{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5031710863113403, "min": 0.5031710863113403, "max": 1.4903753995895386, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15264.1982421875, "min": 15264.1982421875, "max": 45212.02734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989979.0, "min": 29952.0, "max": 989979.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989979.0, "min": 29952.0, "max": 989979.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.22171305119991302, "min": -0.09936545789241791, "max": 0.27778708934783936, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 56.31511688232422, "min": -23.94707489013672, "max": 71.94685363769531, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0048962971195578575, "min": 0.0048962971195578575, "max": 0.3788735270500183, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.243659496307373, "min": 1.243659496307373, "max": 91.30851745605469, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.070088814740995, "min": 0.06592614136216249, "max": 0.07395314150538382, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9812434063739299, "min": 0.4990641479517585, "max": 1.0074290353861894, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01106673844419891, "min": 3.0746316199108414e-05, "max": 0.01288747329475454, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.15493433821878475, "min": 0.00043044842678751776, "max": 0.1933120994213181, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.688197437300002e-06, "min": 7.688197437300002e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010763476412220002, "min": 0.00010763476412220002, "max": 0.0031402136532622, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256270000000002, "min": 0.10256270000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358778000000003, "min": 1.3886848, "max": 2.3588536, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026601373, "min": 0.00026601373, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037241922200000003, "min": 0.0037241922200000003, "max": 0.10469910622000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013294554315507412, "min": 0.013294554315507412, "max": 0.523243248462677, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18612375855445862, "min": 0.18612375855445862, "max": 3.6627025604248047, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 573.3157894736842, "min": 516.1296296296297, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32679.0, "min": 15984.0, "max": 33120.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9698571082470673, "min": -1.0000000521540642, "max": 1.187499970473625, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 54.311998061835766, "min": -31.99920167028904, "max": 64.12499840557575, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9698571082470673, "min": -1.0000000521540642, "max": 1.187499970473625, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 54.311998061835766, "min": -31.99920167028904, "max": 64.12499840557575, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07861246664521916, "min": 0.07750708504048547, "max": 11.522968675941229, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.402298132132273, "min": 4.169718474688125, "max": 184.36749881505966, "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": "1700655015", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training 2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700657276" }, "total": 2260.808455814, "count": 1, "self": 0.4760207500003162, "children": { "run_training.setup": { "total": 0.04212735500004783, "count": 1, "self": 0.04212735500004783 }, "TrainerController.start_learning": { "total": 2260.2903077089995, "count": 1, "self": 1.4252282159031893, "children": { "TrainerController._reset_env": { "total": 5.114430971999354, "count": 1, "self": 5.114430971999354 }, "TrainerController.advance": { "total": 2253.6769748790966, "count": 63306, "self": 1.5299453430825452, "children": { "env_step": { "total": 1586.6602766650576, "count": 63306, "self": 1447.0657044692261, "children": { "SubprocessEnvManager._take_step": { "total": 138.71192185084328, "count": 63306, "self": 4.820160322748052, "children": { "TorchPolicy.evaluate": { "total": 133.89176152809523, "count": 62568, "self": 133.89176152809523 } } }, "workers": { "total": 0.8826503449881784, "count": 63306, "self": 0.0, "children": { "worker_root": { "total": 2255.2954823369573, "count": 63306, "is_parallel": true, "self": 939.2218950749357, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019254640001236112, "count": 1, "is_parallel": true, "self": 0.0006251940021684277, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013002699979551835, "count": 8, "is_parallel": true, "self": 0.0013002699979551835 } } }, "UnityEnvironment.step": { "total": 0.09234835600000224, "count": 1, "is_parallel": true, "self": 0.0007140890002119704, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005510259998118272, "count": 1, "is_parallel": true, "self": 0.0005510259998118272 }, "communicator.exchange": { "total": 0.08912456300004123, "count": 1, "is_parallel": true, "self": 0.08912456300004123 }, "steps_from_proto": { "total": 0.0019586779999372084, "count": 1, "is_parallel": true, "self": 0.0003944770014641108, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015642009984730976, "count": 8, "is_parallel": true, "self": 0.0015642009984730976 } } } } } } }, "UnityEnvironment.step": { "total": 1316.0735872620216, "count": 63305, "is_parallel": true, "self": 35.0853134739682, "children": { "UnityEnvironment._generate_step_input": { "total": 25.522476065018964, "count": 63305, "is_parallel": true, "self": 25.522476065018964 }, "communicator.exchange": { "total": 1151.4365955930407, "count": 63305, "is_parallel": true, "self": 1151.4365955930407 }, "steps_from_proto": { "total": 104.02920212999379, "count": 63305, "is_parallel": true, "self": 21.264445424690166, "children": { "_process_rank_one_or_two_observation": { "total": 82.76475670530363, "count": 506440, "is_parallel": true, "self": 82.76475670530363 } } } } } } } } } } }, "trainer_advance": { "total": 665.4867528709565, "count": 63306, "self": 2.6932269949256806, "children": { "process_trajectory": { "total": 133.82721107503858, "count": 63306, "self": 133.65430523603936, "children": { "RLTrainer._checkpoint": { "total": 0.1729058389992133, "count": 2, "self": 0.1729058389992133 } } }, "_update_policy": { "total": 528.9663148009922, "count": 439, "self": 319.9470520519026, "children": { "TorchPPOOptimizer.update": { "total": 209.01926274908965, "count": 22872, "self": 209.01926274908965 } } } } } } }, "trainer_threads": { "total": 1.0570001904852688e-06, "count": 1, "self": 1.0570001904852688e-06 }, "TrainerController._save_models": { "total": 0.0736725850001676, "count": 1, "self": 0.0013871739993192023, "children": { "RLTrainer._checkpoint": { "total": 0.0722854110008484, "count": 1, "self": 0.0722854110008484 } } } } } } }