{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.16045987606048584, "min": 0.16045987606048584, "max": 1.5260409116744995, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4788.12255859375, "min": 4788.12255859375, "max": 46293.9765625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999946.0, "min": 29952.0, "max": 2999946.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999946.0, "min": 29952.0, "max": 2999946.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7394574880599976, "min": -0.13438574969768524, "max": 0.8234678506851196, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 215.18212890625, "min": -32.386966705322266, "max": 247.8638153076172, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.003540883306413889, "min": -0.021626511588692665, "max": 0.18829579651355743, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.0303970575332642, "min": -6.250061988830566, "max": 45.19099044799805, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06687768562447412, "min": 0.06420061187530055, "max": 0.07276679890734765, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9362875987426377, "min": 0.503802805162676, "max": 1.0905991646868642, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015652976910738896, "min": 7.588733751763217e-05, "max": 0.017017340752580722, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21914167675034454, "min": 0.0009865353877292183, "max": 0.25526011128871084, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4731923661119038e-06, "min": 1.4731923661119038e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0624693125566654e-05, "min": 2.0624693125566654e-05, "max": 0.0039274356908547995, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049103095238096, "min": 0.10049103095238096, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4068744333333334, "min": 1.3897045333333333, "max": 2.7091452, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.905399214285712e-05, "min": 5.905399214285712e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008267558899999997, "min": 0.0008267558899999997, "max": 0.13092360548, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007227752357721329, "min": 0.007227752357721329, "max": 0.29172483086586, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1011885330080986, "min": 0.1011885330080986, "max": 2.0420737266540527, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 248.91596638655463, "min": 226.27407407407406, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29621.0, "min": 15984.0, "max": 33594.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6838369608050634, "min": -1.0000000521540642, "max": 1.7634846003009723, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 200.37659833580256, "min": -32.000001668930054, "max": 237.4523979872465, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6838369608050634, "min": -1.0000000521540642, "max": 1.7634846003009723, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 200.37659833580256, "min": -32.000001668930054, "max": 237.4523979872465, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01871169538385364, "min": 0.01869043863072033, "max": 5.54133652895689, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.226691750678583, "min": 2.226691750678583, "max": 88.66138446331024, "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": "1693766086", "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 --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": "1693773550" }, "total": 7464.196976846, "count": 1, "self": 0.5451362140011042, "children": { "run_training.setup": { "total": 0.04165027799996324, "count": 1, "self": 0.04165027799996324 }, "TrainerController.start_learning": { "total": 7463.610190353999, "count": 1, "self": 4.932517323769389, "children": { "TrainerController._reset_env": { "total": 5.479297559000031, "count": 1, "self": 5.479297559000031 }, "TrainerController.advance": { "total": 7453.102992057229, "count": 193733, "self": 5.089813519285599, "children": { "env_step": { "total": 5442.89362370595, "count": 193733, "self": 5080.063369418969, "children": { "SubprocessEnvManager._take_step": { "total": 359.7998152251275, "count": 193733, "self": 15.33291352708261, "children": { "TorchPolicy.evaluate": { "total": 344.46690169804486, "count": 187564, "self": 344.46690169804486 } } }, "workers": { "total": 3.030439061853542, "count": 193733, "self": 0.0, "children": { "worker_root": { "total": 7445.39212622585, "count": 193733, "is_parallel": true, "self": 2743.98471133317, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0049740470000188, "count": 1, "is_parallel": true, "self": 0.003614544000015485, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013595030000033148, "count": 8, "is_parallel": true, "self": 0.0013595030000033148 } } }, "UnityEnvironment.step": { "total": 0.07938696700000492, "count": 1, "is_parallel": true, "self": 0.0005937839999887728, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004881570000065949, "count": 1, "is_parallel": true, "self": 0.0004881570000065949 }, "communicator.exchange": { "total": 0.07640568599998687, "count": 1, "is_parallel": true, "self": 0.07640568599998687 }, "steps_from_proto": { "total": 0.0018993400000226757, "count": 1, "is_parallel": true, "self": 0.00040903900003286253, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014903009999898131, "count": 8, "is_parallel": true, "self": 0.0014903009999898131 } } } } } } }, "UnityEnvironment.step": { "total": 4701.40741489268, "count": 193732, "is_parallel": true, "self": 108.14099685301244, "children": { "UnityEnvironment._generate_step_input": { "total": 70.70813504794171, "count": 193732, "is_parallel": true, "self": 70.70813504794171 }, "communicator.exchange": { "total": 4194.097456398821, "count": 193732, "is_parallel": true, "self": 4194.097456398821 }, "steps_from_proto": { "total": 328.4608265929048, "count": 193732, "is_parallel": true, "self": 65.9363583229869, "children": { "_process_rank_one_or_two_observation": { "total": 262.5244682699179, "count": 1549856, "is_parallel": true, "self": 262.5244682699179 } } } } } } } } } } }, "trainer_advance": { "total": 2005.1195548319934, "count": 193733, "self": 9.56850367816537, "children": { "process_trajectory": { "total": 346.76151133085637, "count": 193733, "self": 346.102720988858, "children": { "RLTrainer._checkpoint": { "total": 0.6587903419983832, "count": 6, "self": 0.6587903419983832 } } }, "_update_policy": { "total": 1648.7895398229716, "count": 1380, "self": 1071.3529030429665, "children": { "TorchPPOOptimizer.update": { "total": 577.4366367800051, "count": 68403, "self": 577.4366367800051 } } } } } } }, "trainer_threads": { "total": 9.800005500437692e-07, "count": 1, "self": 9.800005500437692e-07 }, "TrainerController._save_models": { "total": 0.09538243400038482, "count": 1, "self": 0.0014789450005991966, "children": { "RLTrainer._checkpoint": { "total": 0.09390348899978562, "count": 1, "self": 0.09390348899978562 } } } } } } }