{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.45258909463882446, "min": 0.43814757466316223, "max": 1.4355192184448242, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13541.4658203125, "min": 13022.3828125, "max": 43547.91015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989962.0, "min": 29932.0, "max": 989962.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989962.0, "min": 29932.0, "max": 989962.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.44720879197120667, "min": -0.06426848471164703, "max": 0.5496165752410889, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 118.9575424194336, "min": -15.42443561553955, "max": 153.343017578125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.007702940609306097, "min": -0.007702940609306097, "max": 0.28451427817344666, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.0489821434020996, "min": -2.0489821434020996, "max": 68.56793975830078, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0669531777329255, "min": 0.06418856106263504, "max": 0.07315886364709254, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9373444882609571, "min": 0.5799136728916079, "max": 1.0841321698389947, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014745346955216104, "min": 0.0009476999942720192, "max": 0.016067235355795774, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20643485737302544, "min": 0.013267799919808268, "max": 0.2410085303369366, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.63610459752143e-06, "min": 7.63610459752143e-06, "max": 0.0002948427017191, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001069054643653, "min": 0.0001069054643653, "max": 0.0036329905890031995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254533571428572, "min": 0.10254533571428572, "max": 0.19828090000000004, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356347, "min": 1.4356347, "max": 2.6109967999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026427903785714295, "min": 0.00026427903785714295, "max": 0.00982826191, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036999065300000016, "min": 0.0036999065300000016, "max": 0.12111858032, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010372297838330269, "min": 0.010372297838330269, "max": 0.5342194437980652, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14521217346191406, "min": 0.14521217346191406, "max": 4.2737555503845215, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 440.768115942029, "min": 338.7375, "max": 991.96875, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30413.0, "min": 16858.0, "max": 32427.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4432666468015616, "min": -0.867806299822405, "max": 1.584131635631187, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 99.58539862930775, "min": -27.76980159431696, "max": 129.66739765554667, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4432666468015616, "min": -0.867806299822405, "max": 1.584131635631187, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 99.58539862930775, "min": -27.76980159431696, "max": 129.66739765554667, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0474270057817668, "min": 0.04181055792480636, "max": 10.579345943251004, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.272463398941909, "min": 3.272463398941909, "max": 190.42822697851807, "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": "1685313227", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1685315495" }, "total": 2267.802993951, "count": 1, "self": 0.48006245299984585, "children": { "run_training.setup": { "total": 0.06018648700000995, "count": 1, "self": 0.06018648700000995 }, "TrainerController.start_learning": { "total": 2267.2627450110003, "count": 1, "self": 1.3122973627801002, "children": { "TrainerController._reset_env": { "total": 5.161210052000115, "count": 1, "self": 5.161210052000115 }, "TrainerController.advance": { "total": 2260.700102805219, "count": 63821, "self": 1.3514135983091364, "children": { "env_step": { "total": 1608.6989295230878, "count": 63821, "self": 1502.0613850281134, "children": { "SubprocessEnvManager._take_step": { "total": 105.84057527694586, "count": 63821, "self": 4.743688395873505, "children": { "TorchPolicy.evaluate": { "total": 101.09688688107235, "count": 62547, "self": 101.09688688107235 } } }, "workers": { "total": 0.7969692180286074, "count": 63821, "self": 0.0, "children": { "worker_root": { "total": 2262.1474579489345, "count": 63821, "is_parallel": true, "self": 872.0164611189084, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026017109998974774, "count": 1, "is_parallel": true, "self": 0.0007088199999998324, "children": { "_process_rank_one_or_two_observation": { "total": 0.001892890999897645, "count": 8, "is_parallel": true, "self": 0.001892890999897645 } } }, "UnityEnvironment.step": { "total": 0.048915236000084406, "count": 1, "is_parallel": true, "self": 0.0005412089994933922, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047054800006662845, "count": 1, "is_parallel": true, "self": 0.00047054800006662845 }, "communicator.exchange": { "total": 0.04589184800033763, "count": 1, "is_parallel": true, "self": 0.04589184800033763 }, "steps_from_proto": { "total": 0.0020116310001867532, "count": 1, "is_parallel": true, "self": 0.00039613199942323263, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016154990007635206, "count": 8, "is_parallel": true, "self": 0.0016154990007635206 } } } } } } }, "UnityEnvironment.step": { "total": 1390.130996830026, "count": 63820, "is_parallel": true, "self": 32.78478030020278, "children": { "UnityEnvironment._generate_step_input": { "total": 22.935648423909697, "count": 63820, "is_parallel": true, "self": 22.935648423909697 }, "communicator.exchange": { "total": 1234.7858288999519, "count": 63820, "is_parallel": true, "self": 1234.7858288999519 }, "steps_from_proto": { "total": 99.62473920596176, "count": 63820, "is_parallel": true, "self": 20.074739841846167, "children": { "_process_rank_one_or_two_observation": { "total": 79.54999936411559, "count": 510560, "is_parallel": true, "self": 79.54999936411559 } } } } } } } } } } }, "trainer_advance": { "total": 650.6497596838221, "count": 63821, "self": 2.627454681888139, "children": { "process_trajectory": { "total": 109.9296894859267, "count": 63821, "self": 109.71693135492615, "children": { "RLTrainer._checkpoint": { "total": 0.2127581310005553, "count": 2, "self": 0.2127581310005553 } } }, "_update_policy": { "total": 538.0926155160073, "count": 459, "self": 349.06568278599434, "children": { "TorchPPOOptimizer.update": { "total": 189.02693273001296, "count": 22758, "self": 189.02693273001296 } } } } } } }, "trainer_threads": { "total": 9.170007615466602e-07, "count": 1, "self": 9.170007615466602e-07 }, "TrainerController._save_models": { "total": 0.08913387400025385, "count": 1, "self": 0.001339168999948015, "children": { "RLTrainer._checkpoint": { "total": 0.08779470500030584, "count": 1, "self": 0.08779470500030584 } } } } } } }