mlewand's picture
First model
0a3e64f
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.27246880531311035,
"min": 0.2627556025981903,
"max": 1.5386015176773071,
"count": 50
},
"Pyramids.Policy.Entropy.sum": {
"value": 8230.7373046875,
"min": 7903.6884765625,
"max": 46675.015625,
"count": 50
},
"Pyramids.Step.mean": {
"value": 1499958.0,
"min": 29952.0,
"max": 1499958.0,
"count": 50
},
"Pyramids.Step.sum": {
"value": 1499958.0,
"min": 29952.0,
"max": 1499958.0,
"count": 50
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5998520851135254,
"min": -0.1066562607884407,
"max": 0.6411776542663574,
"count": 50
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 163.75961303710938,
"min": -25.704158782958984,
"max": 186.58270263671875,
"count": 50
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0033998675644397736,
"min": -0.013668715953826904,
"max": 0.2063014954328537,
"count": 50
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 0.9281638264656067,
"min": -3.635878324508667,
"max": 48.893455505371094,
"count": 50
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.14151808634556204,
"min": 0.1336244730214038,
"max": 0.14492919666964504,
"count": 50
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.9812532088378685,
"min": 0.9822851577740237,
"max": 2.1010401871094184,
"count": 50
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014188774131002054,
"min": 0.00014515176736311413,
"max": 0.017480790394181753,
"count": 50
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.19864283783402875,
"min": 0.001161214138904913,
"max": 0.2622118559127263,
"count": 50
},
"Pyramids.Policy.LearningRate.mean": {
"value": 2.9947847160571397e-06,
"min": 2.9947847160571397e-06,
"max": 0.00029676708679192377,
"count": 50
},
"Pyramids.Policy.LearningRate.sum": {
"value": 4.1926986024799954e-05,
"min": 4.1926986024799954e-05,
"max": 0.003738778953740399,
"count": 50
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1009982285714286,
"min": 0.1009982285714286,
"max": 0.19892236190476195,
"count": 50
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4139752000000003,
"min": 1.3794090666666667,
"max": 2.6462596,
"count": 50
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00010972303428571421,
"min": 0.00010972303428571421,
"max": 0.009892343954285714,
"count": 50
},
"Pyramids.Policy.Beta.sum": {
"value": 0.001536122479999999,
"min": 0.001536122479999999,
"max": 0.12464133404,
"count": 50
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.004553825128823519,
"min": 0.004553825128823519,
"max": 0.2124662697315216,
"count": 50
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.06375355273485184,
"min": 0.06375355273485184,
"max": 1.4872639179229736,
"count": 50
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 341.15909090909093,
"min": 280.23423423423424,
"max": 999.0,
"count": 50
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30022.0,
"min": 15984.0,
"max": 32359.0,
"count": 50
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5451658887957984,
"min": -1.0000000521540642,
"max": 1.6656936742700972,
"count": 50
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 135.97459821403027,
"min": -32.000001668930054,
"max": 184.8919978439808,
"count": 50
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5451658887957984,
"min": -1.0000000521540642,
"max": 1.6656936742700972,
"count": 50
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 135.97459821403027,
"min": -32.000001668930054,
"max": 184.8919978439808,
"count": 50
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.01642101402140642,
"min": 0.014596151844987458,
"max": 7.208528668154031,
"count": 50
},
"Pyramids.Policy.RndReward.sum": {
"value": 1.4450492338837648,
"min": 1.3428459697388462,
"max": 115.3364586904645,
"count": 50
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1677014694",
"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=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": "1677019057"
},
"total": 4363.426508095999,
"count": 1,
"self": 0.4884871619997284,
"children": {
"run_training.setup": {
"total": 0.12265524899999036,
"count": 1,
"self": 0.12265524899999036
},
"TrainerController.start_learning": {
"total": 4362.815365685,
"count": 1,
"self": 1.8861137390940712,
"children": {
"TrainerController._reset_env": {
"total": 7.183632853999825,
"count": 1,
"self": 7.183632853999825
},
"TrainerController.advance": {
"total": 4353.658359171906,
"count": 96072,
"self": 2.06223893600054,
"children": {
"env_step": {
"total": 2197.7975628218774,
"count": 96072,
"self": 2035.132120281842,
"children": {
"SubprocessEnvManager._take_step": {
"total": 161.48518114002695,
"count": 96072,
"self": 6.583467337016373,
"children": {
"TorchPolicy.evaluate": {
"total": 154.90171380301058,
"count": 93821,
"self": 51.885210409935326,
"children": {
"TorchPolicy.sample_actions": {
"total": 103.01650339307525,
"count": 93821,
"self": 103.01650339307525
}
}
}
}
},
"workers": {
"total": 1.180261400008476,
"count": 96072,
"self": 0.0,
"children": {
"worker_root": {
"total": 4356.047121898962,
"count": 96072,
"is_parallel": true,
"self": 2482.6301365491313,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017420769997897878,
"count": 1,
"is_parallel": true,
"self": 0.00065015099971788,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010919260000719078,
"count": 8,
"is_parallel": true,
"self": 0.0010919260000719078
}
}
},
"UnityEnvironment.step": {
"total": 0.07128982800008998,
"count": 1,
"is_parallel": true,
"self": 0.0005246330001682509,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004319629999827157,
"count": 1,
"is_parallel": true,
"self": 0.0004319629999827157
},
"communicator.exchange": {
"total": 0.06868898499988063,
"count": 1,
"is_parallel": true,
"self": 0.06868898499988063
},
"steps_from_proto": {
"total": 0.0016442470000583853,
"count": 1,
"is_parallel": true,
"self": 0.00040072600017992954,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012435209998784558,
"count": 8,
"is_parallel": true,
"self": 0.0012435209998784558
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1873.416985349831,
"count": 96071,
"is_parallel": true,
"self": 45.87203197090071,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 33.392651519004175,
"count": 96071,
"is_parallel": true,
"self": 33.392651519004175
},
"communicator.exchange": {
"total": 1657.7813132249714,
"count": 96071,
"is_parallel": true,
"self": 1657.7813132249714
},
"steps_from_proto": {
"total": 136.37098863495476,
"count": 96071,
"is_parallel": true,
"self": 31.441610067712645,
"children": {
"_process_rank_one_or_two_observation": {
"total": 104.92937856724211,
"count": 768568,
"is_parallel": true,
"self": 104.92937856724211
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 2153.7985574140284,
"count": 96072,
"self": 3.774511789018561,
"children": {
"process_trajectory": {
"total": 238.97834312701752,
"count": 96072,
"self": 238.64842508701759,
"children": {
"RLTrainer._checkpoint": {
"total": 0.32991803999993863,
"count": 3,
"self": 0.32991803999993863
}
}
},
"_update_policy": {
"total": 1911.0457024979924,
"count": 680,
"self": 357.0731223349005,
"children": {
"TorchPPOOptimizer.update": {
"total": 1553.9725801630918,
"count": 139620,
"self": 1553.9725801630918
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.400002116104588e-07,
"count": 1,
"self": 8.400002116104588e-07
},
"TrainerController._save_models": {
"total": 0.08725907999996707,
"count": 1,
"self": 0.0014595969996662461,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08579948300030082,
"count": 1,
"self": 0.08579948300030082
}
}
}
}
}
}
}