{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1583540141582489, "min": 0.1569911539554596, "max": 1.4295436143875122, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4682.21142578125, "min": 4682.21142578125, "max": 43366.63671875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999900.0, "min": 29958.0, "max": 2999900.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999900.0, "min": 29958.0, "max": 2999900.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6855654120445251, "min": -0.11735038459300995, "max": 0.8141212463378906, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 196.0717010498047, "min": -28.164093017578125, "max": 249.12109375, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0009839418344199657, "min": -0.04976990818977356, "max": 0.30917128920555115, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.28140735626220703, "min": -13.13925552368164, "max": 73.582763671875, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.068841402062736, "min": 0.06385058625782089, "max": 0.07520887412568451, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9637796288783042, "min": 0.5013290572645217, "max": 1.0945816190505866, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014411442883399767, "min": 0.0001768181377851187, "max": 0.01723156768000788, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20176020036759673, "min": 0.0022986357912065433, "max": 0.2584735152001182, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4118709579809567e-06, "min": 1.4118709579809567e-06, "max": 0.0002984127148148095, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 1.9766193411733393e-05, "min": 1.9766193411733393e-05, "max": 0.004010902763032433, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10047059047619049, "min": 0.10047059047619049, "max": 0.19947090476190477, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.406588266666667, "min": 1.3962963333333334, "max": 2.7825211333333337, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.701198857142871e-05, "min": 5.701198857142871e-05, "max": 0.009947143385714285, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.000798167840000002, "min": 0.000798167840000002, "max": 0.13370305990999998, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.003546312218531966, "min": 0.003440025495365262, "max": 0.3492596447467804, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.04964837059378624, "min": 0.04964837059378624, "max": 2.444817543029785, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 275.8073394495413, "min": 223.92424242424244, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30063.0, "min": 16501.0, "max": 32948.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6324238348581375, "min": -0.9998250515200198, "max": 1.761833573798187, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 177.934197999537, "min": -31.994401648640633, "max": 230.80019816756248, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6324238348581375, "min": -0.9998250515200198, "max": 1.761833573798187, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 177.934197999537, "min": -31.994401648640633, "max": 230.80019816756248, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.010114989154417428, "min": 0.008378281504318352, "max": 7.170091878732338, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.1025338178314996, "min": 1.0820825783848704, "max": 121.89156193844974, "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": "1690131704", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1690138932" }, "total": 7227.094410279, "count": 1, "self": 0.5406771950001712, "children": { "run_training.setup": { "total": 0.03387568599998758, "count": 1, "self": 0.03387568599998758 }, "TrainerController.start_learning": { "total": 7226.519857398, "count": 1, "self": 4.241300886135832, "children": { "TrainerController._reset_env": { "total": 5.605377068999985, "count": 1, "self": 5.605377068999985 }, "TrainerController.advance": { "total": 7216.579065499865, "count": 194471, "self": 4.210799172885345, "children": { "env_step": { "total": 5253.931546014923, "count": 194471, "self": 4934.258907916256, "children": { "SubprocessEnvManager._take_step": { "total": 317.17883631676534, "count": 194471, "self": 13.861422689872143, "children": { "TorchPolicy.evaluate": { "total": 303.3174136268932, "count": 187547, "self": 303.3174136268932 } } }, "workers": { "total": 2.493801781900885, "count": 194471, "self": 0.0, "children": { "worker_root": { "total": 7210.7183236569845, "count": 194471, "is_parallel": true, "self": 2621.511850755074, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005578925999998319, "count": 1, "is_parallel": true, "self": 0.004264917999961426, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013140080000368926, "count": 8, "is_parallel": true, "self": 0.0013140080000368926 } } }, "UnityEnvironment.step": { "total": 0.0485699969999871, "count": 1, "is_parallel": true, "self": 0.0005575790000023062, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000489198999986229, "count": 1, "is_parallel": true, "self": 0.000489198999986229 }, "communicator.exchange": { "total": 0.04569660199999248, "count": 1, "is_parallel": true, "self": 0.04569660199999248 }, "steps_from_proto": { "total": 0.001826617000006081, "count": 1, "is_parallel": true, "self": 0.0003665819999696396, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014600350000364415, "count": 8, "is_parallel": true, "self": 0.0014600350000364415 } } } } } } }, "UnityEnvironment.step": { "total": 4589.20647290191, "count": 194470, "is_parallel": true, "self": 101.9978814120077, "children": { "UnityEnvironment._generate_step_input": { "total": 66.23918016588752, "count": 194470, "is_parallel": true, "self": 66.23918016588752 }, "communicator.exchange": { "total": 4120.199638423996, "count": 194470, "is_parallel": true, "self": 4120.199638423996 }, "steps_from_proto": { "total": 300.7697729000196, "count": 194470, "is_parallel": true, "self": 61.30925270568426, "children": { "_process_rank_one_or_two_observation": { "total": 239.46052019433532, "count": 1555760, "is_parallel": true, "self": 239.46052019433532 } } } } } } } } } } }, "trainer_advance": { "total": 1958.4367203120564, "count": 194471, "self": 8.13576571609292, "children": { "process_trajectory": { "total": 337.79089529597263, "count": 194471, "self": 337.0852878179717, "children": { "RLTrainer._checkpoint": { "total": 0.7056074780009567, "count": 6, "self": 0.7056074780009567 } } }, "_update_policy": { "total": 1612.5100592999909, "count": 1397, "self": 1050.922811772968, "children": { "TorchPPOOptimizer.update": { "total": 561.5872475270229, "count": 68325, "self": 561.5872475270229 } } } } } } }, "trainer_threads": { "total": 8.739998520468362e-07, "count": 1, "self": 8.739998520468362e-07 }, "TrainerController._save_models": { "total": 0.09411306899983174, "count": 1, "self": 0.0013412210000751656, "children": { "RLTrainer._checkpoint": { "total": 0.09277184799975657, "count": 1, "self": 0.09277184799975657 } } } } } } }