APLunch commited on
Commit
120de1e
1 Parent(s): c99169d

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: APLunch/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:b511857232ed39369fded38d093bd01871171621e5d108163e519a75f3d2a5e1
3
+ size 650646
SnowballTarget/SnowballTarget-149984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2b836db82ca5e93ad2cf0c661c0b9e8ea72687f062dac60a1885750cd78f682
3
+ size 650646
SnowballTarget/SnowballTarget-149984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49578f2387a227694cb10fb30167757bec724813dbb1bb8359a8d01e7cf305c6
3
+ size 3850075
SnowballTarget/SnowballTarget-199984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f51b2475d2c6711977a272a733e0888cb728e874bb304e3136464790c65b7aa
3
+ size 650646
SnowballTarget/SnowballTarget-199984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54ff55aab59295d5f44c18a2dd59e88ec32cc797ed1fbdb34536b4a1274ab54c
3
+ size 3850075
SnowballTarget/SnowballTarget-249944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:087dd42f8b78cced235fe06d8064be0d25759aa1b791258156e304fbd3bb7808
3
+ size 650646
SnowballTarget/SnowballTarget-249944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:888a3204e0b76a635fdf14653fee2373159457c559a2d23c98e6975f6c0f42e7
3
+ size 3850075
SnowballTarget/SnowballTarget-299968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca0b940e90a193206660f2aafc331e7f5f72c114bf70fb246b0c8ee415f49ca7
3
+ size 650646
SnowballTarget/SnowballTarget-299968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7afba72ce5c517ed62b56fb072ffcbb8fb8a5514e1221cf0c4c6e1321e65a00
3
+ size 3850075
SnowballTarget/SnowballTarget-349992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0002dbac6e3786492d13953ebe37fcd9712b4295e069679307eecf8b1e8314a7
3
+ size 650646
SnowballTarget/SnowballTarget-349992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69b88d903b1903d7930d70b0e862ae4dc3fa216b8f47d05568129dd929ac41e1
3
+ size 3850075
SnowballTarget/SnowballTarget-399992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fa7b9f57d2f9fdd5a8831f640de0ccb83f8a1d89d41151ed72ae52265c3eed2
3
+ size 650646
SnowballTarget/SnowballTarget-399992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0818916501b11e08c09b9c41724740b2ee45943781131d274ca2a0b944132b96
3
+ size 3850075
SnowballTarget/SnowballTarget-449952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fae79dfa0b0f51e9014865ed7b445b99100a7b2bc5d93b78a5353a45fa3be221
3
+ size 650646
SnowballTarget/SnowballTarget-449952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aeb5666958f51d9c9fc354697f03a722a7b04803fe16f4974c08dbf319e1082
3
+ size 3850075
SnowballTarget/SnowballTarget-499976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b511857232ed39369fded38d093bd01871171621e5d108163e519a75f3d2a5e1
3
+ size 650646
SnowballTarget/SnowballTarget-499976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aa928346b8bb6e9a16a5896fcb25a0029dde07f7fd0d48a47b96d32ec3ac0d4
3
+ size 3850075
SnowballTarget/SnowballTarget-500104.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b511857232ed39369fded38d093bd01871171621e5d108163e519a75f3d2a5e1
3
+ size 650646
SnowballTarget/SnowballTarget-500104.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e99588ecf908884237bfd0c75564f0b07a7f601052e86c89ef6e8d9b6a832589
3
+ size 3850075
SnowballTarget/SnowballTarget-99960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf566372b39b08af2c8e571ee19e27eaafe35a2db2a183f85ff8fee61141a5a5
3
+ size 650646
SnowballTarget/SnowballTarget-99960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88bb37a1884668d4389c90b7edf43247d05cb810b39c33bab0af35a7c6155427
3
+ size 3850000
SnowballTarget/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8708a27e4c278afacdf9db567642df5b023b80037997c87f9a52b7715f565f3b
3
+ size 3849250
SnowballTarget/events.out.tfevents.1713755675.d56161c322ba.10512.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59fc855bfbfa2b8c492ecda6e4d706200aea3bd800de1408b6526505262ff469
3
+ size 1114
SnowballTarget/events.out.tfevents.1713755894.d56161c322ba.11477.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39c2a948691bf944e7484864a3974ce5d55369369abe42af29024cb047d5e5e2
3
+ size 47846
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": 500000, "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": true, "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: 500000
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: true
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 0.083 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: 0.658171 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]: 13415 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 41
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]: 10815 frames, [8.0 MB-16.0 MB]: 2828 frames
176
+ Requested Block Size 16.0 MB
177
+ Peak Block count 1
178
+ Peak Allocated memory 10.0 MB
179
+ Peak Large allocation bytes 0 B
180
+ [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 13643 frames
182
+ Requested Block Size 16.0 MB
183
+ Peak Block count 1
184
+ Peak Allocated memory 17.4 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]: 12153 frames, [64.0 KB-128.0 KB]: 1490 frames
214
+ Requested Block Size 16.0 MB
215
+ Peak Block count 1
216
+ Peak Allocated memory 66.8 KB
217
+ Peak Large allocation bytes 0 B
218
+ [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 13643 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]: 13643 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]: 13642 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]: 13643 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]: 13643 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 +1,377 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.7050622701644897,
6
+ "min": 0.7050622701644897,
7
+ "max": 2.8619587421417236,
8
+ "count": 50
9
+ },
10
+ "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 6817.2470703125,
12
+ "min": 6817.2470703125,
13
+ "max": 29309.318359375,
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": 13.77859878540039,
30
+ "min": 0.38366881012916565,
31
+ "max": 13.784880638122559,
32
+ "count": 50
33
+ },
34
+ "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2824.61279296875,
36
+ "min": 74.43174743652344,
37
+ "max": 2824.61279296875,
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.Losses.PolicyLoss.mean": {
53
+ "value": 0.0697863629494118,
54
+ "min": 0.06103006867953238,
55
+ "max": 0.07554256657552767,
56
+ "count": 50
57
+ },
58
+ "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.34893181474705903,
60
+ "min": 0.2493930504492977,
61
+ "max": 0.37771283287763835,
62
+ "count": 50
63
+ },
64
+ "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.16576103445361642,
66
+ "min": 0.10228879785612591,
67
+ "max": 0.2810851101781808,
68
+ "count": 50
69
+ },
70
+ "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.8288051722680821,
72
+ "min": 0.40915519142450363,
73
+ "max": 1.405425550890904,
74
+ "count": 50
75
+ },
76
+ "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 3.0528989824000028e-06,
78
+ "min": 3.0528989824000028e-06,
79
+ "max": 0.00029675280108239997,
80
+ "count": 50
81
+ },
82
+ "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 1.5264494912000015e-05,
84
+ "min": 1.5264494912000015e-05,
85
+ "max": 0.001454064015312,
86
+ "count": 50
87
+ },
88
+ "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10101760000000001,
90
+ "min": 0.10101760000000001,
91
+ "max": 0.19891759999999997,
92
+ "count": 50
93
+ },
94
+ "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.5050880000000001,
96
+ "min": 0.41199040000000003,
97
+ "max": 0.984688,
98
+ "count": 50
99
+ },
100
+ "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 6.0778240000000044e-05,
102
+ "min": 6.0778240000000044e-05,
103
+ "max": 0.00494598824,
104
+ "count": 50
105
+ },
106
+ "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.0003038912000000002,
108
+ "min": 0.0003038912000000002,
109
+ "max": 0.0242359312,
110
+ "count": 50
111
+ },
112
+ "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 27.09090909090909,
114
+ "min": 3.022727272727273,
115
+ "max": 27.22222222222222,
116
+ "count": 50
117
+ },
118
+ "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1490.0,
120
+ "min": 133.0,
121
+ "max": 1490.0,
122
+ "count": 50
123
+ },
124
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 27.09090909090909,
126
+ "min": 3.022727272727273,
127
+ "max": 27.22222222222222,
128
+ "count": 50
129
+ },
130
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1490.0,
132
+ "min": 133.0,
133
+ "max": 1490.0,
134
+ "count": 50
135
+ },
136
+ "SnowballTarget.IsTraining.mean": {
137
+ "value": 1.0,
138
+ "min": 1.0,
139
+ "max": 1.0,
140
+ "count": 50
141
+ },
142
+ "SnowballTarget.IsTraining.sum": {
143
+ "value": 1.0,
144
+ "min": 1.0,
145
+ "max": 1.0,
146
+ "count": 50
147
+ }
148
+ },
149
+ "metadata": {
150
+ "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1713755893",
152
+ "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
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": "1713756922"
160
+ },
161
+ "total": 1029.065024473,
162
+ "count": 1,
163
+ "self": 0.4303295839999919,
164
+ "children": {
165
+ "run_training.setup": {
166
+ "total": 0.0499855060002119,
167
+ "count": 1,
168
+ "self": 0.0499855060002119
169
+ },
170
+ "TrainerController.start_learning": {
171
+ "total": 1028.5847093829998,
172
+ "count": 1,
173
+ "self": 1.2475098059903758,
174
+ "children": {
175
+ "TrainerController._reset_env": {
176
+ "total": 1.8984900469999957,
177
+ "count": 1,
178
+ "self": 1.8984900469999957
179
+ },
180
+ "TrainerController.advance": {
181
+ "total": 1025.3477508910096,
182
+ "count": 45474,
183
+ "self": 0.5957604879963583,
184
+ "children": {
185
+ "env_step": {
186
+ "total": 1024.7519904030132,
187
+ "count": 45474,
188
+ "self": 655.1423231740359,
189
+ "children": {
190
+ "SubprocessEnvManager._take_step": {
191
+ "total": 368.9562461170117,
192
+ "count": 45474,
193
+ "self": 3.3754614180870703,
194
+ "children": {
195
+ "TorchPolicy.evaluate": {
196
+ "total": 365.5807846989246,
197
+ "count": 45474,
198
+ "self": 365.5807846989246
199
+ }
200
+ }
201
+ },
202
+ "workers": {
203
+ "total": 0.6534211119655993,
204
+ "count": 45474,
205
+ "self": 0.0,
206
+ "children": {
207
+ "worker_root": {
208
+ "total": 1026.0563821750065,
209
+ "count": 45474,
210
+ "is_parallel": true,
211
+ "self": 513.3324466010185,
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": 0.002136040000095818,
221
+ "count": 1,
222
+ "is_parallel": true,
223
+ "self": 0.0006323219995465479,
224
+ "children": {
225
+ "_process_rank_one_or_two_observation": {
226
+ "total": 0.00150371800054927,
227
+ "count": 10,
228
+ "is_parallel": true,
229
+ "self": 0.00150371800054927
230
+ }
231
+ }
232
+ },
233
+ "UnityEnvironment.step": {
234
+ "total": 0.06122114300023895,
235
+ "count": 1,
236
+ "is_parallel": true,
237
+ "self": 0.0007813479996912065,
238
+ "children": {
239
+ "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00038281300021481,
241
+ "count": 1,
242
+ "is_parallel": true,
243
+ "self": 0.00038281300021481
244
+ },
245
+ "communicator.exchange": {
246
+ "total": 0.057974640000338695,
247
+ "count": 1,
248
+ "is_parallel": true,
249
+ "self": 0.057974640000338695
250
+ },
251
+ "steps_from_proto": {
252
+ "total": 0.0020823419999942416,
253
+ "count": 1,
254
+ "is_parallel": true,
255
+ "self": 0.0005318999992596218,
256
+ "children": {
257
+ "_process_rank_one_or_two_observation": {
258
+ "total": 0.0015504420007346198,
259
+ "count": 10,
260
+ "is_parallel": true,
261
+ "self": 0.0015504420007346198
262
+ }
263
+ }
264
+ }
265
+ }
266
+ }
267
+ }
268
+ },
269
+ "UnityEnvironment.step": {
270
+ "total": 512.723935573988,
271
+ "count": 45473,
272
+ "is_parallel": true,
273
+ "self": 24.294358876990373,
274
+ "children": {
275
+ "UnityEnvironment._generate_step_input": {
276
+ "total": 12.698900528976083,
277
+ "count": 45473,
278
+ "is_parallel": true,
279
+ "self": 12.698900528976083
280
+ },
281
+ "communicator.exchange": {
282
+ "total": 397.27121901300734,
283
+ "count": 45473,
284
+ "is_parallel": true,
285
+ "self": 397.27121901300734
286
+ },
287
+ "steps_from_proto": {
288
+ "total": 78.4594571550142,
289
+ "count": 45473,
290
+ "is_parallel": true,
291
+ "self": 14.235531979853477,
292
+ "children": {
293
+ "_process_rank_one_or_two_observation": {
294
+ "total": 64.22392517516073,
295
+ "count": 454730,
296
+ "is_parallel": true,
297
+ "self": 64.22392517516073
298
+ }
299
+ }
300
+ }
301
+ }
302
+ }
303
+ }
304
+ }
305
+ }
306
+ }
307
+ }
308
+ }
309
+ }
310
+ },
311
+ "trainer_threads": {
312
+ "total": 0.00015396199978567893,
313
+ "count": 1,
314
+ "self": 0.00015396199978567893,
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": 1012.3589760440541,
324
+ "count": 1594238,
325
+ "is_parallel": true,
326
+ "self": 32.25760287538969,
327
+ "children": {
328
+ "process_trajectory": {
329
+ "total": 557.6758756986669,
330
+ "count": 1594238,
331
+ "is_parallel": true,
332
+ "self": 556.4826696096661,
333
+ "children": {
334
+ "RLTrainer._checkpoint": {
335
+ "total": 1.193206089000796,
336
+ "count": 10,
337
+ "is_parallel": true,
338
+ "self": 1.193206089000796
339
+ }
340
+ }
341
+ },
342
+ "_update_policy": {
343
+ "total": 422.4254974699975,
344
+ "count": 227,
345
+ "is_parallel": true,
346
+ "self": 119.07021200201507,
347
+ "children": {
348
+ "TorchPPOOptimizer.update": {
349
+ "total": 303.3552854679824,
350
+ "count": 11574,
351
+ "is_parallel": true,
352
+ "self": 303.3552854679824
353
+ }
354
+ }
355
+ }
356
+ }
357
+ }
358
+ }
359
+ }
360
+ }
361
+ },
362
+ "TrainerController._save_models": {
363
+ "total": 0.09080467700005102,
364
+ "count": 1,
365
+ "self": 0.0011834860001727066,
366
+ "children": {
367
+ "RLTrainer._checkpoint": {
368
+ "total": 0.08962119099987831,
369
+ "count": 1,
370
+ "self": 0.08962119099987831
371
+ }
372
+ }
373
+ }
374
+ }
375
+ }
376
+ }
377
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "stats_format_version": "0.3.0",
4
+ "mlagents_version": "1.1.0.dev0",
5
+ "torch_version": "2.2.1+cu121"
6
+ },
7
+ "SnowballTarget": {
8
+ "checkpoints": [
9
+ {
10
+ "steps": 99960,
11
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
12
+ "reward": 22.272727272727273,
13
+ "creation_time": 1713756102.5162458,
14
+ "auxillary_file_paths": [
15
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
16
+ ]
17
+ },
18
+ {
19
+ "steps": 149984,
20
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
21
+ "reward": 23.454545454545453,
22
+ "creation_time": 1713756205.5760412,
23
+ "auxillary_file_paths": [
24
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
25
+ ]
26
+ },
27
+ {
28
+ "steps": 199984,
29
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
30
+ "reward": 25.181818181818183,
31
+ "creation_time": 1713756309.5784678,
32
+ "auxillary_file_paths": [
33
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
34
+ ]
35
+ },
36
+ {
37
+ "steps": 249944,
38
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.onnx",
39
+ "reward": 25.90909090909091,
40
+ "creation_time": 1713756411.6754107,
41
+ "auxillary_file_paths": [
42
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.pt"
43
+ ]
44
+ },
45
+ {
46
+ "steps": 299968,
47
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
48
+ "reward": 25.636363636363637,
49
+ "creation_time": 1713756515.5451283,
50
+ "auxillary_file_paths": [
51
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.pt"
52
+ ]
53
+ },
54
+ {
55
+ "steps": 349992,
56
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.onnx",
57
+ "reward": 26.363636363636363,
58
+ "creation_time": 1713756617.2733657,
59
+ "auxillary_file_paths": [
60
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.pt"
61
+ ]
62
+ },
63
+ {
64
+ "steps": 399992,
65
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.onnx",
66
+ "reward": 25.727272727272727,
67
+ "creation_time": 1713756718.5039818,
68
+ "auxillary_file_paths": [
69
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.pt"
70
+ ]
71
+ },
72
+ {
73
+ "steps": 449952,
74
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.onnx",
75
+ "reward": 26.454545454545453,
76
+ "creation_time": 1713756820.167297,
77
+ "auxillary_file_paths": [
78
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.pt"
79
+ ]
80
+ },
81
+ {
82
+ "steps": 499976,
83
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.onnx",
84
+ "reward": 27.272727272727273,
85
+ "creation_time": 1713756921.9604635,
86
+ "auxillary_file_paths": [
87
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.pt"
88
+ ]
89
+ },
90
+ {
91
+ "steps": 500104,
92
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.onnx",
93
+ "reward": 27.272727272727273,
94
+ "creation_time": 1713756922.070023,
95
+ "auxillary_file_paths": [
96
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.pt"
97
+ ]
98
+ }
99
+ ],
100
+ "final_checkpoint": {
101
+ "steps": 500104,
102
+ "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
103
+ "reward": 27.272727272727273,
104
+ "creation_time": 1713756922.070023,
105
+ "auxillary_file_paths": [
106
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.pt"
107
+ ]
108
+ }
109
+ }
110
+ }