{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.43720242381095886, "min": 0.43720242381095886, "max": 1.4303398132324219, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12941.19140625, "min": 12941.19140625, "max": 43390.7890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989882.0, "min": 29952.0, "max": 989882.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989882.0, "min": 29952.0, "max": 989882.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4182339906692505, "min": -0.11693937331438065, "max": 0.4645828306674957, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 112.50494384765625, "min": -28.065448760986328, "max": 125.90194702148438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.027908990159630775, "min": -0.04473424330353737, "max": 0.182784304022789, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.507518291473389, "min": -12.122980117797852, "max": 43.86823272705078, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06946025908525502, "min": 0.06301827772126888, "max": 0.07351974557818776, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9724436271935702, "min": 0.4855232238291158, "max": 1.0362409316265828, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017324575300812113, "min": 8.412653702876808e-05, "max": 0.017889288832225313, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24254405421136957, "min": 0.0011777715184027532, "max": 0.25446993922620703, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.560483194157145e-06, "min": 7.560483194157145e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010584676471820002, "min": 0.00010584676471820002, "max": 0.0036328804890399004, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252012857142857, "min": 0.10252012857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352818, "min": 1.3691136000000002, "max": 2.6109601000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002617608442857144, "min": 0.0002617608442857144, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036646518200000016, "min": 0.0036646518200000016, "max": 0.12111491399, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010757037438452244, "min": 0.010726222768425941, "max": 0.41071945428848267, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15059852600097656, "min": 0.15016712248325348, "max": 2.8750362396240234, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 410.06666666666666, "min": 369.6219512195122, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30755.0, "min": 15984.0, "max": 32802.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5098959745963414, "min": -1.0000000521540642, "max": 1.5649862847711942, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 113.24219809472561, "min": -32.000001668930054, "max": 125.68899834156036, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5098959745963414, "min": -1.0000000521540642, "max": 1.5649862847711942, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 113.24219809472561, "min": -32.000001668930054, "max": 125.68899834156036, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04510228737296226, "min": 0.04180632956345884, "max": 7.98756505176425, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3826715529721696, "min": 3.329371457512025, "max": 127.801040828228, "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": "1742549512", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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 --torch-device cuda --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1742551805" }, "total": 2292.4740300000003, "count": 1, "self": 1.001347452000573, "children": { "run_training.setup": { "total": 0.023166481999965072, "count": 1, "self": 0.023166481999965072 }, "TrainerController.start_learning": { "total": 2291.449516066, "count": 1, "self": 1.4027518740012965, "children": { "TrainerController._reset_env": { "total": 3.1273657149999963, "count": 1, "self": 3.1273657149999963 }, "TrainerController.advance": { "total": 2286.7838432349986, "count": 63594, "self": 1.4478279310333164, "children": { "env_step": { "total": 1592.5637231140054, "count": 63594, "self": 1431.2720389249262, "children": { "SubprocessEnvManager._take_step": { "total": 160.45802642805018, "count": 63594, "self": 4.710121787071557, "children": { "TorchPolicy.evaluate": { "total": 155.74790464097862, "count": 62554, "self": 155.74790464097862 } } }, "workers": { "total": 0.8336577610289169, "count": 63594, "self": 0.0, "children": { "worker_root": { "total": 2286.1069317289985, "count": 63594, "is_parallel": true, "self": 971.4820647049064, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00569976199994926, "count": 1, "is_parallel": true, "self": 0.004212240999891037, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014875210000582229, "count": 8, "is_parallel": true, "self": 0.0014875210000582229 } } }, "UnityEnvironment.step": { "total": 0.04955776000008427, "count": 1, "is_parallel": true, "self": 0.0005949330002295028, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004306329999508307, "count": 1, "is_parallel": true, "self": 0.0004306329999508307 }, "communicator.exchange": { "total": 0.04671783799994955, "count": 1, "is_parallel": true, "self": 0.04671783799994955 }, "steps_from_proto": { "total": 0.0018143559999543868, "count": 1, "is_parallel": true, "self": 0.0005205229999774019, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012938329999769849, "count": 8, "is_parallel": true, "self": 0.0012938329999769849 } } } } } } }, "UnityEnvironment.step": { "total": 1314.624867024092, "count": 63593, "is_parallel": true, "self": 32.84691686615611, "children": { "UnityEnvironment._generate_step_input": { "total": 23.577951244928954, "count": 63593, "is_parallel": true, "self": 23.577951244928954 }, "communicator.exchange": { "total": 1157.6780891230428, "count": 63593, "is_parallel": true, "self": 1157.6780891230428 }, "steps_from_proto": { "total": 100.52190978996418, "count": 63593, "is_parallel": true, "self": 20.622254472032296, "children": { "_process_rank_one_or_two_observation": { "total": 79.89965531793189, "count": 508744, "is_parallel": true, "self": 79.89965531793189 } } } } } } } } } } }, "trainer_advance": { "total": 692.7722921899599, "count": 63594, "self": 2.7847412829477207, "children": { "process_trajectory": { "total": 132.65599233000944, "count": 63594, "self": 132.33780991500976, "children": { "RLTrainer._checkpoint": { "total": 0.3181824149996828, "count": 2, "self": 0.3181824149996828 } } }, "_update_policy": { "total": 557.3315585770027, "count": 447, "self": 305.7532253620202, "children": { "TorchPPOOptimizer.update": { "total": 251.57833321498254, "count": 22800, "self": 251.57833321498254 } } } } } } }, "trainer_threads": { "total": 1.4060001376492437e-06, "count": 1, "self": 1.4060001376492437e-06 }, "TrainerController._save_models": { "total": 0.1355538359998718, "count": 1, "self": 0.002349521999803983, "children": { "RLTrainer._checkpoint": { "total": 0.13320431400006782, "count": 1, "self": 0.13320431400006782 } } } } } } }