hwting's picture
First Push
e425e5d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.839619517326355,
"min": 0.8253195881843567,
"max": 2.8579723834991455,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7979.744140625,
"min": 7979.744140625,
"max": 29174.181640625,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.378495216369629,
"min": 0.4476465582847595,
"max": 13.378495216369629,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2608.806640625,
"min": 86.84342956542969,
"max": 2705.97607421875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06783712903221634,
"min": 0.061873014971349095,
"max": 0.07516086707371013,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27134851612886535,
"min": 0.2578956640853921,
"max": 0.3758043353685506,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18601390328623502,
"min": 0.13329229385628566,
"max": 0.328822505167302,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7440556131449401,
"min": 0.5331691754251426,
"max": 1.4941328515609107,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.727272727272727,
"min": 4.0,
"max": 26.272727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1132.0,
"min": 176.0,
"max": 1444.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.727272727272727,
"min": 4.0,
"max": 26.272727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1132.0,
"min": 176.0,
"max": 1444.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1737432710",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/hwting/anaconda3/envs/rl/bin/mlagents-learn ./SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1737432957"
},
"total": 246.5397319560002,
"count": 1,
"self": 0.21812426600035906,
"children": {
"run_training.setup": {
"total": 0.016835274999948524,
"count": 1,
"self": 0.016835274999948524
},
"TrainerController.start_learning": {
"total": 246.3047724149999,
"count": 1,
"self": 0.2910446419971322,
"children": {
"TrainerController._reset_env": {
"total": 1.5563008640001499,
"count": 1,
"self": 1.5563008640001499
},
"TrainerController.advance": {
"total": 244.4119245010029,
"count": 18192,
"self": 0.2692179910061441,
"children": {
"env_step": {
"total": 174.09237209899698,
"count": 18192,
"self": 127.94992434799474,
"children": {
"SubprocessEnvManager._take_step": {
"total": 45.95720267399497,
"count": 18192,
"self": 0.7792767300015839,
"children": {
"TorchPolicy.evaluate": {
"total": 45.17792594399339,
"count": 18192,
"self": 45.17792594399339
}
}
},
"workers": {
"total": 0.18524507700726645,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 245.81526583999198,
"count": 18192,
"is_parallel": true,
"self": 136.52884938597663,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011627149999640096,
"count": 1,
"is_parallel": true,
"self": 0.00031357999955616833,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008491350004078413,
"count": 10,
"is_parallel": true,
"self": 0.0008491350004078413
}
}
},
"UnityEnvironment.step": {
"total": 0.015795585999967443,
"count": 1,
"is_parallel": true,
"self": 0.0002067290001832589,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00027149900006406824,
"count": 1,
"is_parallel": true,
"self": 0.00027149900006406824
},
"communicator.exchange": {
"total": 0.014658102999874245,
"count": 1,
"is_parallel": true,
"self": 0.014658102999874245
},
"steps_from_proto": {
"total": 0.0006592549998458708,
"count": 1,
"is_parallel": true,
"self": 0.00014601799944102822,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005132370004048425,
"count": 10,
"is_parallel": true,
"self": 0.0005132370004048425
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 109.28641645401535,
"count": 18191,
"is_parallel": true,
"self": 4.793272886011891,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.6975049470013346,
"count": 18191,
"is_parallel": true,
"self": 3.6975049470013346
},
"communicator.exchange": {
"total": 86.36194317501418,
"count": 18191,
"is_parallel": true,
"self": 86.36194317501418
},
"steps_from_proto": {
"total": 14.43369544598795,
"count": 18191,
"is_parallel": true,
"self": 2.93736481503106,
"children": {
"_process_rank_one_or_two_observation": {
"total": 11.49633063095689,
"count": 181910,
"is_parallel": true,
"self": 11.49633063095689
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 70.05033441099977,
"count": 18192,
"self": 0.38300438798046343,
"children": {
"process_trajectory": {
"total": 15.570853505020068,
"count": 18192,
"self": 15.364981002020158,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20587250299990956,
"count": 4,
"self": 0.20587250299990956
}
}
},
"_update_policy": {
"total": 54.096476517999236,
"count": 90,
"self": 21.361156281989224,
"children": {
"TorchPPOOptimizer.update": {
"total": 32.73532023601001,
"count": 4587,
"self": 32.73532023601001
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.909998890274437e-07,
"count": 1,
"self": 5.909998890274437e-07
},
"TrainerController._save_models": {
"total": 0.045501816999831135,
"count": 1,
"self": 0.0006089129997235432,
"children": {
"RLTrainer._checkpoint": {
"total": 0.04489290400010759,
"count": 1,
"self": 0.04489290400010759
}
}
}
}
}
}
}