Pyramids-ppo-1 / run_logs /timers.json
DoctorRobotnik's picture
First commit
0b63ff1
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.6766155362129211,
"min": 0.6572026610374451,
"max": 1.423122763633728,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 20081.94921875,
"min": 19631.95703125,
"max": 43171.8515625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989975.0,
"min": 29952.0,
"max": 989975.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989975.0,
"min": 29952.0,
"max": 989975.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.08718821406364441,
"min": -0.10258835554122925,
"max": 0.3340301215648651,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 21.622676849365234,
"min": -24.82638168334961,
"max": 87.5158920288086,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -2.506495714187622,
"min": -2.506495714187622,
"max": 0.37579649686813354,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -621.6109619140625,
"min": -621.6109619140625,
"max": 89.06376647949219,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07175339503252567,
"min": 0.06426785871662404,
"max": 0.07328574997466207,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0045475304553595,
"min": 0.476311751783507,
"max": 1.0624096134173062,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 1.9164532147503153,
"min": 0.0005044481577996672,
"max": 1.9164532147503153,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 26.830345006504412,
"min": 0.007062274209195341,
"max": 26.830345006504412,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.670026014785716e-06,
"min": 7.670026014785716e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010738036420700003,
"min": 0.00010738036420700003,
"max": 0.0035075384308206003,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10255664285714286,
"min": 0.10255664285714286,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.435793,
"min": 1.3691136000000002,
"max": 2.5691794,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002654086214285715,
"min": 0.0002654086214285715,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0037157207000000007,
"min": 0.0037157207000000007,
"max": 0.11694102206,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.008343641646206379,
"min": 0.008343641646206379,
"max": 0.4376717209815979,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.11681097745895386,
"min": 0.11681097745895386,
"max": 3.06370210647583,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 791.675,
"min": 506.537037037037,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31667.0,
"min": 15984.0,
"max": 33176.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.3580599559471011,
"min": -1.0000000521540642,
"max": 1.1970740548438497,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 14.322398237884045,
"min": -32.000001668930054,
"max": 74.34699853509665,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.3580599559471011,
"min": -1.0000000521540642,
"max": 1.1970740548438497,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 14.322398237884045,
"min": -32.000001668930054,
"max": 74.34699853509665,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.07008112093026284,
"min": 0.047034447628431265,
"max": 9.101165883243084,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.8032448372105137,
"min": 2.370920064044185,
"max": 145.61865413188934,
"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": "1673635938",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "0.29.0.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": "1673637895"
},
"total": 1957.602624481,
"count": 1,
"self": 0.4397261780000008,
"children": {
"run_training.setup": {
"total": 0.10244814199995744,
"count": 1,
"self": 0.10244814199995744
},
"TrainerController.start_learning": {
"total": 1957.060450161,
"count": 1,
"self": 1.2948300279508658,
"children": {
"TrainerController._reset_env": {
"total": 6.278697254999997,
"count": 1,
"self": 6.278697254999997
},
"TrainerController.advance": {
"total": 1949.394694459049,
"count": 63394,
"self": 1.2757816201190053,
"children": {
"env_step": {
"total": 1281.9357476419395,
"count": 63394,
"self": 1175.7571032029716,
"children": {
"SubprocessEnvManager._take_step": {
"total": 105.3867207679616,
"count": 63394,
"self": 4.321939768916309,
"children": {
"TorchPolicy.evaluate": {
"total": 101.0647809990453,
"count": 62542,
"self": 34.18940943703319,
"children": {
"TorchPolicy.sample_actions": {
"total": 66.8753715620121,
"count": 62542,
"self": 66.8753715620121
}
}
}
}
},
"workers": {
"total": 0.791923671006316,
"count": 63394,
"self": 0.0,
"children": {
"worker_root": {
"total": 1952.4092322509612,
"count": 63394,
"is_parallel": true,
"self": 877.7905723979463,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019478750000416767,
"count": 1,
"is_parallel": true,
"self": 0.0008314019999033917,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001116473000138285,
"count": 8,
"is_parallel": true,
"self": 0.001116473000138285
}
}
},
"UnityEnvironment.step": {
"total": 0.047540064000031634,
"count": 1,
"is_parallel": true,
"self": 0.00048510399983570096,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004972930000803899,
"count": 1,
"is_parallel": true,
"self": 0.0004972930000803899
},
"communicator.exchange": {
"total": 0.04480020300002252,
"count": 1,
"is_parallel": true,
"self": 0.04480020300002252
},
"steps_from_proto": {
"total": 0.001757464000093023,
"count": 1,
"is_parallel": true,
"self": 0.0004414909999468364,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013159730001461867,
"count": 8,
"is_parallel": true,
"self": 0.0013159730001461867
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1074.6186598530148,
"count": 63393,
"is_parallel": true,
"self": 28.24721357201952,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.33706038203036,
"count": 63393,
"is_parallel": true,
"self": 24.33706038203036
},
"communicator.exchange": {
"total": 915.971670909044,
"count": 63393,
"is_parallel": true,
"self": 915.971670909044
},
"steps_from_proto": {
"total": 106.062714989921,
"count": 63393,
"is_parallel": true,
"self": 23.313166395955932,
"children": {
"_process_rank_one_or_two_observation": {
"total": 82.74954859396507,
"count": 507144,
"is_parallel": true,
"self": 82.74954859396507
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 666.1831651969906,
"count": 63394,
"self": 2.292422194992241,
"children": {
"process_trajectory": {
"total": 151.69469667499857,
"count": 63394,
"self": 151.4954409759987,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1992556989998775,
"count": 2,
"self": 0.1992556989998775
}
}
},
"_update_policy": {
"total": 512.1960463269997,
"count": 449,
"self": 197.93188096602285,
"children": {
"TorchPPOOptimizer.update": {
"total": 314.2641653609769,
"count": 22809,
"self": 314.2641653609769
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3409999155555852e-06,
"count": 1,
"self": 1.3409999155555852e-06
},
"TrainerController._save_models": {
"total": 0.09222707800017815,
"count": 1,
"self": 0.0014728010000908398,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09075427700008731,
"count": 1,
"self": 0.09075427700008731
}
}
}
}
}
}
}