PyramidsRND / run_logs /timers.json
Amiko's picture
Test MLAgent
31f9d2c
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.34306779503822327,
"min": 0.33792629837989807,
"max": 1.4229812622070312,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 10253.6103515625,
"min": 10213.484375,
"max": 43167.55859375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989897.0,
"min": 29999.0,
"max": 989897.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989897.0,
"min": 29999.0,
"max": 989897.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6559207439422607,
"min": -0.08983538299798965,
"max": 0.6975507736206055,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 186.93740844726562,
"min": -21.650327682495117,
"max": 199.50827026367188,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.02124886028468609,
"min": -4.6796347305644304e-05,
"max": 0.37116318941116333,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 6.055925369262695,
"min": -0.01165229082107544,
"max": 88.33683776855469,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07044055880743101,
"min": 0.06521518054257502,
"max": 0.07652427307504428,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9861678233040342,
"min": 0.6121941846003542,
"max": 1.051170549801706,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015041637269730148,
"min": 0.00025990155824236736,
"max": 0.01741500302298283,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21058292177622207,
"min": 0.003378720257150776,
"max": 0.2438100423217596,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.533868917314285e-06,
"min": 7.533868917314285e-06,
"max": 0.0002948491142169625,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010547416484239998,
"min": 0.00010547416484239998,
"max": 0.0036341497886167987,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10251125714285715,
"min": 0.10251125714285715,
"max": 0.1982830375,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4351576000000001,
"min": 1.4351576000000001,
"max": 2.6113832000000006,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026087458857142854,
"min": 0.00026087458857142854,
"max": 0.009828475446249998,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036522442399999993,
"min": 0.0036522442399999993,
"max": 0.12115718168,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.012351734563708305,
"min": 0.012274319306015968,
"max": 0.4807741940021515,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.17292428016662598,
"min": 0.17292428016662598,
"max": 3.846193552017212,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 304.680412371134,
"min": 265.3693693693694,
"max": 991.40625,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29554.0,
"min": 16286.0,
"max": 33613.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.654070081784553,
"min": -0.9998194063382764,
"max": 1.7310917306383815,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 160.44479793310165,
"min": -30.99440159648657,
"max": 193.6625982373953,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.654070081784553,
"min": -0.9998194063382764,
"max": 1.7310917306383815,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 160.44479793310165,
"min": -30.99440159648657,
"max": 193.6625982373953,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03903063018260207,
"min": 0.03461205147100332,
"max": 9.380820733659407,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.7859711277124006,
"min": 3.774734306585742,
"max": 159.47395247220993,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1676400178",
"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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsRND --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": "1676402457"
},
"total": 2278.731857847,
"count": 1,
"self": 0.47419845500007796,
"children": {
"run_training.setup": {
"total": 0.11126216599996042,
"count": 1,
"self": 0.11126216599996042
},
"TrainerController.start_learning": {
"total": 2278.146397226,
"count": 1,
"self": 1.2585914991582285,
"children": {
"TrainerController._reset_env": {
"total": 7.090030713000033,
"count": 1,
"self": 7.090030713000033
},
"TrainerController.advance": {
"total": 2269.7139833238416,
"count": 64244,
"self": 1.3686263148301805,
"children": {
"env_step": {
"total": 1532.3639787259956,
"count": 64244,
"self": 1422.4782739440088,
"children": {
"SubprocessEnvManager._take_step": {
"total": 109.09527956499346,
"count": 64244,
"self": 4.462386612029832,
"children": {
"TorchPolicy.evaluate": {
"total": 104.63289295296363,
"count": 62548,
"self": 35.204047125948364,
"children": {
"TorchPolicy.sample_actions": {
"total": 69.42884582701527,
"count": 62548,
"self": 69.42884582701527
}
}
}
}
},
"workers": {
"total": 0.7904252169932988,
"count": 64244,
"self": 0.0,
"children": {
"worker_root": {
"total": 2273.3072149530276,
"count": 64244,
"is_parallel": true,
"self": 962.5992886750184,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018387770001027093,
"count": 1,
"is_parallel": true,
"self": 0.0007393580003736133,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001099418999729096,
"count": 8,
"is_parallel": true,
"self": 0.001099418999729096
}
}
},
"UnityEnvironment.step": {
"total": 0.046086102999879586,
"count": 1,
"is_parallel": true,
"self": 0.0005201870001201314,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00045518299998548173,
"count": 1,
"is_parallel": true,
"self": 0.00045518299998548173
},
"communicator.exchange": {
"total": 0.04345832299986796,
"count": 1,
"is_parallel": true,
"self": 0.04345832299986796
},
"steps_from_proto": {
"total": 0.0016524099999060127,
"count": 1,
"is_parallel": true,
"self": 0.00040729399961492163,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001245116000291091,
"count": 8,
"is_parallel": true,
"self": 0.001245116000291091
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1310.7079262780092,
"count": 64243,
"is_parallel": true,
"self": 30.969371205950665,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.46813734200441,
"count": 64243,
"is_parallel": true,
"self": 22.46813734200441
},
"communicator.exchange": {
"total": 1156.8344953060398,
"count": 64243,
"is_parallel": true,
"self": 1156.8344953060398
},
"steps_from_proto": {
"total": 100.43592242401428,
"count": 64243,
"is_parallel": true,
"self": 21.823167135161157,
"children": {
"_process_rank_one_or_two_observation": {
"total": 78.61275528885312,
"count": 513944,
"is_parallel": true,
"self": 78.61275528885312
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 735.9813782830158,
"count": 64244,
"self": 2.4906925560351283,
"children": {
"process_trajectory": {
"total": 160.44571696897856,
"count": 64244,
"self": 160.26132525497815,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18439171400041232,
"count": 2,
"self": 0.18439171400041232
}
}
},
"_update_policy": {
"total": 573.0449687580021,
"count": 457,
"self": 221.94481570201992,
"children": {
"TorchPPOOptimizer.update": {
"total": 351.1001530559822,
"count": 22788,
"self": 351.1001530559822
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.669994713272899e-07,
"count": 1,
"self": 8.669994713272899e-07
},
"TrainerController._save_models": {
"total": 0.08379082300052687,
"count": 1,
"self": 0.0014473740002358682,
"children": {
"RLTrainer._checkpoint": {
"total": 0.082343449000291,
"count": 1,
"self": 0.082343449000291
}
}
}
}
}
}
}