{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3066718578338623, "min": 0.2893904149532318, "max": 1.4698185920715332, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9131.4609375, "min": 8695.603515625, "max": 44588.41796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989985.0, "min": 29952.0, "max": 989985.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989985.0, "min": 29952.0, "max": 989985.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6080477237701416, "min": -0.15932567417621613, "max": 0.7327609062194824, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 171.46945190429688, "min": -37.76018524169922, "max": 211.7678985595703, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.006747949868440628, "min": -0.02458539605140686, "max": 0.4148670434951782, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.9029219150543213, "min": -6.957666873931885, "max": 98.323486328125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06754543235102436, "min": 0.06474447751857547, "max": 0.07369184458888464, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0131814852653656, "min": 0.5158429121221925, "max": 1.0500620032447234, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01739208238892519, "min": 0.0007052905423405618, "max": 0.018550731861937998, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.26088123583387784, "min": 0.008463486508086742, "max": 0.27826097792906995, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.542397485900002e-06, "min": 7.542397485900002e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011313596228850003, "min": 0.00011313596228850003, "max": 0.003382717172427701, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251410000000002, "min": 0.10251410000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5377115000000003, "min": 1.3886848, "max": 2.5277301, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002611585900000001, "min": 0.0002611585900000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003917378850000001, "min": 0.003917378850000001, "max": 0.11278447276999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011926326900720596, "min": 0.011926326900720596, "max": 0.4563201069831848, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17889490723609924, "min": 0.17786893248558044, "max": 3.1942408084869385, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 284.752380952381, "min": 266.86725663716817, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29899.0, "min": 15984.0, "max": 33256.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6602358264883734, "min": -1.0000000521540642, "max": 1.7139053348717945, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 175.98499760776758, "min": -30.261001639068127, "max": 191.95739750564098, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6602358264883734, "min": -1.0000000521540642, "max": 1.7139053348717945, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 175.98499760776758, "min": -30.261001639068127, "max": 191.95739750564098, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03469302946067951, "min": 0.03469302946067951, "max": 9.748336830176413, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.677461122832028, "min": 3.677461122832028, "max": 155.9733892828226, "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": "1684119274", "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": "1684121411" }, "total": 2136.9016088000003, "count": 1, "self": 0.4246431589999702, "children": { "run_training.setup": { "total": 0.03638583000019935, "count": 1, "self": 0.03638583000019935 }, "TrainerController.start_learning": { "total": 2136.440579811, "count": 1, "self": 1.2471470641357882, "children": { "TrainerController._reset_env": { "total": 4.4761023289997866, "count": 1, "self": 4.4761023289997866 }, "TrainerController.advance": { "total": 2130.6284641378647, "count": 64196, "self": 1.2857482269650973, "children": { "env_step": { "total": 1502.6509267179204, "count": 64196, "self": 1400.4863885109758, "children": { "SubprocessEnvManager._take_step": { "total": 101.42811584192532, "count": 64196, "self": 4.482402277906203, "children": { "TorchPolicy.evaluate": { "total": 96.94571356401912, "count": 62567, "self": 96.94571356401912 } } }, "workers": { "total": 0.7364223650192798, "count": 64196, "self": 0.0, "children": { "worker_root": { "total": 2131.9518716390335, "count": 64196, "is_parallel": true, "self": 837.1257247291819, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017627170000196202, "count": 1, "is_parallel": true, "self": 0.0005442329998004425, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012184840002191777, "count": 8, "is_parallel": true, "self": 0.0012184840002191777 } } }, "UnityEnvironment.step": { "total": 0.07853424200038717, "count": 1, "is_parallel": true, "self": 0.0008476200000586687, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004865570003858011, "count": 1, "is_parallel": true, "self": 0.0004865570003858011 }, "communicator.exchange": { "total": 0.07544739200011463, "count": 1, "is_parallel": true, "self": 0.07544739200011463 }, "steps_from_proto": { "total": 0.0017526729998280643, "count": 1, "is_parallel": true, "self": 0.00035192000041206484, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014007529994159995, "count": 8, "is_parallel": true, "self": 0.0014007529994159995 } } } } } } }, "UnityEnvironment.step": { "total": 1294.8261469098516, "count": 64195, "is_parallel": true, "self": 30.649774108837846, "children": { "UnityEnvironment._generate_step_input": { "total": 21.762033531959787, "count": 64195, "is_parallel": true, "self": 21.762033531959787 }, "communicator.exchange": { "total": 1148.0287329120251, "count": 64195, "is_parallel": true, "self": 1148.0287329120251 }, "steps_from_proto": { "total": 94.38560635702879, "count": 64195, "is_parallel": true, "self": 18.921950378291513, "children": { "_process_rank_one_or_two_observation": { "total": 75.46365597873728, "count": 513560, "is_parallel": true, "self": 75.46365597873728 } } } } } } } } } } }, "trainer_advance": { "total": 626.6917891929793, "count": 64196, "self": 2.3591495549985666, "children": { "process_trajectory": { "total": 104.65718356297475, "count": 64196, "self": 104.4625739629746, "children": { "RLTrainer._checkpoint": { "total": 0.19460960000014893, "count": 2, "self": 0.19460960000014893 } } }, "_update_policy": { "total": 519.675456075006, "count": 450, "self": 335.80775448099394, "children": { "TorchPPOOptimizer.update": { "total": 183.86770159401203, "count": 22860, "self": 183.86770159401203 } } } } } } }, "trainer_threads": { "total": 9.120003596763127e-07, "count": 1, "self": 9.120003596763127e-07 }, "TrainerController._save_models": { "total": 0.08886536799946043, "count": 1, "self": 0.0014281129988376051, "children": { "RLTrainer._checkpoint": { "total": 0.08743725500062283, "count": 1, "self": 0.08743725500062283 } } } } } } }