ppo-Pyramids / run_logs /timers.json
HazemHM's picture
First Push
47ea991
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.47563430666923523,
"min": 0.47563430666923523,
"max": 1.4564183950424194,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 14375.5712890625,
"min": 14375.5712890625,
"max": 44181.91015625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989995.0,
"min": 29876.0,
"max": 989995.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989995.0,
"min": 29876.0,
"max": 989995.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.08883735537528992,
"min": -0.12027698010206223,
"max": 0.24023815989494324,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 21.942827224731445,
"min": -28.986751556396484,
"max": 61.02049255371094,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0008622928871773183,
"min": -0.0012597617460414767,
"max": 0.39244329929351807,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 0.21298635005950928,
"min": -0.3199794888496399,
"max": 93.00906372070312,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07123764542038083,
"min": 0.06459933799845272,
"max": 0.07202546846770853,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9973270358853316,
"min": 0.6361696113207717,
"max": 1.0769325104831973,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.005212601856180785,
"min": 0.00015535760897572316,
"max": 0.010748283252583804,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.072976425986531,
"min": 0.002019648916684401,
"max": 0.15047596553617326,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.752097416e-06,
"min": 7.752097416e-06,
"max": 0.00029486430171189997,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.000108529363824,
"min": 0.000108529363824,
"max": 0.003633028688990499,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10258400000000001,
"min": 0.10258400000000001,
"max": 0.19828809999999997,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4361760000000001,
"min": 1.4361760000000001,
"max": 2.6110095,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002681416,
"min": 0.0002681416,
"max": 0.00982898119,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0037539824,
"min": 0.0037539824,
"max": 0.12111984905,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.00793372467160225,
"min": 0.00793372467160225,
"max": 0.36963120102882385,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.11107214540243149,
"min": 0.11107214540243149,
"max": 3.326680898666382,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 762.1951219512196,
"min": 611.2745098039215,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31250.0,
"min": 16419.0,
"max": 32811.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.2131804545841566,
"min": -0.9997500516474247,
"max": 0.9840817878192122,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 8.74039863795042,
"min": -31.99200165271759,
"max": 48.819398403167725,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.2131804545841566,
"min": -0.9997500516474247,
"max": 0.9840817878192122,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 8.74039863795042,
"min": -31.99200165271759,
"max": 48.819398403167725,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.06351880095444801,
"min": 0.05508329216950098,
"max": 8.069510455517207,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.6042708391323686,
"min": 2.515879717815551,
"max": 137.18167774379253,
"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": "1696028276",
"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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1696030353"
},
"total": 2076.5423971269997,
"count": 1,
"self": 0.5252886649996071,
"children": {
"run_training.setup": {
"total": 0.04098327799965773,
"count": 1,
"self": 0.04098327799965773
},
"TrainerController.start_learning": {
"total": 2075.9761251840005,
"count": 1,
"self": 1.3751292350580115,
"children": {
"TrainerController._reset_env": {
"total": 4.292325912000251,
"count": 1,
"self": 4.292325912000251
},
"TrainerController.advance": {
"total": 2070.2117000329417,
"count": 63435,
"self": 1.415372491918788,
"children": {
"env_step": {
"total": 1415.3371657419875,
"count": 63435,
"self": 1303.3286863119197,
"children": {
"SubprocessEnvManager._take_step": {
"total": 111.16765632513489,
"count": 63435,
"self": 5.048529597157994,
"children": {
"TorchPolicy.evaluate": {
"total": 106.11912672797689,
"count": 62578,
"self": 106.11912672797689
}
}
},
"workers": {
"total": 0.8408231049329515,
"count": 63435,
"self": 0.0,
"children": {
"worker_root": {
"total": 2070.732809205912,
"count": 63435,
"is_parallel": true,
"self": 885.0592534870402,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001982086999760213,
"count": 1,
"is_parallel": true,
"self": 0.0006539099990732211,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001328177000686992,
"count": 8,
"is_parallel": true,
"self": 0.001328177000686992
}
}
},
"UnityEnvironment.step": {
"total": 0.10752852399991752,
"count": 1,
"is_parallel": true,
"self": 0.0006149650007500895,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005946769997535739,
"count": 1,
"is_parallel": true,
"self": 0.0005946769997535739
},
"communicator.exchange": {
"total": 0.09556907599971964,
"count": 1,
"is_parallel": true,
"self": 0.09556907599971964
},
"steps_from_proto": {
"total": 0.010749805999694217,
"count": 1,
"is_parallel": true,
"self": 0.008088802000202122,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0026610039994920953,
"count": 8,
"is_parallel": true,
"self": 0.0026610039994920953
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1185.6735557188717,
"count": 63434,
"is_parallel": true,
"self": 34.265084819955064,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.208996559068964,
"count": 63434,
"is_parallel": true,
"self": 24.208996559068964
},
"communicator.exchange": {
"total": 1017.2859972599531,
"count": 63434,
"is_parallel": true,
"self": 1017.2859972599531
},
"steps_from_proto": {
"total": 109.91347707989462,
"count": 63434,
"is_parallel": true,
"self": 21.583072417527546,
"children": {
"_process_rank_one_or_two_observation": {
"total": 88.33040466236707,
"count": 507472,
"is_parallel": true,
"self": 88.33040466236707
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 653.4591617990354,
"count": 63435,
"self": 2.6276223908971588,
"children": {
"process_trajectory": {
"total": 114.05323331313275,
"count": 63435,
"self": 113.84551126013275,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2077220529999977,
"count": 2,
"self": 0.2077220529999977
}
}
},
"_update_policy": {
"total": 536.7783060950055,
"count": 456,
"self": 351.040621830964,
"children": {
"TorchPPOOptimizer.update": {
"total": 185.7376842640415,
"count": 22740,
"self": 185.7376842640415
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.750001481734216e-07,
"count": 1,
"self": 9.750001481734216e-07
},
"TrainerController._save_models": {
"total": 0.09696902900032,
"count": 1,
"self": 0.0015073820004545269,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09546164699986548,
"count": 1,
"self": 0.09546164699986548
}
}
}
}
}
}
}