makwingchi's picture
First Push
68a9b72
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9226247668266296,
"min": 0.9008288383483887,
"max": 2.8716602325439453,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8819.3701171875,
"min": 8819.3701171875,
"max": 29440.26171875,
"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": 12.55770492553711,
"min": 0.3948158323764801,
"max": 12.55770492553711,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2448.75244140625,
"min": 76.59426879882812,
"max": 2531.4755859375,
"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": 0.06830834056916715,
"min": 0.06276629079480237,
"max": 0.07169812014648877,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2732333622766686,
"min": 0.25106516317920946,
"max": 0.3500800304432678,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22437103158410857,
"min": 0.11804419471517061,
"max": 0.27555059328967446,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8974841263364343,
"min": 0.47217677886068243,
"max": 1.3777529664483723,
"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": 25.181818181818183,
"min": 3.6363636363636362,
"max": 25.181818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1108.0,
"min": 160.0,
"max": 1363.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.181818181818183,
"min": 3.6363636363636362,
"max": 25.181818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1108.0,
"min": 160.0,
"max": 1363.0,
"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": "1699357392",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1699357916"
},
"total": 524.111636374,
"count": 1,
"self": 0.4246065009999711,
"children": {
"run_training.setup": {
"total": 0.06931183699998655,
"count": 1,
"self": 0.06931183699998655
},
"TrainerController.start_learning": {
"total": 523.617718036,
"count": 1,
"self": 0.7294910769994658,
"children": {
"TrainerController._reset_env": {
"total": 8.715056610999966,
"count": 1,
"self": 8.715056610999966
},
"TrainerController.advance": {
"total": 514.0848026850006,
"count": 18202,
"self": 0.3545278690023679,
"children": {
"env_step": {
"total": 513.7302748159982,
"count": 18202,
"self": 353.47905782800393,
"children": {
"SubprocessEnvManager._take_step": {
"total": 159.89979223199555,
"count": 18202,
"self": 1.6611749459985958,
"children": {
"TorchPolicy.evaluate": {
"total": 158.23861728599695,
"count": 18202,
"self": 158.23861728599695
}
}
},
"workers": {
"total": 0.35142475599872114,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 521.8989451379935,
"count": 18202,
"is_parallel": true,
"self": 252.37558998999327,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006778659000019616,
"count": 1,
"is_parallel": true,
"self": 0.004729629999928875,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020490290000907407,
"count": 10,
"is_parallel": true,
"self": 0.0020490290000907407
}
}
},
"UnityEnvironment.step": {
"total": 0.07397300799999584,
"count": 1,
"is_parallel": true,
"self": 0.0006962800000565039,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000497215999985201,
"count": 1,
"is_parallel": true,
"self": 0.000497215999985201
},
"communicator.exchange": {
"total": 0.07049082899999348,
"count": 1,
"is_parallel": true,
"self": 0.07049082899999348
},
"steps_from_proto": {
"total": 0.002288682999960656,
"count": 1,
"is_parallel": true,
"self": 0.00038528199996790136,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019034009999927548,
"count": 10,
"is_parallel": true,
"self": 0.0019034009999927548
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 269.5233551480002,
"count": 18201,
"is_parallel": true,
"self": 11.69004383799296,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.186750244006873,
"count": 18201,
"is_parallel": true,
"self": 6.186750244006873
},
"communicator.exchange": {
"total": 212.5125173589987,
"count": 18201,
"is_parallel": true,
"self": 212.5125173589987
},
"steps_from_proto": {
"total": 39.13404370700164,
"count": 18201,
"is_parallel": true,
"self": 7.8100788210141445,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.323964885987493,
"count": 182010,
"is_parallel": true,
"self": 31.323964885987493
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016869600005975371,
"count": 1,
"self": 0.00016869600005975371,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 509.44835807097513,
"count": 542742,
"is_parallel": true,
"self": 12.264576230988837,
"children": {
"process_trajectory": {
"total": 292.0645167219859,
"count": 542742,
"is_parallel": true,
"self": 291.50025971498604,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5642570069998669,
"count": 4,
"is_parallel": true,
"self": 0.5642570069998669
}
}
},
"_update_policy": {
"total": 205.11926511800038,
"count": 90,
"is_parallel": true,
"self": 62.99095603399843,
"children": {
"TorchPPOOptimizer.update": {
"total": 142.12830908400196,
"count": 4587,
"is_parallel": true,
"self": 142.12830908400196
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08819896700003937,
"count": 1,
"self": 0.0009560390000160623,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08724292800002331,
"count": 1,
"self": 0.08724292800002331
}
}
}
}
}
}
}