ppo-Pyramids / run_logs /timers.json
dana11235's picture
Hi
ceb43c2
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4624592959880829,
"min": 0.4624592959880829,
"max": 1.4692448377609253,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 13622.201171875,
"min": 13622.201171875,
"max": 44571.01171875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989962.0,
"min": 29952.0,
"max": 989962.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989962.0,
"min": 29952.0,
"max": 989962.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4840852618217468,
"min": -0.09797441214323044,
"max": 0.4840852618217468,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 130.70301818847656,
"min": -23.709808349609375,
"max": 130.70301818847656,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.026912441477179527,
"min": -0.028821103274822235,
"max": 0.26651960611343384,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 7.266359329223633,
"min": -7.608771324157715,
"max": 63.16514587402344,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06279694756501288,
"min": 0.06279694756501288,
"max": 0.07375830784399337,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.8791572659101803,
"min": 0.493792959435404,
"max": 1.0911709208157845,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014459573504739507,
"min": 0.0008416765055081287,
"max": 0.01579056686346626,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2024340290663531,
"min": 0.011783471077113802,
"max": 0.2368585029519939,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.609040320828574e-06,
"min": 7.609040320828574e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010652656449160003,
"min": 0.00010652656449160003,
"max": 0.0036330925889692,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10253631428571428,
"min": 0.10253631428571428,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4355083999999998,
"min": 1.3886848,
"max": 2.6110308,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002633777971428573,
"min": 0.0002633777971428573,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036872891600000022,
"min": 0.0036872891600000022,
"max": 0.12112197692,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.008728482760488987,
"min": 0.008728482760488987,
"max": 0.27401918172836304,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.12219875305891037,
"min": 0.12219875305891037,
"max": 1.918134331703186,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 392.19736842105266,
"min": 392.19736842105266,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29807.0,
"min": 15984.0,
"max": 32379.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4498552435911016,
"min": -1.0000000521540642,
"max": 1.463216415517134,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 110.18899851292372,
"min": -30.41100163757801,
"max": 110.18899851292372,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4498552435911016,
"min": -1.0000000521540642,
"max": 1.463216415517134,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 110.18899851292372,
"min": -30.41100163757801,
"max": 110.18899851292372,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03575554829053305,
"min": 0.03575554829053305,
"max": 5.837577868252993,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.717421670080512,
"min": 2.717421670080512,
"max": 93.40124589204788,
"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": "1695621122",
"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": "1695623346"
},
"total": 2223.615931684,
"count": 1,
"self": 0.5253644399999757,
"children": {
"run_training.setup": {
"total": 0.04465708199995788,
"count": 1,
"self": 0.04465708199995788
},
"TrainerController.start_learning": {
"total": 2223.045910162,
"count": 1,
"self": 1.5311568529614306,
"children": {
"TrainerController._reset_env": {
"total": 4.223907093000207,
"count": 1,
"self": 4.223907093000207
},
"TrainerController.advance": {
"total": 2217.1930853330387,
"count": 63673,
"self": 1.604317045944299,
"children": {
"env_step": {
"total": 1551.3950206980487,
"count": 63673,
"self": 1434.2591839430584,
"children": {
"SubprocessEnvManager._take_step": {
"total": 116.24535175999335,
"count": 63673,
"self": 5.049823912996999,
"children": {
"TorchPolicy.evaluate": {
"total": 111.19552784699636,
"count": 62557,
"self": 111.19552784699636
}
}
},
"workers": {
"total": 0.8904849949969957,
"count": 63673,
"self": 0.0,
"children": {
"worker_root": {
"total": 2217.808463362993,
"count": 63673,
"is_parallel": true,
"self": 905.2272118109393,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017440829999486596,
"count": 1,
"is_parallel": true,
"self": 0.0005433379999431054,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012007450000055542,
"count": 8,
"is_parallel": true,
"self": 0.0012007450000055542
}
}
},
"UnityEnvironment.step": {
"total": 0.055531222999888996,
"count": 1,
"is_parallel": true,
"self": 0.0011909779996130965,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005208290001519345,
"count": 1,
"is_parallel": true,
"self": 0.0005208290001519345
},
"communicator.exchange": {
"total": 0.050619755000070654,
"count": 1,
"is_parallel": true,
"self": 0.050619755000070654
},
"steps_from_proto": {
"total": 0.003199661000053311,
"count": 1,
"is_parallel": true,
"self": 0.00040604500009067124,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0027936159999626398,
"count": 8,
"is_parallel": true,
"self": 0.0027936159999626398
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1312.5812515520536,
"count": 63672,
"is_parallel": true,
"self": 35.01119055508457,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 25.36416544495546,
"count": 63672,
"is_parallel": true,
"self": 25.36416544495546
},
"communicator.exchange": {
"total": 1138.935282281032,
"count": 63672,
"is_parallel": true,
"self": 1138.935282281032
},
"steps_from_proto": {
"total": 113.27061327098158,
"count": 63672,
"is_parallel": true,
"self": 22.931172725030365,
"children": {
"_process_rank_one_or_two_observation": {
"total": 90.33944054595122,
"count": 509376,
"is_parallel": true,
"self": 90.33944054595122
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 664.1937475890456,
"count": 63673,
"self": 2.753725159077476,
"children": {
"process_trajectory": {
"total": 114.89545886196902,
"count": 63673,
"self": 114.68452871296904,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21093014899997797,
"count": 2,
"self": 0.21093014899997797
}
}
},
"_update_policy": {
"total": 546.5445635679991,
"count": 451,
"self": 356.8689936889823,
"children": {
"TorchPPOOptimizer.update": {
"total": 189.67556987901685,
"count": 22803,
"self": 189.67556987901685
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.219999472203199e-07,
"count": 1,
"self": 8.219999472203199e-07
},
"TrainerController._save_models": {
"total": 0.09776006099991719,
"count": 1,
"self": 0.0013981659999444673,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09636189499997272,
"count": 1,
"self": 0.09636189499997272
}
}
}
}
}
}
}