Schoolar's picture
Start_model
252b69c
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8479135036468506,
"min": 0.8479135036468506,
"max": 2.85935378074646,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8123.859375,
"min": 8123.859375,
"max": 29282.642578125,
"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": 13.09673023223877,
"min": 0.3229563236236572,
"max": 13.236286163330078,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2553.8623046875,
"min": 62.653526306152344,
"max": 2700.202392578125,
"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.Losses.PolicyLoss.mean": {
"value": 0.07247368372376442,
"min": 0.06045743289652426,
"max": 0.07365899186868988,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2898947348950577,
"min": 0.24182973158609705,
"max": 0.36646940288055163,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22034890263103968,
"min": 0.11552755227632017,
"max": 0.2797866183168748,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8813956105241587,
"min": 0.46211020910528067,
"max": 1.3989330915843738,
"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.CumulativeReward.mean": {
"value": 25.363636363636363,
"min": 3.590909090909091,
"max": 26.236363636363638,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1116.0,
"min": 158.0,
"max": 1443.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.363636363636363,
"min": 3.590909090909091,
"max": 26.236363636363638,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1116.0,
"min": 158.0,
"max": 1443.0,
"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": "1677431856",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.22.4",
"end_time_seconds": "1677432325"
},
"total": 469.3531149060001,
"count": 1,
"self": 0.6901469400002043,
"children": {
"run_training.setup": {
"total": 0.1106621169999471,
"count": 1,
"self": 0.1106621169999471
},
"TrainerController.start_learning": {
"total": 468.55230584899994,
"count": 1,
"self": 0.5789831369913827,
"children": {
"TrainerController._reset_env": {
"total": 9.755024954999953,
"count": 1,
"self": 9.755024954999953
},
"TrainerController.advance": {
"total": 457.9792367590086,
"count": 18211,
"self": 0.2849749760026725,
"children": {
"env_step": {
"total": 457.6942617830059,
"count": 18211,
"self": 317.53921989100695,
"children": {
"SubprocessEnvManager._take_step": {
"total": 139.87735543700876,
"count": 18211,
"self": 1.510703102998832,
"children": {
"TorchPolicy.evaluate": {
"total": 138.36665233400993,
"count": 18211,
"self": 31.515825310008495,
"children": {
"TorchPolicy.sample_actions": {
"total": 106.85082702400143,
"count": 18211,
"self": 106.85082702400143
}
}
}
}
},
"workers": {
"total": 0.27768645499020295,
"count": 18211,
"self": 0.0,
"children": {
"worker_root": {
"total": 466.84891645100515,
"count": 18211,
"is_parallel": true,
"self": 228.60536032699156,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005959253000014542,
"count": 1,
"is_parallel": true,
"self": 0.004067177999786509,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018920750002280329,
"count": 10,
"is_parallel": true,
"self": 0.0018920750002280329
}
}
},
"UnityEnvironment.step": {
"total": 0.06048624299990024,
"count": 1,
"is_parallel": true,
"self": 0.0005357149999554167,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046826899995267013,
"count": 1,
"is_parallel": true,
"self": 0.00046826899995267013
},
"communicator.exchange": {
"total": 0.05767390899995917,
"count": 1,
"is_parallel": true,
"self": 0.05767390899995917
},
"steps_from_proto": {
"total": 0.0018083500000329877,
"count": 1,
"is_parallel": true,
"self": 0.000416939000047023,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013914109999859647,
"count": 10,
"is_parallel": true,
"self": 0.0013914109999859647
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 238.2435561240136,
"count": 18210,
"is_parallel": true,
"self": 9.412290877006967,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.3724227410081085,
"count": 18210,
"is_parallel": true,
"self": 5.3724227410081085
},
"communicator.exchange": {
"total": 191.37062067599766,
"count": 18210,
"is_parallel": true,
"self": 191.37062067599766
},
"steps_from_proto": {
"total": 32.08822183000086,
"count": 18210,
"is_parallel": true,
"self": 7.104000310013362,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.9842215199875,
"count": 182100,
"is_parallel": true,
"self": 24.9842215199875
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001835500002016488,
"count": 1,
"self": 0.0001835500002016488,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 454.80834780999646,
"count": 393006,
"is_parallel": true,
"self": 9.607940090019042,
"children": {
"process_trajectory": {
"total": 261.08781276497746,
"count": 393006,
"is_parallel": true,
"self": 259.90966327597766,
"children": {
"RLTrainer._checkpoint": {
"total": 1.178149488999793,
"count": 4,
"is_parallel": true,
"self": 1.178149488999793
}
}
},
"_update_policy": {
"total": 184.11259495499996,
"count": 90,
"is_parallel": true,
"self": 62.65751539399707,
"children": {
"TorchPPOOptimizer.update": {
"total": 121.45507956100289,
"count": 4587,
"is_parallel": true,
"self": 121.45507956100289
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.23887744799981192,
"count": 1,
"self": 0.001456919999782258,
"children": {
"RLTrainer._checkpoint": {
"total": 0.23742052800002966,
"count": 1,
"self": 0.23742052800002966
}
}
}
}
}
}
}