{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4196625351905823, "min": 0.4196625351905823, "max": 1.41886568069458, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12596.5908203125, "min": 12596.5908203125, "max": 43042.7109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989919.0, "min": 29898.0, "max": 989919.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989919.0, "min": 29898.0, "max": 989919.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6028959155082703, "min": -0.1111360490322113, "max": 0.6234883666038513, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 168.81085205078125, "min": -26.672651290893555, "max": 174.5767364501953, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012983628548681736, "min": 0.004052899777889252, "max": 0.4872196316719055, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.635416030883789, "min": 1.1348118782043457, "max": 115.47105407714844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06972227239748463, "min": 0.06561141521554978, "max": 0.07464767450513057, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9761118135647848, "min": 0.4860330713627159, "max": 1.056745916826413, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016303230630694002, "min": 0.0008567029595568368, "max": 0.01683679746305903, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22824522882971604, "min": 0.011993841433795715, "max": 0.2357151644828264, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.67941172594286e-06, "min": 7.67941172594286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010751176416320005, "min": 0.00010751176416320005, "max": 0.0036347398884200998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255977142857144, "min": 0.10255977142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358368000000001, "min": 1.3886848, "max": 2.6115798999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026572116571428584, "min": 0.00026572116571428584, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037200963200000018, "min": 0.0037200963200000018, "max": 0.12117683201000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011492903344333172, "min": 0.011332242749631405, "max": 0.6197848320007324, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16090065240859985, "min": 0.15865139663219452, "max": 4.338493824005127, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 311.3958333333333, "min": 304.5979381443299, "max": 989.7058823529412, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29894.0, "min": 16825.0, "max": 32432.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6677603953673195, "min": -0.9274313007481396, "max": 1.6677603953673195, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 160.10499795526266, "min": -29.677801623940468, "max": 160.10499795526266, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6677603953673195, "min": -0.9274313007481396, "max": 1.6677603953673195, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 160.10499795526266, "min": -29.677801623940468, "max": 160.10499795526266, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03719392929648772, "min": 0.03719392929648772, "max": 12.45234901414198, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.570617212462821, "min": 3.473447735304944, "max": 211.68993324041367, "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": "1698732842", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1698735033" }, "total": 2190.5253614989997, "count": 1, "self": 0.4876275909996366, "children": { "run_training.setup": { "total": 0.042965344000094774, "count": 1, "self": 0.042965344000094774 }, "TrainerController.start_learning": { "total": 2189.994768564, "count": 1, "self": 1.2236730989411626, "children": { "TrainerController._reset_env": { "total": 3.6002044649999334, "count": 1, "self": 3.6002044649999334 }, "TrainerController.advance": { "total": 2185.097524904059, "count": 64058, "self": 1.3282011960759519, "children": { "env_step": { "total": 1556.632285402965, "count": 64058, "self": 1430.7925285808421, "children": { "SubprocessEnvManager._take_step": { "total": 125.04808728407374, "count": 64058, "self": 4.428189619183968, "children": { "TorchPolicy.evaluate": { "total": 120.61989766488978, "count": 62552, "self": 120.61989766488978 } } }, "workers": { "total": 0.7916695380490637, "count": 64058, "self": 0.0, "children": { "worker_root": { "total": 2185.447332159048, "count": 64058, "is_parallel": true, "self": 863.043152776132, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018261499999425723, "count": 1, "is_parallel": true, "self": 0.0005855839999640011, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012405659999785712, "count": 8, "is_parallel": true, "self": 0.0012405659999785712 } } }, "UnityEnvironment.step": { "total": 0.04940018799993595, "count": 1, "is_parallel": true, "self": 0.0005784789996141626, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004306780001570587, "count": 1, "is_parallel": true, "self": 0.0004306780001570587 }, "communicator.exchange": { "total": 0.046824899000057485, "count": 1, "is_parallel": true, "self": 0.046824899000057485 }, "steps_from_proto": { "total": 0.0015661320001072454, "count": 1, "is_parallel": true, "self": 0.00032841400025063194, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012377179998566135, "count": 8, "is_parallel": true, "self": 0.0012377179998566135 } } } } } } }, "UnityEnvironment.step": { "total": 1322.404179382916, "count": 64057, "is_parallel": true, "self": 34.29504546689782, "children": { "UnityEnvironment._generate_step_input": { "total": 23.579009642987103, "count": 64057, "is_parallel": true, "self": 23.579009642987103 }, "communicator.exchange": { "total": 1168.1666875630647, "count": 64057, "is_parallel": true, "self": 1168.1666875630647 }, "steps_from_proto": { "total": 96.36343670996644, "count": 64057, "is_parallel": true, "self": 18.975003317015762, "children": { "_process_rank_one_or_two_observation": { "total": 77.38843339295067, "count": 512456, "is_parallel": true, "self": 77.38843339295067 } } } } } } } } } } }, "trainer_advance": { "total": 627.1370383050178, "count": 64058, "self": 2.4065252870377662, "children": { "process_trajectory": { "total": 119.53899423998155, "count": 64058, "self": 119.37757685298175, "children": { "RLTrainer._checkpoint": { "total": 0.16141738699980124, "count": 2, "self": 0.16141738699980124 } } }, "_update_policy": { "total": 505.19151877799845, "count": 457, "self": 301.67014457896767, "children": { "TorchPPOOptimizer.update": { "total": 203.5213741990308, "count": 22779, "self": 203.5213741990308 } } } } } } }, "trainer_threads": { "total": 9.57999873207882e-07, "count": 1, "self": 9.57999873207882e-07 }, "TrainerController._save_models": { "total": 0.07336513800009925, "count": 1, "self": 0.0012650480002776021, "children": { "RLTrainer._checkpoint": { "total": 0.07210008999982165, "count": 1, "self": 0.07210008999982165 } } } } } } }