{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1675896942615509, "min": 0.15619903802871704, "max": 1.4463694095611572, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5046.4609375, "min": 4658.47998046875, "max": 43877.0625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999968.0, "min": 29952.0, "max": 2999968.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999968.0, "min": 29952.0, "max": 2999968.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8542202711105347, "min": -0.11359960585832596, "max": 0.9074349999427795, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 257.9745178222656, "min": -27.377504348754883, "max": 284.02716064453125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0017805934185162187, "min": -0.015386064536869526, "max": 0.4931967258453369, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.5377392172813416, "min": -4.261940002441406, "max": 116.88762664794922, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06635366058459481, "min": 0.0645563912216208, "max": 0.07512656123676084, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9953049087689221, "min": 0.5004124569247648, "max": 1.0954213114980353, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014018549785258409, "min": 0.000143824416789731, "max": 0.016372136348287488, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21027824677887613, "min": 0.001582068584687041, "max": 0.22920990887602483, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5089861637044447e-06, "min": 1.5089861637044447e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.263479245556667e-05, "min": 2.263479245556667e-05, "max": 0.0038024851325050334, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050296222222223, "min": 0.10050296222222223, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5075444333333334, "min": 1.3962282666666668, "max": 2.7674949666666664, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.0245925999999996e-05, "min": 6.0245925999999996e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.00090368889, "min": 0.00090368889, "max": 0.12677274717, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006820132955908775, "min": 0.006820132955908775, "max": 0.5500985383987427, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10230199247598648, "min": 0.09635388106107712, "max": 3.850689649581909, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 210.13475177304966, "min": 181.472049689441, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29629.0, "min": 15984.0, "max": 34066.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7896689990876427, "min": -1.0000000521540642, "max": 1.8185279357322255, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 254.13299787044525, "min": -31.99760165810585, "max": 292.7829976528883, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7896689990876427, "min": -1.0000000521540642, "max": 1.8185279357322255, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 254.13299787044525, "min": -31.99760165810585, "max": 292.7829976528883, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01493767273080868, "min": 0.01290985809554858, "max": 11.261916616931558, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.1211495277748327, "min": 2.0756597265681194, "max": 180.19066587090492, "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": "1741521100", "python_version": "3.10.12 (main, Feb 4 2025, 14:57:36) [GCC 11.4.0]", "command_line_arguments": "/home/jonathan/projects/hf-deep-rl/.venv/bin/mlagents-learn ./PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids1 --no-graphics", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1741525579" }, "total": 4479.381298983, "count": 1, "self": 0.3202905060006742, "children": { "run_training.setup": { "total": 0.013251334999949904, "count": 1, "self": 0.013251334999949904 }, "TrainerController.start_learning": { "total": 4479.047757142, "count": 1, "self": 2.9265605919745212, "children": { "TrainerController._reset_env": { "total": 5.0582509610001125, "count": 1, "self": 5.0582509610001125 }, "TrainerController.advance": { "total": 4471.004294981024, "count": 195368, "self": 2.4496963197616424, "children": { "env_step": { "total": 2861.3375824730874, "count": 195368, "self": 2268.380089427163, "children": { "SubprocessEnvManager._take_step": { "total": 591.0812078229856, "count": 195368, "self": 8.49595003307877, "children": { "TorchPolicy.evaluate": { "total": 582.5852577899068, "count": 187563, "self": 582.5852577899068 } } }, "workers": { "total": 1.8762852229388045, "count": 195368, "self": 0.0, "children": { "worker_root": { "total": 4472.690290674141, "count": 195368, "is_parallel": true, "self": 2379.7203438792685, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010615250000682863, "count": 1, "is_parallel": true, "self": 0.00039092400038498454, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006706009996833018, "count": 8, "is_parallel": true, "self": 0.0006706009996833018 } } }, "UnityEnvironment.step": { "total": 0.02468785900009607, "count": 1, "is_parallel": true, "self": 0.00016123800014611334, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00014534399997501168, "count": 1, "is_parallel": true, "self": 0.00014534399997501168 }, "communicator.exchange": { "total": 0.023884611000084988, "count": 1, "is_parallel": true, "self": 0.023884611000084988 }, "steps_from_proto": { "total": 0.0004966659998899559, "count": 1, "is_parallel": true, "self": 0.00014127399958852038, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003553920003014355, "count": 8, "is_parallel": true, "self": 0.0003553920003014355 } } } } } } }, "UnityEnvironment.step": { "total": 2092.969946794872, "count": 195367, "is_parallel": true, "self": 31.08566460283373, "children": { "UnityEnvironment._generate_step_input": { "total": 21.262918701040007, "count": 195367, "is_parallel": true, "self": 21.262918701040007 }, "communicator.exchange": { "total": 1957.5482230889838, "count": 195367, "is_parallel": true, "self": 1957.5482230889838 }, "steps_from_proto": { "total": 83.07314040201459, "count": 195367, "is_parallel": true, "self": 19.14613925719118, "children": { "_process_rank_one_or_two_observation": { "total": 63.92700114482341, "count": 1562936, "is_parallel": true, "self": 63.92700114482341 } } } } } } } } } } }, "trainer_advance": { "total": 1607.2170161881752, "count": 195368, "self": 5.098827644121229, "children": { "process_trajectory": { "total": 290.62955342507007, "count": 195368, "self": 290.2455951470695, "children": { "RLTrainer._checkpoint": { "total": 0.38395827800059124, "count": 6, "self": 0.38395827800059124 } } }, "_update_policy": { "total": 1311.488635118984, "count": 1389, "self": 571.7987836369844, "children": { "TorchPPOOptimizer.update": { "total": 739.6898514819995, "count": 68361, "self": 739.6898514819995 } } } } } } }, "trainer_threads": { "total": 4.2400006350362673e-07, "count": 1, "self": 4.2400006350362673e-07 }, "TrainerController._save_models": { "total": 0.05865018400072586, "count": 1, "self": 0.0008864540004651644, "children": { "RLTrainer._checkpoint": { "total": 0.057763730000260693, "count": 1, "self": 0.057763730000260693 } } } } } } }