lbaeriswyl commited on
Commit
a62cd35
1 Parent(s): 15fd83b

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: lbaeriswyl/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 sha256:2f2760ca49e7ec9f12a26a3e233415d7f6c12a16acd7ff6ce256bd417f116daf
3
+ size 914755
SnowballTarget/SnowballTarget-149984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1f9c0a8db7de9d29c8657be799f2b60cbc0b1c752688843219d23248b7a06dc
3
+ size 914755
SnowballTarget/SnowballTarget-149984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4e4de3a87c593f27199a7f26d4d984e647355a77382bb8bc899ce44c503a36c
3
+ size 5434379
SnowballTarget/SnowballTarget-199984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a2c28ccd76d79c63dbc93f5f35d19742fc4897f71ba19cd97fad7e3c2753a35
3
+ size 914755
SnowballTarget/SnowballTarget-199984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a343f886d5feef4fd194a612c5565b8fa523817691267966e049b43efa454055
3
+ size 5434379
SnowballTarget/SnowballTarget-249944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c7c8adb3cb5ff8f62732f3c11532c189bfdf97e215004294d3dab95c85790dd
3
+ size 914755
SnowballTarget/SnowballTarget-249944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73eef4999c4979a6ca517bfec9c992f1e8d7f471361705e27c274852036e68aa
3
+ size 5434379
SnowballTarget/SnowballTarget-299968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eea004eb2a5d8d779e4b8f639a6c70dcda4f8b734758e93764c0318a30e09857
3
+ size 914755
SnowballTarget/SnowballTarget-299968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec07daa430740942907609d964100e01a53e07d1c951a1abb9203eb3a45e2cdb
3
+ size 5434379
SnowballTarget/SnowballTarget-349992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ad02bd22d26688a6ee7a9d0563e361c931530c27c1b9083d751c9721928e0be
3
+ size 914755
SnowballTarget/SnowballTarget-349992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a39d68a0b068b13a2994083585a68b208d6679c68d5e9f5106b3f8fe59c7df8
3
+ size 5434379
SnowballTarget/SnowballTarget-399992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bc298908d853ef2d26f21060ae811eab4b817cf6eec42c3eab3c4c5df7cd30a
3
+ size 914755
SnowballTarget/SnowballTarget-399992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:604e9f3e03c2f0b144282058afd0c4d4c90592e825dab9870f7ef9292aa2add9
3
+ size 5434379
SnowballTarget/SnowballTarget-449952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:938f04a0204b448ef124d62cc0d83dd15c3bc6150cfedcea4e70c0e3b7eb25b2
3
+ size 914755
SnowballTarget/SnowballTarget-449952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55de5a0423c38fc37a98e9825e32bd5886fab6c7f0b0ec616c0b411765ce400e
3
+ size 5434379
SnowballTarget/SnowballTarget-499976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f2760ca49e7ec9f12a26a3e233415d7f6c12a16acd7ff6ce256bd417f116daf
3
+ size 914755
SnowballTarget/SnowballTarget-499976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97b1dbca4e3239419968f84f5e7ab0d86551971e387ab6c92c5f2dc9567bccbd
3
+ size 5434379
SnowballTarget/SnowballTarget-500104.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f2760ca49e7ec9f12a26a3e233415d7f6c12a16acd7ff6ce256bd417f116daf
3
+ size 914755
SnowballTarget/SnowballTarget-500104.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cded7950473d2b455d1727dbb296d156ebe8f5bf484f5b3eeff866698b7717f
3
+ size 5434379
SnowballTarget/SnowballTarget-99960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:915c8a2b42ec4fe03219b3c2b7afc6d6aa119209ed734653a56209607d7a2fe8
3
+ size 914755
SnowballTarget/SnowballTarget-99960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31e64d32e872abe4baa50951422cae49606041b64d5b90b381c1a36b36de8edc
3
+ size 5434288
SnowballTarget/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c465d623e3de5c635736c4f154379b85b7f4b213c5778ed04184318cf4806ac
3
+ size 5433378
SnowballTarget/events.out.tfevents.1712005252.d34f7e47cfb6.11335.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4cc7e50c7405b0ce79a9e5c10cde25ede5307f509bc98ce0c5e9b3a5f7393f1
3
+ size 59115
config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 512, "buffer_size": 10240, "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": 3, "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": 500000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "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": "SnowballTarget2", "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: 512
7
+ buffer_size: 10240
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: 3
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: 500000
42
+ time_horizon: 64
43
+ summary_freq: 10000
44
+ threaded: false
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: SnowballTarget2
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 +1,259 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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:855:(parse_card) cannot find card '0'
14
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
15
+ ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
16
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
17
+ ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
18
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
19
+ ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
20
+ ALSA lib pcm.c:2664:(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:855:(parse_card) cannot find card '0'
24
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
25
+ ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
26
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
27
+ ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
28
+ ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
29
+ ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
30
+ ALSA lib pcm.c:2664:(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 0.085 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: 0.772145 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]: 13412 frames, [16.0 KB-32.0 KB]: 227 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 44
170
+ [ALLOC_BUCKET]
171
+ Large Block size 4.0 MB
172
+ Used Block count 1
173
+ Peak Allocated bytes 1.0 MB
174
+ [ALLOC_DEFAULT_MAIN]
175
+ Peak usage frame count: [4.0 MB-8.0 MB]: 13506 frames, [8.0 MB-16.0 MB]: 134 frames
176
+ Requested Block Size 16.0 MB
177
+ Peak Block count 1
178
+ Peak Allocated memory 9.5 MB
179
+ Peak Large allocation bytes 0 B
180
+ [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 13640 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 1.0 MB
212
+ [ALLOC_GFX_MAIN]
213
+ Peak usage frame count: [32.0 KB-64.0 KB]: 10699 frames, [64.0 KB-128.0 KB]: 2941 frames
214
+ Requested Block Size 16.0 MB
215
+ Peak Block count 1
216
+ Peak Allocated memory 67.3 KB
217
+ Peak Large allocation bytes 0 B
218
+ [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 13640 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 1.0 MB
230
+ [ALLOC_CACHEOBJECTS_MAIN]
231
+ Peak usage frame count: [0.5 MB-1.0 MB]: 13640 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]: 13639 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 1.0 MB
248
+ [ALLOC_TYPETREE_MAIN]
249
+ Peak usage frame count: [0-1.0 KB]: 13640 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]: 13640 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 +1,362 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 1.0747202634811401,
6
+ "min": 1.0697622299194336,
7
+ "max": 2.8903579711914062,
8
+ "count": 50
9
+ },
10
+ "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 10308.716796875,
12
+ "min": 10296.0625,
13
+ "max": 29613.673828125,
14
+ "count": 50
15
+ },
16
+ "SnowballTarget.Step.mean": {
17
+ "value": 499976.0,
18
+ "min": 9952.0,
19
+ "max": 499976.0,
20
+ "count": 50
21
+ },
22
+ "SnowballTarget.Step.sum": {
23
+ "value": 499976.0,
24
+ "min": 9952.0,
25
+ "max": 499976.0,
26
+ "count": 50
27
+ },
28
+ "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 12.507528305053711,
30
+ "min": -0.020696792751550674,
31
+ "max": 12.507528305053711,
32
+ "count": 50
33
+ },
34
+ "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2564.043212890625,
36
+ "min": -4.0151777267456055,
37
+ "max": 2564.043212890625,
38
+ "count": 50
39
+ },
40
+ "SnowballTarget.Environment.EpisodeLength.mean": {
41
+ "value": 199.0,
42
+ "min": 199.0,
43
+ "max": 199.0,
44
+ "count": 50
45
+ },
46
+ "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 10945.0,
48
+ "min": 8756.0,
49
+ "max": 10945.0,
50
+ "count": 50
51
+ },
52
+ "SnowballTarget.Environment.CumulativeReward.mean": {
53
+ "value": 25.727272727272727,
54
+ "min": 2.3863636363636362,
55
+ "max": 26.295454545454547,
56
+ "count": 50
57
+ },
58
+ "SnowballTarget.Environment.CumulativeReward.sum": {
59
+ "value": 1415.0,
60
+ "min": 105.0,
61
+ "max": 1420.0,
62
+ "count": 50
63
+ },
64
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
+ "value": 25.727272727272727,
66
+ "min": 2.3863636363636362,
67
+ "max": 26.295454545454547,
68
+ "count": 50
69
+ },
70
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
+ "value": 1415.0,
72
+ "min": 105.0,
73
+ "max": 1420.0,
74
+ "count": 50
75
+ },
76
+ "SnowballTarget.IsTraining.mean": {
77
+ "value": 1.0,
78
+ "min": 1.0,
79
+ "max": 1.0,
80
+ "count": 50
81
+ },
82
+ "SnowballTarget.IsTraining.sum": {
83
+ "value": 1.0,
84
+ "min": 1.0,
85
+ "max": 1.0,
86
+ "count": 50
87
+ },
88
+ "SnowballTarget.Losses.PolicyLoss.mean": {
89
+ "value": 0.03377082737715682,
90
+ "min": 0.03017920497513842,
91
+ "max": 0.041207270572340346,
92
+ "count": 47
93
+ },
94
+ "SnowballTarget.Losses.PolicyLoss.sum": {
95
+ "value": 0.03377082737715682,
96
+ "min": 0.03017920497513842,
97
+ "max": 0.041207270572340346,
98
+ "count": 47
99
+ },
100
+ "SnowballTarget.Losses.ValueLoss.mean": {
101
+ "value": 0.19784099807341893,
102
+ "min": 0.07500213319583544,
103
+ "max": 0.3213471621274948,
104
+ "count": 47
105
+ },
106
+ "SnowballTarget.Losses.ValueLoss.sum": {
107
+ "value": 0.19784099807341893,
108
+ "min": 0.07500213319583544,
109
+ "max": 0.3213471621274948,
110
+ "count": 47
111
+ },
112
+ "SnowballTarget.Policy.LearningRate.mean": {
113
+ "value": 5.21769826079999e-06,
114
+ "min": 5.21769826079999e-06,
115
+ "max": 0.00029345280218239997,
116
+ "count": 47
117
+ },
118
+ "SnowballTarget.Policy.LearningRate.sum": {
119
+ "value": 5.21769826079999e-06,
120
+ "min": 5.21769826079999e-06,
121
+ "max": 0.00029345280218239997,
122
+ "count": 47
123
+ },
124
+ "SnowballTarget.Policy.Epsilon.mean": {
125
+ "value": 0.1017392,
126
+ "min": 0.1017392,
127
+ "max": 0.19781760000000007,
128
+ "count": 47
129
+ },
130
+ "SnowballTarget.Policy.Epsilon.sum": {
131
+ "value": 0.1017392,
132
+ "min": 0.1017392,
133
+ "max": 0.19781760000000007,
134
+ "count": 47
135
+ },
136
+ "SnowballTarget.Policy.Beta.mean": {
137
+ "value": 9.678607999999981e-05,
138
+ "min": 9.678607999999981e-05,
139
+ "max": 0.004891098240000002,
140
+ "count": 47
141
+ },
142
+ "SnowballTarget.Policy.Beta.sum": {
143
+ "value": 9.678607999999981e-05,
144
+ "min": 9.678607999999981e-05,
145
+ "max": 0.004891098240000002,
146
+ "count": 47
147
+ }
148
+ },
149
+ "metadata": {
150
+ "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1712005252",
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=SnowballTarget2 --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": "2.2.1+cu121",
158
+ "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1712006259"
160
+ },
161
+ "total": 1006.7551526090001,
162
+ "count": 1,
163
+ "self": 0.4754103750001377,
164
+ "children": {
165
+ "run_training.setup": {
166
+ "total": 0.05499911400011115,
167
+ "count": 1,
168
+ "self": 0.05499911400011115
169
+ },
170
+ "TrainerController.start_learning": {
171
+ "total": 1006.2247431199999,
172
+ "count": 1,
173
+ "self": 1.0095576380076636,
174
+ "children": {
175
+ "TrainerController._reset_env": {
176
+ "total": 1.939219668000078,
177
+ "count": 1,
178
+ "self": 1.939219668000078
179
+ },
180
+ "TrainerController.advance": {
181
+ "total": 1003.1369046829923,
182
+ "count": 45464,
183
+ "self": 1.0276376590309155,
184
+ "children": {
185
+ "env_step": {
186
+ "total": 789.5192624559918,
187
+ "count": 45464,
188
+ "self": 623.9515064660118,
189
+ "children": {
190
+ "SubprocessEnvManager._take_step": {
191
+ "total": 164.9713538080223,
192
+ "count": 45464,
193
+ "self": 3.392746150009316,
194
+ "children": {
195
+ "TorchPolicy.evaluate": {
196
+ "total": 161.57860765801297,
197
+ "count": 45464,
198
+ "self": 161.57860765801297
199
+ }
200
+ }
201
+ },
202
+ "workers": {
203
+ "total": 0.5964021819577283,
204
+ "count": 45464,
205
+ "self": 0.0,
206
+ "children": {
207
+ "worker_root": {
208
+ "total": 1002.4944070989654,
209
+ "count": 45464,
210
+ "is_parallel": true,
211
+ "self": 457.6928957929681,
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": 0.002348888000142324,
221
+ "count": 1,
222
+ "is_parallel": true,
223
+ "self": 0.0007011549996605027,
224
+ "children": {
225
+ "_process_rank_one_or_two_observation": {
226
+ "total": 0.0016477330004818214,
227
+ "count": 10,
228
+ "is_parallel": true,
229
+ "self": 0.0016477330004818214
230
+ }
231
+ }
232
+ },
233
+ "UnityEnvironment.step": {
234
+ "total": 0.040288954000061494,
235
+ "count": 1,
236
+ "is_parallel": true,
237
+ "self": 0.000789435000569938,
238
+ "children": {
239
+ "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00048295699980371865,
241
+ "count": 1,
242
+ "is_parallel": true,
243
+ "self": 0.00048295699980371865
244
+ },
245
+ "communicator.exchange": {
246
+ "total": 0.03684074699958728,
247
+ "count": 1,
248
+ "is_parallel": true,
249
+ "self": 0.03684074699958728
250
+ },
251
+ "steps_from_proto": {
252
+ "total": 0.002175815000100556,
253
+ "count": 1,
254
+ "is_parallel": true,
255
+ "self": 0.00041472400016573374,
256
+ "children": {
257
+ "_process_rank_one_or_two_observation": {
258
+ "total": 0.0017610909999348223,
259
+ "count": 10,
260
+ "is_parallel": true,
261
+ "self": 0.0017610909999348223
262
+ }
263
+ }
264
+ }
265
+ }
266
+ }
267
+ }
268
+ },
269
+ "UnityEnvironment.step": {
270
+ "total": 544.8015113059973,
271
+ "count": 45463,
272
+ "is_parallel": true,
273
+ "self": 26.88873167888596,
274
+ "children": {
275
+ "UnityEnvironment._generate_step_input": {
276
+ "total": 14.982445247975647,
277
+ "count": 45463,
278
+ "is_parallel": true,
279
+ "self": 14.982445247975647
280
+ },
281
+ "communicator.exchange": {
282
+ "total": 415.06697272404836,
283
+ "count": 45463,
284
+ "is_parallel": true,
285
+ "self": 415.06697272404836
286
+ },
287
+ "steps_from_proto": {
288
+ "total": 87.86336165508737,
289
+ "count": 45463,
290
+ "is_parallel": true,
291
+ "self": 15.925444751959276,
292
+ "children": {
293
+ "_process_rank_one_or_two_observation": {
294
+ "total": 71.9379169031281,
295
+ "count": 454630,
296
+ "is_parallel": true,
297
+ "self": 71.9379169031281
298
+ }
299
+ }
300
+ }
301
+ }
302
+ }
303
+ }
304
+ }
305
+ }
306
+ }
307
+ }
308
+ },
309
+ "trainer_advance": {
310
+ "total": 212.59000456796957,
311
+ "count": 45464,
312
+ "self": 1.128955105949899,
313
+ "children": {
314
+ "process_trajectory": {
315
+ "total": 70.564516887021,
316
+ "count": 45464,
317
+ "self": 69.21331099902181,
318
+ "children": {
319
+ "RLTrainer._checkpoint": {
320
+ "total": 1.3512058879991855,
321
+ "count": 10,
322
+ "self": 1.3512058879991855
323
+ }
324
+ }
325
+ },
326
+ "_update_policy": {
327
+ "total": 140.89653257499867,
328
+ "count": 47,
329
+ "self": 99.6590631869908,
330
+ "children": {
331
+ "TorchPPOOptimizer.update": {
332
+ "total": 41.23746938800787,
333
+ "count": 2856,
334
+ "self": 41.23746938800787
335
+ }
336
+ }
337
+ }
338
+ }
339
+ }
340
+ }
341
+ },
342
+ "trainer_threads": {
343
+ "total": 1.421999968442833e-06,
344
+ "count": 1,
345
+ "self": 1.421999968442833e-06
346
+ },
347
+ "TrainerController._save_models": {
348
+ "total": 0.13905970899986642,
349
+ "count": 1,
350
+ "self": 0.0013036739997005498,
351
+ "children": {
352
+ "RLTrainer._checkpoint": {
353
+ "total": 0.13775603500016587,
354
+ "count": 1,
355
+ "self": 0.13775603500016587
356
+ }
357
+ }
358
+ }
359
+ }
360
+ }
361
+ }
362
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "SnowballTarget": {
3
+ "checkpoints": [
4
+ {
5
+ "steps": 99960,
6
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.onnx",
7
+ "reward": 12.242424242424242,
8
+ "creation_time": 1712005461.1449492,
9
+ "auxillary_file_paths": [
10
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.pt"
11
+ ]
12
+ },
13
+ {
14
+ "steps": 149984,
15
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
16
+ "reward": 15.272727272727273,
17
+ "creation_time": 1712005560.8134532,
18
+ "auxillary_file_paths": [
19
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 199984,
24
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
25
+ "reward": null,
26
+ "creation_time": 1712005661.4864366,
27
+ "auxillary_file_paths": [
28
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.pt"
29
+ ]
30
+ },
31
+ {
32
+ "steps": 249944,
33
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-249944.onnx",
34
+ "reward": 19.65909090909091,
35
+ "creation_time": 1712005758.11508,
36
+ "auxillary_file_paths": [
37
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-249944.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 299968,
42
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-299968.onnx",
43
+ "reward": 21.636363636363637,
44
+ "creation_time": 1712005859.2158036,
45
+ "auxillary_file_paths": [
46
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-299968.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 349992,
51
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-349992.onnx",
52
+ "reward": 23.606060606060606,
53
+ "creation_time": 1712005961.0949166,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-349992.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 399992,
60
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-399992.onnx",
61
+ "reward": 26.454545454545453,
62
+ "creation_time": 1712006060.3823366,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-399992.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 449952,
69
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-449952.onnx",
70
+ "reward": null,
71
+ "creation_time": 1712006160.8632898,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-449952.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 499976,
78
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-499976.onnx",
79
+ "reward": 25.613636363636363,
80
+ "creation_time": 1712006258.3812459,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-499976.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 500104,
87
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-500104.onnx",
88
+ "reward": 25.613636363636363,
89
+ "creation_time": 1712006258.5429263,
90
+ "auxillary_file_paths": [
91
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-500104.pt"
92
+ ]
93
+ }
94
+ ],
95
+ "final_checkpoint": {
96
+ "steps": 500104,
97
+ "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
98
+ "reward": 25.613636363636363,
99
+ "creation_time": 1712006258.5429263,
100
+ "auxillary_file_paths": [
101
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-500104.pt"
102
+ ]
103
+ }
104
+ },
105
+ "metadata": {
106
+ "stats_format_version": "0.3.0",
107
+ "mlagents_version": "1.1.0.dev0",
108
+ "torch_version": "2.2.1+cu121"
109
+ }
110
+ }