{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3967175781726837, "min": 0.3967175781726837, "max": 1.470564365386963, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11888.83203125, "min": 11888.83203125, "max": 44611.0390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989884.0, "min": 29952.0, "max": 989884.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989884.0, "min": 29952.0, "max": 989884.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.40006300806999207, "min": -0.09921251982450485, "max": 0.4204469323158264, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 106.0167007446289, "min": -23.811004638671875, "max": 111.83888244628906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.028152400627732277, "min": -0.019910020753741264, "max": 0.2713225185871124, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.460386276245117, "min": -5.156695365905762, "max": 64.30343627929688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06571029606510863, "min": 0.06246582840168059, "max": 0.07274278134607659, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9199441449115209, "min": 0.48764772487679847, "max": 1.0694529890509632, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012535094126568374, "min": 0.000574469913561805, "max": 0.012535094126568374, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17549131777195723, "min": 0.004231217452013817, "max": 0.17549131777195723, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5094189254642854e-06, "min": 7.5094189254642854e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001051318649565, "min": 0.0001051318649565, "max": 0.003508599230467, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250310714285715, "min": 0.10250310714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350435000000001, "min": 1.3691136000000002, "max": 2.5695330000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002600604035714286, "min": 0.0002600604035714286, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036408456500000006, "min": 0.0036408456500000006, "max": 0.1169763467, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0089518828317523, "min": 0.0089518828317523, "max": 0.26469674706459045, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12532636523246765, "min": 0.12532636523246765, "max": 1.852877140045166, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 468.03225806451616, "min": 441.97058823529414, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29018.0, "min": 15984.0, "max": 34345.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3796158564232646, "min": -1.0000000521540642, "max": 1.4126153550468958, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 86.91579895466566, "min": -32.000001668930054, "max": 91.94159838557243, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3796158564232646, "min": -1.0000000521540642, "max": 1.4126153550468958, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 86.91579895466566, "min": -32.000001668930054, "max": 91.94159838557243, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.043639913245680784, "min": 0.043639913245680784, "max": 5.003246303647757, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7493145344778895, "min": 2.725948053455795, "max": 80.0519408583641, "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": "1711288654", "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=Pyramids Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1711291071" }, "total": 2417.012243529, "count": 1, "self": 0.5315161779994924, "children": { "run_training.setup": { "total": 0.05548073799991471, "count": 1, "self": 0.05548073799991471 }, "TrainerController.start_learning": { "total": 2416.4252466130006, "count": 1, "self": 1.8827543269735543, "children": { "TrainerController._reset_env": { "total": 2.3674357680001776, "count": 1, "self": 2.3674357680001776 }, "TrainerController.advance": { "total": 2412.081721876027, "count": 63521, "self": 1.9629994520751097, "children": { "env_step": { "total": 1716.0478175169528, "count": 63521, "self": 1548.9214127348123, "children": { "SubprocessEnvManager._take_step": { "total": 165.9626234850184, "count": 63521, "self": 5.728046202960286, "children": { "TorchPolicy.evaluate": { "total": 160.23457728205813, "count": 62563, "self": 160.23457728205813 } } }, "workers": { "total": 1.1637812971221138, "count": 63521, "self": 0.0, "children": { "worker_root": { "total": 2410.36389314002, "count": 63521, "is_parallel": true, "self": 1009.3111868550432, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002198155999849405, "count": 1, "is_parallel": true, "self": 0.0006615259999307455, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015366299999186595, "count": 8, "is_parallel": true, "self": 0.0015366299999186595 } } }, "UnityEnvironment.step": { "total": 0.05699184700006299, "count": 1, "is_parallel": true, "self": 0.0007437839994963724, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005449960003716114, "count": 1, "is_parallel": true, "self": 0.0005449960003716114 }, "communicator.exchange": { "total": 0.05379317300003095, "count": 1, "is_parallel": true, "self": 0.05379317300003095 }, "steps_from_proto": { "total": 0.0019098940001640585, "count": 1, "is_parallel": true, "self": 0.0004771490002895007, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014327449998745578, "count": 8, "is_parallel": true, "self": 0.0014327449998745578 } } } } } } }, "UnityEnvironment.step": { "total": 1401.052706284977, "count": 63520, "is_parallel": true, "self": 42.09226425889801, "children": { "UnityEnvironment._generate_step_input": { "total": 26.08116683407161, "count": 63520, "is_parallel": true, "self": 26.08116683407161 }, "communicator.exchange": { "total": 1218.0553012769765, "count": 63520, "is_parallel": true, "self": 1218.0553012769765 }, "steps_from_proto": { "total": 114.82397391503082, "count": 63520, "is_parallel": true, "self": 24.336441032039602, "children": { "_process_rank_one_or_two_observation": { "total": 90.48753288299122, "count": 508160, "is_parallel": true, "self": 90.48753288299122 } } } } } } } } } } }, "trainer_advance": { "total": 694.0709049069992, "count": 63521, "self": 3.707349038068969, "children": { "process_trajectory": { "total": 137.81577978093128, "count": 63521, "self": 137.60651652393108, "children": { "RLTrainer._checkpoint": { "total": 0.20926325700020243, "count": 2, "self": 0.20926325700020243 } } }, "_update_policy": { "total": 552.547776087999, "count": 443, "self": 322.60332443501966, "children": { "TorchPPOOptimizer.update": { "total": 229.9444516529793, "count": 22845, "self": 229.9444516529793 } } } } } } }, "trainer_threads": { "total": 1.1889997040270828e-06, "count": 1, "self": 1.1889997040270828e-06 }, "TrainerController._save_models": { "total": 0.09333345300001383, "count": 1, "self": 0.0016025850000005448, "children": { "RLTrainer._checkpoint": { "total": 0.09173086800001329, "count": 1, "self": 0.09173086800001329 } } } } } } }