phonenix's picture
PyramidTraining
dc250d1
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.15647119283676147,
"min": 0.1465008556842804,
"max": 1.4826655387878418,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 4689.12890625,
"min": 4399.87744140625,
"max": 44978.140625,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999964.0,
"min": 29952.0,
"max": 2999964.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999964.0,
"min": 29952.0,
"max": 2999964.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.8579196333885193,
"min": -0.3059077560901642,
"max": 0.9174038171768188,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 259.09173583984375,
"min": -72.50013732910156,
"max": 284.138427734375,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.007420403882861137,
"min": -0.08628343045711517,
"max": 0.3240874707698822,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.240962028503418,
"min": -25.626178741455078,
"max": 76.80873107910156,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07031175549837783,
"min": 0.06536318687255181,
"max": 0.07485927269867274,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9843645769772895,
"min": 0.49799280686554204,
"max": 1.0807033645590611,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013283268786351788,
"min": 0.00021984335582263405,
"max": 0.0156818669846481,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.18596576300892503,
"min": 0.0028579636256942428,
"max": 0.22005281544018848,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.4909637887595234e-06,
"min": 1.4909637887595234e-06,
"max": 0.00029838354339596195,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.0873493042633327e-05,
"min": 2.0873493042633327e-05,
"max": 0.0038847563050812663,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10049695476190477,
"min": 0.10049695476190477,
"max": 0.19946118095238097,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4069573666666668,
"min": 1.3897045333333333,
"max": 2.7674754000000004,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 5.964578071428571e-05,
"min": 5.964578071428571e-05,
"max": 0.009946171977142856,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00083504093,
"min": 0.00083504093,
"max": 0.12950238146,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.006232266779989004,
"min": 0.006232266779989004,
"max": 0.3465867042541504,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.08725173771381378,
"min": 0.08725173771381378,
"max": 2.4261069297790527,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 209.3013698630137,
"min": 194.27814569536423,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30558.0,
"min": 15984.0,
"max": 32357.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7761558483386861,
"min": -1.0000000521540642,
"max": 1.7981836625507899,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 257.5425980091095,
"min": -32.000001668930054,
"max": 279.00359734892845,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7761558483386861,
"min": -1.0000000521540642,
"max": 1.7981836625507899,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 257.5425980091095,
"min": -32.000001668930054,
"max": 279.00359734892845,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.013542505146173864,
"min": 0.012719900023172765,
"max": 7.455191017128527,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 1.9636632461952104,
"min": 1.8950678529799916,
"max": 119.28305627405643,
"count": 100
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1676479812",
"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": "1676487242"
},
"total": 7430.021672806,
"count": 1,
"self": 0.5287524189989199,
"children": {
"run_training.setup": {
"total": 0.10565603500026555,
"count": 1,
"self": 0.10565603500026555
},
"TrainerController.start_learning": {
"total": 7429.387264352001,
"count": 1,
"self": 4.135532218003391,
"children": {
"TrainerController._reset_env": {
"total": 7.1609417190002205,
"count": 1,
"self": 7.1609417190002205
},
"TrainerController.advance": {
"total": 7418.0062039879995,
"count": 195618,
"self": 4.120584531485292,
"children": {
"env_step": {
"total": 5216.852861309711,
"count": 195618,
"self": 4880.640854313438,
"children": {
"SubprocessEnvManager._take_step": {
"total": 333.6898954190483,
"count": 195618,
"self": 13.479663653178704,
"children": {
"TorchPolicy.evaluate": {
"total": 320.2102317658696,
"count": 187541,
"self": 107.02624381487794,
"children": {
"TorchPolicy.sample_actions": {
"total": 213.18398795099165,
"count": 187541,
"self": 213.18398795099165
}
}
}
}
},
"workers": {
"total": 2.522111577225587,
"count": 195618,
"self": 0.0,
"children": {
"worker_root": {
"total": 7413.0742486841555,
"count": 195618,
"is_parallel": true,
"self": 2876.0146561870934,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0025283820000367996,
"count": 1,
"is_parallel": true,
"self": 0.0009368119999635383,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015915700000732613,
"count": 8,
"is_parallel": true,
"self": 0.0015915700000732613
}
}
},
"UnityEnvironment.step": {
"total": 0.04749137599992537,
"count": 1,
"is_parallel": true,
"self": 0.0005043179999120184,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004828529999940656,
"count": 1,
"is_parallel": true,
"self": 0.0004828529999940656
},
"communicator.exchange": {
"total": 0.04491929200003142,
"count": 1,
"is_parallel": true,
"self": 0.04491929200003142
},
"steps_from_proto": {
"total": 0.0015849129999878642,
"count": 1,
"is_parallel": true,
"self": 0.0004286970001885493,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011562159997993149,
"count": 8,
"is_parallel": true,
"self": 0.0011562159997993149
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 4537.059592497062,
"count": 195617,
"is_parallel": true,
"self": 93.61681658014913,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 67.75990198261434,
"count": 195617,
"is_parallel": true,
"self": 67.75990198261434
},
"communicator.exchange": {
"total": 4073.6811763242717,
"count": 195617,
"is_parallel": true,
"self": 4073.6811763242717
},
"steps_from_proto": {
"total": 302.0016976100269,
"count": 195617,
"is_parallel": true,
"self": 67.26917776956407,
"children": {
"_process_rank_one_or_two_observation": {
"total": 234.73251984046283,
"count": 1564936,
"is_parallel": true,
"self": 234.73251984046283
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 2197.032758146803,
"count": 195618,
"self": 7.938636375906299,
"children": {
"process_trajectory": {
"total": 484.1093086539113,
"count": 195618,
"self": 483.4773898849112,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6319187690000945,
"count": 6,
"self": 0.6319187690000945
}
}
},
"_update_policy": {
"total": 1704.9848131169856,
"count": 1392,
"self": 658.4360570930226,
"children": {
"TorchPPOOptimizer.update": {
"total": 1046.548756023963,
"count": 68364,
"self": 1046.548756023963
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.709986675763503e-07,
"count": 1,
"self": 7.709986675763503e-07
},
"TrainerController._save_models": {
"total": 0.08458565599903523,
"count": 1,
"self": 0.0013521299988497049,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08323352600018552,
"count": 1,
"self": 0.08323352600018552
}
}
}
}
}
}
}