asuzuki's picture
Default params
b525980
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8125110864639282,
"min": 0.8125110864639282,
"max": 2.867156505584717,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7766.79345703125,
"min": 7766.79345703125,
"max": 29362.55078125,
"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": 12.551424980163574,
"min": 0.3338642716407776,
"max": 12.551424980163574,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2447.52783203125,
"min": 64.76966857910156,
"max": 2547.35693359375,
"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": 0.06775050015644143,
"min": 0.06353750943124076,
"max": 0.07314143516671132,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27100200062576574,
"min": 0.26453466443590334,
"max": 0.3657071758335566,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20530853435104968,
"min": 0.10148170780659854,
"max": 0.2802498653969344,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8212341374041987,
"min": 0.40592683122639417,
"max": 1.305111322332831,
"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": 25.25,
"min": 3.0681818181818183,
"max": 25.25,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1111.0,
"min": 135.0,
"max": 1368.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.25,
"min": 3.0681818181818183,
"max": 25.25,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1111.0,
"min": 135.0,
"max": 1368.0,
"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": "1676066275",
"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 /content/ml-agents/config/ppo/SnowballTarget.yaml --env=/content/ml-agents/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": "1.21.6",
"end_time_seconds": "1676066725"
},
"total": 449.2723719769999,
"count": 1,
"self": 0.432452572000102,
"children": {
"run_training.setup": {
"total": 0.179529329999923,
"count": 1,
"self": 0.179529329999923
},
"TrainerController.start_learning": {
"total": 448.6603900749999,
"count": 1,
"self": 0.5113178610122304,
"children": {
"TrainerController._reset_env": {
"total": 9.413752078000016,
"count": 1,
"self": 9.413752078000016
},
"TrainerController.advance": {
"total": 438.62138488598725,
"count": 18202,
"self": 0.2600246559702555,
"children": {
"env_step": {
"total": 438.361360230017,
"count": 18202,
"self": 301.5895223350119,
"children": {
"SubprocessEnvManager._take_step": {
"total": 136.50495595497728,
"count": 18202,
"self": 1.402779940967548,
"children": {
"TorchPolicy.evaluate": {
"total": 135.10217601400973,
"count": 18202,
"self": 30.34390158803535,
"children": {
"TorchPolicy.sample_actions": {
"total": 104.75827442597438,
"count": 18202,
"self": 104.75827442597438
}
}
}
}
},
"workers": {
"total": 0.2668819400278153,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 447.2514535040234,
"count": 18202,
"is_parallel": true,
"self": 216.73531419203505,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008544118999907369,
"count": 1,
"is_parallel": true,
"self": 0.0038118439999834663,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004732274999923902,
"count": 10,
"is_parallel": true,
"self": 0.004732274999923902
}
}
},
"UnityEnvironment.step": {
"total": 0.03613967799992679,
"count": 1,
"is_parallel": true,
"self": 0.0005311820000315493,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002915689999554161,
"count": 1,
"is_parallel": true,
"self": 0.0002915689999554161
},
"communicator.exchange": {
"total": 0.03352640200000678,
"count": 1,
"is_parallel": true,
"self": 0.03352640200000678
},
"steps_from_proto": {
"total": 0.0017905249999330408,
"count": 1,
"is_parallel": true,
"self": 0.000411267999879783,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013792570000532578,
"count": 10,
"is_parallel": true,
"self": 0.0013792570000532578
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 230.51613931198835,
"count": 18201,
"is_parallel": true,
"self": 9.32443063198616,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.081458811969469,
"count": 18201,
"is_parallel": true,
"self": 5.081458811969469
},
"communicator.exchange": {
"total": 183.04186676098948,
"count": 18201,
"is_parallel": true,
"self": 183.04186676098948
},
"steps_from_proto": {
"total": 33.068383107043246,
"count": 18201,
"is_parallel": true,
"self": 6.838481040058241,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.229902066985005,
"count": 182010,
"is_parallel": true,
"self": 26.229902066985005
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.596300014891312e-05,
"count": 1,
"self": 9.596300014891312e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 435.4199951089813,
"count": 393290,
"is_parallel": true,
"self": 9.829630480774085,
"children": {
"process_trajectory": {
"total": 248.99589278920485,
"count": 393290,
"is_parallel": true,
"self": 248.2905804772049,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7053123119999327,
"count": 4,
"is_parallel": true,
"self": 0.7053123119999327
}
}
},
"_update_policy": {
"total": 176.59447183900238,
"count": 90,
"is_parallel": true,
"self": 61.08907313801501,
"children": {
"TorchPPOOptimizer.update": {
"total": 115.50539870098737,
"count": 4587,
"is_parallel": true,
"self": 115.50539870098737
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11383928700024626,
"count": 1,
"self": 0.0008229120003306889,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11301637499991557,
"count": 1,
"self": 0.11301637499991557
}
}
}
}
}
}
}