{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8558732271194458, "min": 0.8137807250022888, "max": 0.9180604219436646, "count": 7 }, "Pyramids.Policy.Entropy.sum": { "value": 25169.51953125, "min": 21353.60546875, "max": 27953.103515625, "count": 7 }, "Pyramids.Step.mean": { "value": 299923.0, "min": 119919.0, "max": 299923.0, "count": 7 }, "Pyramids.Step.sum": { "value": 299923.0, "min": 119919.0, "max": 299923.0, "count": 7 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.06007738783955574, "min": -0.07483578473329544, "max": -0.04461627081036568, "count": 7 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -14.418573379516602, "min": -18.035423278808594, "max": -10.380054473876953, "count": 7 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.023354116827249527, "min": 0.023354116827249527, "max": 0.09894673526287079, "count": 7 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.604988098144531, "min": 5.604988098144531, "max": 20.284080505371094, "count": 7 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06987728989210215, "min": 0.06437342379162089, "max": 0.07039508132033204, "count": 7 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.908404768597328, "min": 0.4759986376065277, "max": 0.9701358893986348, "count": 7 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0020141706624677907, "min": 0.0008949574194232755, "max": 0.0020289772764095987, "count": 7 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.026184218612081277, "min": 0.00986391368833429, "max": 0.026376704593324782, "count": 7 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00021457685155131542, "min": 0.00021457685155131542, "max": 0.00026742451085849997, "count": 7 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0027894990701671004, "min": 0.0018719715760095, "max": 0.003381555272815, "count": 7 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1715256076923077, "min": 0.1715256076923077, "max": 0.1891415, "count": 7 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.2298329000000003, "min": 1.3239904999999998, "max": 2.5271850000000002, "count": 7 }, "Pyramids.Policy.Beta.mean": { "value": 0.007155408208461537, "min": 0.007155408208461537, "max": 0.00891523585, "count": 7 }, "Pyramids.Policy.Beta.sum": { "value": 0.09302030670999999, "min": 0.06240665095, "max": 0.11274578149999999, "count": 7 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.02323523350059986, "min": 0.02323523350059986, "max": 0.07129208743572235, "count": 7 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.30205804109573364, "min": 0.30205804109573364, "max": 0.5963388085365295, "count": 7 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 957.2692307692307, "min": 934.3823529411765, "max": 995.375, "count": 7 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 24889.0, "min": 15926.0, "max": 32429.0, "count": 7 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.6502077479202014, "min": -0.8713125488720834, "max": -0.6502077479202014, "count": 7 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -16.905401445925236, "min": -27.608201697468758, "max": -13.941000781953335, "count": 7 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.6502077479202014, "min": -0.8713125488720834, "max": -0.6502077479202014, "count": 7 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -16.905401445925236, "min": -27.608201697468758, "max": -13.941000781953335, "count": 7 }, "Pyramids.Policy.RndReward.mean": { "value": 0.23212681119688428, "min": 0.23212681119688428, "max": 0.7777849617414176, "count": 7 }, "Pyramids.Policy.RndReward.sum": { "value": 6.035297091118991, "min": 6.035297091118991, "max": 19.24327414482832, "count": 7 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 7 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 7 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1742379513", "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 --resume", "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": "1742380221" }, "total": 707.3125104920001, "count": 1, "self": 0.6893042520000563, "children": { "run_training.setup": { "total": 0.031890160999978434, "count": 1, "self": 0.031890160999978434 }, "TrainerController.start_learning": { "total": 706.5913160790001, "count": 1, "self": 0.5270033520077959, "children": { "TrainerController._reset_env": { "total": 3.681693709000001, "count": 1, "self": 3.681693709000001 }, "TrainerController.advance": { "total": 702.3806202409924, "count": 13388, "self": 0.6119752209780245, "children": { "env_step": { "total": 454.7579597560118, "count": 13388, "self": 416.1234082770269, "children": { "SubprocessEnvManager._take_step": { "total": 38.31387631799805, "count": 13388, "self": 1.8819059059957226, "children": { "TorchPolicy.evaluate": { "total": 36.43197041200233, "count": 13330, "self": 36.43197041200233 } } }, "workers": { "total": 0.3206751609868661, "count": 13387, "self": 0.0, "children": { "worker_root": { "total": 704.8143985960137, "count": 13387, "is_parallel": true, "self": 330.85930494801414, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002585437999982787, "count": 1, "is_parallel": true, "self": 0.000984953999818572, "children": { "_process_rank_one_or_two_observation": { "total": 0.001600484000164215, "count": 8, "is_parallel": true, "self": 0.001600484000164215 } } }, "UnityEnvironment.step": { "total": 0.15027168500000698, "count": 1, "is_parallel": true, "self": 0.0007526140000209125, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000489043000015954, "count": 1, "is_parallel": true, "self": 0.000489043000015954 }, "communicator.exchange": { "total": 0.1472614289999683, "count": 1, "is_parallel": true, "self": 0.1472614289999683 }, "steps_from_proto": { "total": 0.0017685990000018137, "count": 1, "is_parallel": true, "self": 0.00039566899988585646, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013729300001159572, "count": 8, "is_parallel": true, "self": 0.0013729300001159572 } } } } } } }, "UnityEnvironment.step": { "total": 373.95509364799955, "count": 13386, "is_parallel": true, "self": 10.409551639995243, "children": { "UnityEnvironment._generate_step_input": { "total": 7.1573088170003984, "count": 13386, "is_parallel": true, "self": 7.1573088170003984 }, "communicator.exchange": { "total": 327.1678706630105, "count": 13386, "is_parallel": true, "self": 327.1678706630105 }, "steps_from_proto": { "total": 29.220362527993416, "count": 13386, "is_parallel": true, "self": 6.5208721150120255, "children": { "_process_rank_one_or_two_observation": { "total": 22.69949041298139, "count": 107088, "is_parallel": true, "self": 22.69949041298139 } } } } } } } } } } }, "trainer_advance": { "total": 247.01068526400252, "count": 13387, "self": 0.8988366850040848, "children": { "process_trajectory": { "total": 38.45324754599801, "count": 13387, "self": 38.45324754599801 }, "_update_policy": { "total": 207.65860103300042, "count": 88, "self": 84.24850257600417, "children": { "TorchPPOOptimizer.update": { "total": 123.41009845699625, "count": 4836, "self": 123.41009845699625 } } } } } } }, "trainer_threads": { "total": 2.0679999579442665e-06, "count": 1, "self": 2.0679999579442665e-06 }, "TrainerController._save_models": { "total": 0.0019967089999681775, "count": 1, "self": 4.665500000555767e-05, "children": { "RLTrainer._checkpoint": { "total": 0.0019500539999626199, "count": 1, "self": 0.0019500539999626199 } } } } } } }