ppo-pyramids / run_logs /timers.json
innovation64's picture
First Push
715a570
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5371896624565125,
"min": 0.5371896624565125,
"max": 1.46788489818573,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 16021.14453125,
"min": 16021.14453125,
"max": 44529.7578125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989934.0,
"min": 29952.0,
"max": 989934.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989934.0,
"min": 29952.0,
"max": 989934.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.38914620876312256,
"min": -0.11585703492164612,
"max": 0.38914620876312256,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 103.12374877929688,
"min": -27.921545028686523,
"max": 103.12374877929688,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.19963739812374115,
"min": -0.4668425917625427,
"max": 0.36732155084609985,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 52.90391159057617,
"min": -119.97854614257812,
"max": 93.6669921875,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06539950461148222,
"min": 0.06401108294847377,
"max": 0.07467686926765432,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9155930645607511,
"min": 0.47432293358858374,
"max": 1.064791463591688,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015487894414877126,
"min": 0.0006119298642900092,
"max": 0.028204476641572097,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21683052180827977,
"min": 0.006731228507190102,
"max": 0.4081351114077466,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.775004551221427e-06,
"min": 7.775004551221427e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010885006371709999,
"min": 0.00010885006371709999,
"max": 0.0032229994256669,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10259163571428573,
"min": 0.10259163571428573,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4362829000000001,
"min": 1.3886848,
"max": 2.4018484,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002689044078571429,
"min": 0.0002689044078571429,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0037646617100000005,
"min": 0.0037646617100000005,
"max": 0.10744587669,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01007144432514906,
"min": 0.01007144432514906,
"max": 0.47528189420700073,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.14100022614002228,
"min": 0.14100022614002228,
"max": 3.3269731998443604,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 434.4776119402985,
"min": 434.4776119402985,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29110.0,
"min": 15984.0,
"max": 34998.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4460925197423393,
"min": -1.0000000521540642,
"max": 1.4460925197423393,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 96.88819882273674,
"min": -30.99780161678791,
"max": 96.88819882273674,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4460925197423393,
"min": -1.0000000521540642,
"max": 1.4460925197423393,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 96.88819882273674,
"min": -30.99780161678791,
"max": 96.88819882273674,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.045151801472321264,
"min": 0.045151801472321264,
"max": 9.836831261403859,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.0251706986455247,
"min": 3.0251706986455247,
"max": 157.38930018246174,
"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": "1685261227",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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=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": "1685263825"
},
"total": 2598.252246796,
"count": 1,
"self": 1.0859243939999033,
"children": {
"run_training.setup": {
"total": 0.07775123400006123,
"count": 1,
"self": 0.07775123400006123
},
"TrainerController.start_learning": {
"total": 2597.088571168,
"count": 1,
"self": 2.011500117914238,
"children": {
"TrainerController._reset_env": {
"total": 4.834275704999982,
"count": 1,
"self": 4.834275704999982
},
"TrainerController.advance": {
"total": 2590.0715886000858,
"count": 63457,
"self": 1.9845265020580882,
"children": {
"env_step": {
"total": 1869.2524884020656,
"count": 63457,
"self": 1719.8862747290614,
"children": {
"SubprocessEnvManager._take_step": {
"total": 148.1546859500138,
"count": 63457,
"self": 6.05645718497567,
"children": {
"TorchPolicy.evaluate": {
"total": 142.09822876503813,
"count": 62549,
"self": 142.09822876503813
}
}
},
"workers": {
"total": 1.2115277229904677,
"count": 63457,
"self": 0.0,
"children": {
"worker_root": {
"total": 2589.989181203053,
"count": 63457,
"is_parallel": true,
"self": 1020.328625097083,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003202908999810461,
"count": 1,
"is_parallel": true,
"self": 0.0008902699998998287,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023126389999106323,
"count": 8,
"is_parallel": true,
"self": 0.0023126389999106323
}
}
},
"UnityEnvironment.step": {
"total": 0.05826838500001941,
"count": 1,
"is_parallel": true,
"self": 0.0006429749998915213,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005972989999918354,
"count": 1,
"is_parallel": true,
"self": 0.0005972989999918354
},
"communicator.exchange": {
"total": 0.05478078100009043,
"count": 1,
"is_parallel": true,
"self": 0.05478078100009043
},
"steps_from_proto": {
"total": 0.002247330000045622,
"count": 1,
"is_parallel": true,
"self": 0.00044320500046524103,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001804124999580381,
"count": 8,
"is_parallel": true,
"self": 0.001804124999580381
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1569.6605561059698,
"count": 63456,
"is_parallel": true,
"self": 38.16444208495727,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 28.71772268198515,
"count": 63456,
"is_parallel": true,
"self": 28.71772268198515
},
"communicator.exchange": {
"total": 1378.3613255440225,
"count": 63456,
"is_parallel": true,
"self": 1378.3613255440225
},
"steps_from_proto": {
"total": 124.41706579500487,
"count": 63456,
"is_parallel": true,
"self": 26.575655204941768,
"children": {
"_process_rank_one_or_two_observation": {
"total": 97.8414105900631,
"count": 507648,
"is_parallel": true,
"self": 97.8414105900631
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 718.834573695962,
"count": 63457,
"self": 3.6581295119556216,
"children": {
"process_trajectory": {
"total": 128.11317883401352,
"count": 63457,
"self": 127.80291222201367,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3102666119998503,
"count": 2,
"self": 0.3102666119998503
}
}
},
"_update_policy": {
"total": 587.0632653499929,
"count": 444,
"self": 378.13705145106246,
"children": {
"TorchPPOOptimizer.update": {
"total": 208.92621389893043,
"count": 22794,
"self": 208.92621389893043
}
}
}
}
}
}
},
"trainer_threads": {
"total": 2.3530999897047877e-05,
"count": 1,
"self": 2.3530999897047877e-05
},
"TrainerController._save_models": {
"total": 0.17118321399993874,
"count": 1,
"self": 0.002033657999618299,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16914955600032044,
"count": 1,
"self": 0.16914955600032044
}
}
}
}
}
}
}