JiemingYou's picture
First Push
a59428c
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5689113140106201,
"min": 0.5689113140106201,
"max": 1.4412434101104736,
"count": 20
},
"Pyramids.Policy.Entropy.sum": {
"value": 17203.87890625,
"min": 17203.87890625,
"max": 43721.55859375,
"count": 20
},
"Pyramids.Step.mean": {
"value": 599978.0,
"min": 29952.0,
"max": 599978.0,
"count": 20
},
"Pyramids.Step.sum": {
"value": 599978.0,
"min": 29952.0,
"max": 599978.0,
"count": 20
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.464095801115036,
"min": -0.08201377838850021,
"max": 0.464095801115036,
"count": 20
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 126.23405456542969,
"min": -19.683307647705078,
"max": 126.23405456542969,
"count": 20
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.00031448944355361164,
"min": 0.00031448944355361164,
"max": 0.3900849521160126,
"count": 20
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 0.08554112911224365,
"min": 0.08554112911224365,
"max": 92.45013427734375,
"count": 20
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06985421754680353,
"min": 0.06618001399846606,
"max": 0.07401825415619168,
"count": 20
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9779590456552494,
"min": 0.5064248904383785,
"max": 1.063299471278465,
"count": 20
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014380865464599558,
"min": 0.0003472449041416095,
"max": 0.014380865464599558,
"count": 20
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2013321165043938,
"min": 0.0031252041372744855,
"max": 0.2013321165043938,
"count": 20
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.00012440990853005001,
"min": 0.00012440990853005001,
"max": 0.00029515063018788575,
"count": 20
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0017417387194207001,
"min": 0.0017417387194207001,
"max": 0.0032573105142298994,
"count": 20
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.14146995000000004,
"min": 0.14146995000000004,
"max": 0.19838354285714285,
"count": 20
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.9805793000000005,
"min": 1.3886848,
"max": 2.4824938999999997,
"count": 20
},
"Pyramids.Policy.Beta.mean": {
"value": 0.004152848004999999,
"min": 0.004152848004999999,
"max": 0.00983851593142857,
"count": 20
},
"Pyramids.Policy.Beta.sum": {
"value": 0.058139872069999994,
"min": 0.058139872069999994,
"max": 0.10859843299,
"count": 20
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01801672950387001,
"min": 0.01801672950387001,
"max": 0.5898144841194153,
"count": 20
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.25223422050476074,
"min": 0.25223422050476074,
"max": 4.128701210021973,
"count": 20
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 394.44,
"min": 394.44,
"max": 999.0,
"count": 20
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29583.0,
"min": 15984.0,
"max": 32679.0,
"count": 20
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4721786383787792,
"min": -1.0000000521540642,
"max": 1.4721786383787792,
"count": 20
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 110.41339787840843,
"min": -30.999801620841026,
"max": 110.41339787840843,
"count": 20
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4721786383787792,
"min": -1.0000000521540642,
"max": 1.4721786383787792,
"count": 20
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 110.41339787840843,
"min": -30.999801620841026,
"max": 110.41339787840843,
"count": 20
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.07447391705742727,
"min": 0.07447391705742727,
"max": 12.240999970585108,
"count": 20
},
"Pyramids.Policy.RndReward.sum": {
"value": 5.585543779307045,
"min": 5.585543779307045,
"max": 195.85599952936172,
"count": 20
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1693829103",
"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": "1693830466"
},
"total": 1362.6369430089999,
"count": 1,
"self": 0.3071996719997969,
"children": {
"run_training.setup": {
"total": 0.039511822000122265,
"count": 1,
"self": 0.039511822000122265
},
"TrainerController.start_learning": {
"total": 1362.290231515,
"count": 1,
"self": 0.9468783829674976,
"children": {
"TrainerController._reset_env": {
"total": 4.135300695999831,
"count": 1,
"self": 4.135300695999831
},
"TrainerController.advance": {
"total": 1357.0341934160324,
"count": 38485,
"self": 0.894515267101724,
"children": {
"env_step": {
"total": 955.6441660709445,
"count": 38485,
"self": 886.7093979559406,
"children": {
"SubprocessEnvManager._take_step": {
"total": 68.37642833393602,
"count": 38485,
"self": 2.9406857299466083,
"children": {
"TorchPolicy.evaluate": {
"total": 65.43574260398941,
"count": 37920,
"self": 65.43574260398941
}
}
},
"workers": {
"total": 0.5583397810678434,
"count": 38484,
"self": 0.0,
"children": {
"worker_root": {
"total": 1358.7896039089658,
"count": 38484,
"is_parallel": true,
"self": 543.7837837889592,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018214409999472991,
"count": 1,
"is_parallel": true,
"self": 0.0005821059996833355,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012393350002639636,
"count": 8,
"is_parallel": true,
"self": 0.0012393350002639636
}
}
},
"UnityEnvironment.step": {
"total": 0.050979492999886133,
"count": 1,
"is_parallel": true,
"self": 0.0006233559997781413,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004812470001525071,
"count": 1,
"is_parallel": true,
"self": 0.0004812470001525071
},
"communicator.exchange": {
"total": 0.04757878800000981,
"count": 1,
"is_parallel": true,
"self": 0.04757878800000981
},
"steps_from_proto": {
"total": 0.0022961019999456767,
"count": 1,
"is_parallel": true,
"self": 0.0004018140000425774,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018942879999030993,
"count": 8,
"is_parallel": true,
"self": 0.0018942879999030993
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 815.0058201200065,
"count": 38483,
"is_parallel": true,
"self": 20.938298507886884,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 14.005965129018023,
"count": 38483,
"is_parallel": true,
"self": 14.005965129018023
},
"communicator.exchange": {
"total": 714.930820823035,
"count": 38483,
"is_parallel": true,
"self": 714.930820823035
},
"steps_from_proto": {
"total": 65.13073566006665,
"count": 38483,
"is_parallel": true,
"self": 12.97238277404881,
"children": {
"_process_rank_one_or_two_observation": {
"total": 52.15835288601784,
"count": 307864,
"is_parallel": true,
"self": 52.15835288601784
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 400.4955120779862,
"count": 38484,
"self": 1.5933069920370144,
"children": {
"process_trajectory": {
"total": 66.68041924495083,
"count": 38484,
"self": 66.57051476095103,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10990448399979869,
"count": 1,
"self": 0.10990448399979869
}
}
},
"_update_policy": {
"total": 332.22178584099834,
"count": 261,
"self": 218.01032563201034,
"children": {
"TorchPPOOptimizer.update": {
"total": 114.211460208988,
"count": 13854,
"self": 114.211460208988
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.720000000204891e-06,
"count": 1,
"self": 1.720000000204891e-06
},
"TrainerController._save_models": {
"total": 0.17385730000023614,
"count": 1,
"self": 0.0019182770001862082,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17193902300004993,
"count": 1,
"self": 0.17193902300004993
}
}
}
}
}
}
}