 24.636363636363637,
63
+ "creation_time": 1673952749.5381525,
64
+ "auxillary_file_paths": [
65
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200368.pt"
66
+ ]
67
+ }
68
+ },
69
+ "metadata": {
70
+ "stats_format_version": "0.3.0",
71
+ "mlagents_version": "0.29.0.dev0",
72
+ "torch_version": "1.8.1+cu102"
73
+ }
74
+ }