casals90's picture
Train agent
44a6724
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5508182048797607,
"min": 0.5340547561645508,
"max": 1.4265118837356567,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 16568.611328125,
"min": 15996.0078125,
"max": 43274.6640625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989932.0,
"min": 29952.0,
"max": 989932.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989932.0,
"min": 29952.0,
"max": 989932.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3972208499908447,
"min": -0.11308760195970535,
"max": 0.3972208499908447,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 105.2635269165039,
"min": -27.254112243652344,
"max": 105.2635269165039,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 2.2604756355285645,
"min": -0.7517434358596802,
"max": 2.52211332321167,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 599.0260620117188,
"min": -193.19805908203125,
"max": 665.837890625,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.04778814725744139,
"min": 0.04473340471338903,
"max": 0.05069294104823893,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.6690340616041794,
"min": 0.3504393802223993,
"max": 0.7420819742061819,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.3255374666879929,
"min": 0.0002985740899666741,
"max": 0.689656792186378,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 4.5575245336319,
"min": 0.003284314989633415,
"max": 9.655195090609292,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.0248611723585717e-05,
"min": 1.0248611723585717e-05,
"max": 0.0003935341730450285,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00014348056413020005,
"min": 0.00014348056413020005,
"max": 0.0046764998308751,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10256212857142857,
"min": 0.10256212857142857,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4358698,
"min": 1.3886848,
"max": 2.5691249000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002659566442857144,
"min": 0.0002659566442857144,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003723393020000001,
"min": 0.003723393020000001,
"max": 0.11693557751000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.016530394554138184,
"min": 0.016530394554138184,
"max": 0.5854299664497375,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.23142552375793457,
"min": 0.23142552375793457,
"max": 4.0980095863342285,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 434.54545454545456,
"min": 434.54545454545456,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28680.0,
"min": 15984.0,
"max": 33010.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4745060369146592,
"min": -1.0000000521540642,
"max": 1.4745060369146592,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 97.31739843636751,
"min": -31.998001664876938,
"max": 97.31739843636751,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4745060369146592,
"min": -1.0000000521540642,
"max": 1.4745060369146592,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 97.31739843636751,
"min": -31.998001664876938,
"max": 97.31739843636751,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.07317099387331506,
"min": 0.07317099387331506,
"max": 8.897823443636298,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.829285595638794,
"min": 4.829285595638794,
"max": 142.36517509818077,
"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": "1685730744",
"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": "1685732918"
},
"total": 2174.1822528820003,
"count": 1,
"self": 0.48089617400046336,
"children": {
"run_training.setup": {
"total": 0.036908027000208676,
"count": 1,
"self": 0.036908027000208676
},
"TrainerController.start_learning": {
"total": 2173.6644486809996,
"count": 1,
"self": 1.6671747929540288,
"children": {
"TrainerController._reset_env": {
"total": 5.0894109580003715,
"count": 1,
"self": 5.0894109580003715
},
"TrainerController.advance": {
"total": 2166.8095219870443,
"count": 63510,
"self": 1.6481359410508958,
"children": {
"env_step": {
"total": 1616.2203333199818,
"count": 63510,
"self": 1491.1214996100516,
"children": {
"SubprocessEnvManager._take_step": {
"total": 124.1112507519997,
"count": 63510,
"self": 5.235941475076743,
"children": {
"TorchPolicy.evaluate": {
"total": 118.87530927692296,
"count": 62560,
"self": 118.87530927692296
}
}
},
"workers": {
"total": 0.9875829579304991,
"count": 63510,
"self": 0.0,
"children": {
"worker_root": {
"total": 2168.0366718319865,
"count": 63510,
"is_parallel": true,
"self": 801.9045272529911,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0027159359997313004,
"count": 1,
"is_parallel": true,
"self": 0.0007742789998701483,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019416569998611521,
"count": 8,
"is_parallel": true,
"self": 0.0019416569998611521
}
}
},
"UnityEnvironment.step": {
"total": 0.04527298299990434,
"count": 1,
"is_parallel": true,
"self": 0.0005080169999018835,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005229550001786265,
"count": 1,
"is_parallel": true,
"self": 0.0005229550001786265
},
"communicator.exchange": {
"total": 0.042514624999967054,
"count": 1,
"is_parallel": true,
"self": 0.042514624999967054
},
"steps_from_proto": {
"total": 0.0017273859998567787,
"count": 1,
"is_parallel": true,
"self": 0.0003392900002836541,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013880959995731246,
"count": 8,
"is_parallel": true,
"self": 0.0013880959995731246
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1366.1321445789954,
"count": 63509,
"is_parallel": true,
"self": 34.19887077510839,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.47571290910355,
"count": 63509,
"is_parallel": true,
"self": 24.47571290910355
},
"communicator.exchange": {
"total": 1201.0813873368556,
"count": 63509,
"is_parallel": true,
"self": 1201.0813873368556
},
"steps_from_proto": {
"total": 106.37617355792781,
"count": 63509,
"is_parallel": true,
"self": 22.113279989981038,
"children": {
"_process_rank_one_or_two_observation": {
"total": 84.26289356794678,
"count": 508072,
"is_parallel": true,
"self": 84.26289356794678
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 548.9410527260115,
"count": 63510,
"self": 2.991464230055044,
"children": {
"process_trajectory": {
"total": 112.52026848696278,
"count": 63510,
"self": 112.2985001239631,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22176836299968272,
"count": 2,
"self": 0.22176836299968272
}
}
},
"_update_policy": {
"total": 433.4293200089937,
"count": 447,
"self": 323.5623516359851,
"children": {
"TorchPPOOptimizer.update": {
"total": 109.8669683730086,
"count": 11295,
"self": 109.8669683730086
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4000006558489986e-06,
"count": 1,
"self": 1.4000006558489986e-06
},
"TrainerController._save_models": {
"total": 0.0983395430002929,
"count": 1,
"self": 0.001593437999872549,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09674610500042036,
"count": 1,
"self": 0.09674610500042036
}
}
}
}
}
}
}