{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.39161038398742676, "min": 0.3892679512500763, "max": 1.4873254299163818, "count": 40 }, "Pyramids.Policy.Entropy.sum": { "value": 9837.2529296875, "min": 9660.0732421875, "max": 39027.41796875, "count": 40 }, "Pyramids.Step.mean": { "value": 999947.0, "min": 24960.0, "max": 999947.0, "count": 40 }, "Pyramids.Step.sum": { "value": 999947.0, "min": 24960.0, "max": 999947.0, "count": 40 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5577706098556519, "min": -0.10050802677869797, "max": 0.6519138216972351, "count": 40 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 128.28724670410156, "min": -20.302621841430664, "max": 154.50357055664062, "count": 40 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012868339195847511, "min": 0.005618416238576174, "max": 0.4353194832801819, "count": 40 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.9597179889678955, "min": 1.18548583984375, "max": 86.1932601928711, "count": 40 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07048654987496168, "min": 0.06373778805896614, "max": 0.07526202773604179, "count": 40 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8458385984995402, "min": 0.3981097612286458, "max": 0.9031443328325015, "count": 40 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015799540449532086, "min": 0.0018626144759534152, "max": 0.015799540449532086, "count": 40 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18959448539438503, "min": 0.013386984317590738, "max": 0.18959448539438503, "count": 40 }, "Pyramids.Policy.LearningRate.mean": { "value": 3.6753987749000005e-06, "min": 3.6753987749000005e-06, "max": 0.0002957568014144, "count": 40 }, "Pyramids.Policy.LearningRate.sum": { "value": 4.4104785298800004e-05, "min": 4.4104785298800004e-05, "max": 0.0029269388243538, "count": 40 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1012251, "min": 0.1012251, "max": 0.1985856, "count": 40 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.2147012, "min": 1.1771136000000002, "max": 2.1756462, "count": 40 }, "Pyramids.Policy.Beta.mean": { "value": 0.00013238749, "min": 0.00013238749, "max": 0.00985870144, "count": 40 }, "Pyramids.Policy.Beta.sum": { "value": 0.00158864988, "min": 0.00158864988, "max": 0.09758705538, "count": 40 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008755751885473728, "min": 0.008497790433466434, "max": 0.5597033500671387, "count": 40 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10506902635097504, "min": 0.09569065272808075, "max": 3.358220100402832, "count": 40 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 328.0133333333333, "min": 296.6024096385542, "max": 999.0, "count": 40 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 24601.0, "min": 15984.0, "max": 31968.0, "count": 40 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5919653083880743, "min": -1.0000000521540642, "max": 1.6551903460219681, "count": 40 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 119.39739812910557, "min": -32.000001668930054, "max": 137.38079871982336, "count": 40 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5919653083880743, "min": -1.0000000521540642, "max": 1.6551903460219681, "count": 40 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 119.39739812910557, "min": -32.000001668930054, "max": 137.38079871982336, "count": 40 }, "Pyramids.Policy.RndReward.mean": { "value": 0.029587139872989308, "min": 0.027370002108606666, "max": 10.958400049246848, "count": 40 }, "Pyramids.Policy.RndReward.sum": { "value": 2.219035490474198, "min": 2.0833714419277385, "max": 175.33440078794956, "count": 40 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1716730011", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=Pyramids3 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1716732293" }, "total": 2281.9890105399995, "count": 1, "self": 0.48976659899926744, "children": { "run_training.setup": { "total": 0.05181883299974288, "count": 1, "self": 0.05181883299974288 }, "TrainerController.start_learning": { "total": 2281.4474251080005, "count": 1, "self": 1.397449222970863, "children": { "TrainerController._reset_env": { "total": 2.4167706079997515, "count": 1, "self": 2.4167706079997515 }, "TrainerController.advance": { "total": 2277.54545750003, "count": 63983, "self": 1.414589613111275, "children": { "env_step": { "total": 1637.3200555290337, "count": 63983, "self": 1504.1230797850653, "children": { "SubprocessEnvManager._take_step": { "total": 132.3463596849656, "count": 63983, "self": 4.706007048048832, "children": { "TorchPolicy.evaluate": { "total": 127.64035263691676, "count": 62552, "self": 127.64035263691676 } } }, "workers": { "total": 0.8506160590027321, "count": 63983, "self": 0.0, "children": { "worker_root": { "total": 2276.1567987270205, "count": 63983, "is_parallel": true, "self": 895.521353034901, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020543230002658674, "count": 1, "is_parallel": true, "self": 0.0005948570001237385, "children": { "_process_rank_one_or_two_observation": { "total": 0.001459466000142129, "count": 8, "is_parallel": true, "self": 0.001459466000142129 } } }, "UnityEnvironment.step": { "total": 0.04804656100031934, "count": 1, "is_parallel": true, "self": 0.0006337940008052101, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005115260000820854, "count": 1, "is_parallel": true, "self": 0.0005115260000820854 }, "communicator.exchange": { "total": 0.0452873549998003, "count": 1, "is_parallel": true, "self": 0.0452873549998003 }, "steps_from_proto": { "total": 0.0016138859996317478, "count": 1, "is_parallel": true, "self": 0.0003391109994481667, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012747750001835811, "count": 8, "is_parallel": true, "self": 0.0012747750001835811 } } } } } } }, "UnityEnvironment.step": { "total": 1380.6354456921194, "count": 63982, "is_parallel": true, "self": 34.525767212177016, "children": { "UnityEnvironment._generate_step_input": { "total": 23.840742276008314, "count": 63982, "is_parallel": true, "self": 23.840742276008314 }, "communicator.exchange": { "total": 1223.704609926931, "count": 63982, "is_parallel": true, "self": 1223.704609926931 }, "steps_from_proto": { "total": 98.56432627700315, "count": 63982, "is_parallel": true, "self": 20.079214052069347, "children": { "_process_rank_one_or_two_observation": { "total": 78.4851122249338, "count": 511856, "is_parallel": true, "self": 78.4851122249338 } } } } } } } } } } }, "trainer_advance": { "total": 638.810812357885, "count": 63983, "self": 2.6279607609471896, "children": { "process_trajectory": { "total": 129.42429262893575, "count": 63983, "self": 129.22864745593552, "children": { "RLTrainer._checkpoint": { "total": 0.19564517300023, "count": 2, "self": 0.19564517300023 } } }, "_update_policy": { "total": 506.75855896800203, "count": 454, "self": 297.20957183900373, "children": { "TorchPPOOptimizer.update": { "total": 209.5489871289983, "count": 22839, "self": 209.5489871289983 } } } } } } }, "trainer_threads": { "total": 8.770002750679851e-07, "count": 1, "self": 8.770002750679851e-07 }, "TrainerController._save_models": { "total": 0.08774689999972907, "count": 1, "self": 0.0014895069998601684, "children": { "RLTrainer._checkpoint": { "total": 0.0862573929998689, "count": 1, "self": 0.0862573929998689 } } } } } } }