{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.17021304368972778, "min": 0.1539728343486786, "max": 1.3595517873764038, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5065.5400390625, "min": 4552.6689453125, "max": 41243.36328125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999903.0, "min": 29952.0, "max": 2999903.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999903.0, "min": 29952.0, "max": 2999903.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7381600737571716, "min": -0.07790963351726532, "max": 0.8604459762573242, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 217.75721740722656, "min": -18.776222229003906, "max": 261.185791015625, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.009312840178608894, "min": -0.030547717586159706, "max": 0.493220716714859, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.7472877502441406, "min": -8.156240463256836, "max": 116.893310546875, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06889499702637772, "min": 0.06205537507984055, "max": 0.07341466344881889, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.964529958369288, "min": 0.4925004925121199, "max": 1.0939820609443511, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017195192937617235, "min": 0.000306173640556563, "max": 0.017195192937617235, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24073270112664127, "min": 0.0036740836866787563, "max": 0.24073270112664127, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5293994902333355e-06, "min": 1.5293994902333355e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1411592863266698e-05, "min": 2.1411592863266698e-05, "max": 0.0039275577908141, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050976666666667, "min": 0.10050976666666667, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4071367333333333, "min": 1.3897045333333333, "max": 2.722424566666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.092569000000008e-05, "min": 6.092569000000008e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008529596600000011, "min": 0.0008529596600000011, "max": 0.13092767141, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005617339629679918, "min": 0.005569758825004101, "max": 0.5724180936813354, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07864275574684143, "min": 0.07797662168741226, "max": 4.006926536560059, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 217.15555555555557, "min": 203.81632653061226, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29316.0, "min": 15984.0, "max": 33942.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.768125358802169, "min": -1.0000000521540642, "max": 1.7963698473695207, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 236.92879807949066, "min": -32.000001668930054, "max": 262.26999771595, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.768125358802169, "min": -1.0000000521540642, "max": 1.7963698473695207, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 236.92879807949066, "min": -32.000001668930054, "max": 262.26999771595, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.012666591170327321, "min": 0.012666591170327321, "max": 12.27653799764812, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.697323216823861, "min": 1.697323216823861, "max": 196.42460796236992, "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": "1662447824", "python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1662454411" }, "total": 6587.557609621001, "count": 1, "self": 0.43158080900047935, "children": { "run_training.setup": { "total": 0.041116280000096594, "count": 1, "self": 0.041116280000096594 }, "TrainerController.start_learning": { "total": 6587.084912532, "count": 1, "self": 4.093617772909965, "children": { "TrainerController._reset_env": { "total": 10.034562049000215, "count": 1, "self": 10.034562049000215 }, "TrainerController.advance": { "total": 6572.8661664290885, "count": 195445, "self": 4.357207250372994, "children": { "env_step": { "total": 4442.657812127812, "count": 195445, "self": 4133.5495562855995, "children": { "SubprocessEnvManager._take_step": { "total": 306.9304274270412, "count": 195445, "self": 13.648704349893706, "children": { "TorchPolicy.evaluate": { "total": 293.2817230771475, "count": 187563, "self": 101.5056719312579, "children": { "TorchPolicy.sample_actions": { "total": 191.7760511458896, "count": 187563, "self": 191.7760511458896 } } } } }, "workers": { "total": 2.1778284151707794, "count": 195445, "self": 0.0, "children": { "worker_root": { "total": 6575.837247262003, "count": 195445, "is_parallel": true, "self": 2744.0912431730085, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004482362000089779, "count": 1, "is_parallel": true, "self": 0.0033053060003567225, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011770559997330565, "count": 8, "is_parallel": true, "self": 0.0011770559997330565 } } }, "UnityEnvironment.step": { "total": 0.047571722000157024, "count": 1, "is_parallel": true, "self": 0.0005198150004162017, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005074379998859513, "count": 1, "is_parallel": true, "self": 0.0005074379998859513 }, "communicator.exchange": { "total": 0.044947228999944855, "count": 1, "is_parallel": true, "self": 0.044947228999944855 }, "steps_from_proto": { "total": 0.0015972399999100162, "count": 1, "is_parallel": true, "self": 0.0004100909995941038, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011871490003159124, "count": 8, "is_parallel": true, "self": 0.0011871490003159124 } } } } } } }, "UnityEnvironment.step": { "total": 3831.7460040889946, "count": 195444, "is_parallel": true, "self": 82.12580883405008, "children": { "UnityEnvironment._generate_step_input": { "total": 68.60133762810847, "count": 195444, "is_parallel": true, "self": 68.60133762810847 }, "communicator.exchange": { "total": 3405.7431312249937, "count": 195444, "is_parallel": true, "self": 3405.7431312249937 }, "steps_from_proto": { "total": 275.2757264018426, "count": 195444, "is_parallel": true, "self": 67.90399401437048, "children": { "_process_rank_one_or_two_observation": { "total": 207.3717323874721, "count": 1563552, "is_parallel": true, "self": 207.3717323874721 } } } } } } } } } } }, "trainer_advance": { "total": 2125.851147050904, "count": 195445, "self": 7.842430345783214, "children": { "process_trajectory": { "total": 492.1161961481348, "count": 195445, "self": 491.5359822361338, "children": { "RLTrainer._checkpoint": { "total": 0.5802139120009997, "count": 6, "self": 0.5802139120009997 } } }, "_update_policy": { "total": 1625.8925205569856, "count": 1391, "self": 647.0126908379023, "children": { "TorchPPOOptimizer.update": { "total": 978.8798297190833, "count": 68376, "self": 978.8798297190833 } } } } } } }, "trainer_threads": { "total": 1.0860003385460004e-06, "count": 1, "self": 1.0860003385460004e-06 }, "TrainerController._save_models": { "total": 0.09056519500063587, "count": 1, "self": 0.0016041810004026047, "children": { "RLTrainer._checkpoint": { "total": 0.08896101400023326, "count": 1, "self": 0.08896101400023326 } } } } } } }