{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6232019066810608, "min": 0.6061691641807556, "max": 1.4297406673431396, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18805.740234375, "min": 18185.07421875, "max": 43372.61328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2230353057384491, "min": -0.13554693758487701, "max": 0.23377932608127594, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 57.320072174072266, "min": -32.53126525878906, "max": 60.315067291259766, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.032576192170381546, "min": 0.0004582999972626567, "max": 0.19762437045574188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.372081756591797, "min": 0.11778309941291809, "max": 47.429847717285156, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06594617904231724, "min": 0.06464425736536325, "max": 0.07203416965975942, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9232465065924415, "min": 0.4974413671180868, "max": 1.0800178660703001, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011073433284938686, "min": 0.00016122149385192192, "max": 0.012516172327455671, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1550280659891416, "min": 0.002257100913926907, "max": 0.1752264125843794, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.70544743155e-06, "min": 7.70544743155e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010787626404169998, "min": 0.00010787626404169998, "max": 0.0033817754727416003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256845000000002, "min": 0.10256845000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359583000000002, "min": 1.3691136000000002, "max": 2.5272583999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026658815500000003, "min": 0.00026658815500000003, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037322341700000007, "min": 0.0037322341700000007, "max": 0.11275311416, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012006863951683044, "min": 0.012006863951683044, "max": 0.34805330634117126, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16809609532356262, "min": 0.16809609532356262, "max": 2.436373233795166, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 627.1875, "min": 573.0961538461538, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30105.0, "min": 15984.0, "max": 32971.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9977166365521649, "min": -1.0000000521540642, "max": 1.0036961168337326, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 47.89039855450392, "min": -32.000001668930054, "max": 52.1921980753541, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9977166365521649, "min": -1.0000000521540642, "max": 1.0036961168337326, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 47.89039855450392, "min": -32.000001668930054, "max": 52.1921980753541, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07902462910230194, "min": 0.0724002768390794, "max": 6.649603625759482, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.793182196910493, "min": 3.764814395632129, "max": 106.39365801215172, "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": "1683466905", "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=PyramidsTraining --no-graphics --force", "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": "1683468919" }, "total": 2013.1664303940006, "count": 1, "self": 0.5747286510004415, "children": { "run_training.setup": { "total": 0.04477705099998275, "count": 1, "self": 0.04477705099998275 }, "TrainerController.start_learning": { "total": 2012.5469246920002, "count": 1, "self": 1.3369282130115607, "children": { "TrainerController._reset_env": { "total": 3.8934825030000866, "count": 1, "self": 3.8934825030000866 }, "TrainerController.advance": { "total": 2007.222965865989, "count": 63231, "self": 1.3442064910404952, "children": { "env_step": { "total": 1384.266781222027, "count": 63231, "self": 1278.2852177460745, "children": { "SubprocessEnvManager._take_step": { "total": 105.23122875003628, "count": 63231, "self": 4.648131402934268, "children": { "TorchPolicy.evaluate": { "total": 100.58309734710201, "count": 62562, "self": 100.58309734710201 } } }, "workers": { "total": 0.7503347259162183, "count": 63231, "self": 0.0, "children": { "worker_root": { "total": 2007.9589403039881, "count": 63231, "is_parallel": true, "self": 837.6583247110157, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017093460000978666, "count": 1, "is_parallel": true, "self": 0.0004918699987683794, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012174760013294872, "count": 8, "is_parallel": true, "self": 0.0012174760013294872 } } }, "UnityEnvironment.step": { "total": 0.04988965100073983, "count": 1, "is_parallel": true, "self": 0.0005460140000650426, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004481880005187122, "count": 1, "is_parallel": true, "self": 0.0004481880005187122 }, "communicator.exchange": { "total": 0.04711498600045161, "count": 1, "is_parallel": true, "self": 0.04711498600045161 }, "steps_from_proto": { "total": 0.0017804629997044685, "count": 1, "is_parallel": true, "self": 0.0004018709978481638, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013785920018563047, "count": 8, "is_parallel": true, "self": 0.0013785920018563047 } } } } } } }, "UnityEnvironment.step": { "total": 1170.3006155929725, "count": 63230, "is_parallel": true, "self": 31.081045830806033, "children": { "UnityEnvironment._generate_step_input": { "total": 22.699983548968703, "count": 63230, "is_parallel": true, "self": 22.699983548968703 }, "communicator.exchange": { "total": 1019.9888556131609, "count": 63230, "is_parallel": true, "self": 1019.9888556131609 }, "steps_from_proto": { "total": 96.5307306000368, "count": 63230, "is_parallel": true, "self": 19.547159565066977, "children": { "_process_rank_one_or_two_observation": { "total": 76.98357103496983, "count": 505840, "is_parallel": true, "self": 76.98357103496983 } } } } } } } } } } }, "trainer_advance": { "total": 621.6119781529214, "count": 63231, "self": 2.3058016328031954, "children": { "process_trajectory": { "total": 102.87141877011072, "count": 63231, "self": 102.59009208111001, "children": { "RLTrainer._checkpoint": { "total": 0.2813266890007071, "count": 2, "self": 0.2813266890007071 } } }, "_update_policy": { "total": 516.4347577500075, "count": 437, "self": 333.69552560097964, "children": { "TorchPPOOptimizer.update": { "total": 182.73923214902788, "count": 22857, "self": 182.73923214902788 } } } } } } }, "trainer_threads": { "total": 9.34000127017498e-07, "count": 1, "self": 9.34000127017498e-07 }, "TrainerController._save_models": { "total": 0.09354717599944706, "count": 1, "self": 0.0013952249992144061, "children": { "RLTrainer._checkpoint": { "total": 0.09215195100023266, "count": 1, "self": 0.09215195100023266 } } } } } } }