{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3334551751613617, "min": 0.3328145146369934, "max": 1.4795478582382202, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10019.6611328125, "min": 9957.810546875, "max": 44883.5625, "count": 33 }, "Pyramids.Step.mean": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.45167192816734314, "min": -0.08324038237333298, "max": 0.5820865035057068, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 121.04808044433594, "min": -20.227413177490234, "max": 162.40213012695312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012553384527564049, "min": 0.0024715710896998644, "max": 0.5469594597816467, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.364307165145874, "min": 0.674738883972168, "max": 129.62939453125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06851837626891209, "min": 0.0637891361505164, "max": 0.07378796734410163, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9592572677647694, "min": 0.47309644869796336, "max": 1.075766834653526, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014509123679350266, "min": 0.001052090429528759, "max": 0.015688069599272336, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20312773151090371, "min": 0.008736625466397151, "max": 0.22650676813645984, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.495126073085715e-06, "min": 7.495126073085715e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010493176502320001, "min": 0.00010493176502320001, "max": 0.0035097710300763993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249834285714285, "min": 0.10249834285714285, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4349767999999998, "min": 1.3691136000000002, "max": 2.5699236, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025958445142857154, "min": 0.00025958445142857154, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036341823200000014, "min": 0.0036341823200000014, "max": 0.11701536764, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01211926992982626, "min": 0.012000342831015587, "max": 0.4874555468559265, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16966977715492249, "min": 0.16800479590892792, "max": 3.412188768386841, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 386.3246753246753, "min": 307.80645161290323, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29747.0, "min": 15984.0, "max": 33418.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4598615197226024, "min": -1.0000000521540642, "max": 1.6466343874732654, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 113.86919853836298, "min": -32.000001668930054, "max": 153.13699803501368, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4598615197226024, "min": -1.0000000521540642, "max": 1.6466343874732654, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 113.86919853836298, "min": -32.000001668930054, "max": 153.13699803501368, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04828063452105898, "min": 0.04221615365766469, "max": 10.529616260901093, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.7658894926426, "min": 3.7211279100738466, "max": 168.4738601744175, "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": "1673694962", "python_version": "3.9.0 (default, Nov 15 2020, 14:28:56) \n[GCC 7.3.0]", "command_line_arguments": "/home/chqma/miniconda3/envs/ml-agents/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", "numpy_version": "1.21.2", "end_time_seconds": "1673697269" }, "total": 2306.965308354993, "count": 1, "self": 1.0895091279526241, "children": { "run_training.setup": { "total": 0.11840540502453223, "count": 1, "self": 0.11840540502453223 }, "TrainerController.start_learning": { "total": 2305.7573938220157, "count": 1, "self": 1.5852277497760952, "children": { "TrainerController._reset_env": { "total": 9.270528341992758, "count": 1, "self": 9.270528341992758 }, "TrainerController.advance": { "total": 2294.6431791352225, "count": 63951, "self": 1.6329649667604826, "children": { "env_step": { "total": 1511.7483201597352, "count": 63951, "self": 1262.288740124728, "children": { "SubprocessEnvManager._take_step": { "total": 248.4894399245386, "count": 63951, "self": 5.329766222334001, "children": { "TorchPolicy.evaluate": { "total": 243.1596737022046, "count": 62554, "self": 243.1596737022046 } } }, "workers": { "total": 0.9701401104684919, "count": 63951, "self": 0.0, "children": { "worker_root": { "total": 2301.8266824560706, "count": 63951, "is_parallel": true, "self": 1137.919742102793, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003445657028350979, "count": 1, "is_parallel": true, "self": 0.0023907970171421766, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010548600112088025, "count": 8, "is_parallel": true, "self": 0.0010548600112088025 } } }, "UnityEnvironment.step": { "total": 0.03993573802290484, "count": 1, "is_parallel": true, "self": 0.00026884692488238215, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00024389504687860608, "count": 1, "is_parallel": true, "self": 0.00024389504687860608 }, "communicator.exchange": { "total": 0.03859603404998779, "count": 1, "is_parallel": true, "self": 0.03859603404998779 }, "steps_from_proto": { "total": 0.0008269620011560619, "count": 1, "is_parallel": true, "self": 0.00019400299061089754, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006329590105451643, "count": 8, "is_parallel": true, "self": 0.0006329590105451643 } } } } } } }, "UnityEnvironment.step": { "total": 1163.9069403532776, "count": 63950, "is_parallel": true, "self": 18.89088205207372, "children": { "UnityEnvironment._generate_step_input": { "total": 13.054659166315105, "count": 63950, "is_parallel": true, "self": 13.054659166315105 }, "communicator.exchange": { "total": 1083.225232513505, "count": 63950, "is_parallel": true, "self": 1083.225232513505 }, "steps_from_proto": { "total": 48.736166621383745, "count": 63950, "is_parallel": true, "self": 11.51267424330581, "children": { "_process_rank_one_or_two_observation": { "total": 37.223492378077935, "count": 511600, "is_parallel": true, "self": 37.223492378077935 } } } } } } } } } } }, "trainer_advance": { "total": 781.2618940087268, "count": 63951, "self": 2.6005936408764683, "children": { "process_trajectory": { "total": 137.9861471504555, "count": 63951, "self": 137.59224792243913, "children": { "RLTrainer._checkpoint": { "total": 0.3938992280163802, "count": 2, "self": 0.3938992280163802 } } }, "_update_policy": { "total": 640.6751532173948, "count": 448, "self": 309.3586276877322, "children": { "TorchPPOOptimizer.update": { "total": 331.3165255296626, "count": 22812, "self": 331.3165255296626 } } } } } } }, "trainer_threads": { "total": 6.940099410712719e-07, "count": 1, "self": 6.940099410712719e-07 }, "TrainerController._save_models": { "total": 0.25845790101448074, "count": 1, "self": 0.08870779705466703, "children": { "RLTrainer._checkpoint": { "total": 0.16975010395981371, "count": 1, "self": 0.16975010395981371 } } } } } } }