{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2585674822330475, "min": 0.2585674822330475, "max": 1.4343658685684204, "count": 52 }, "Pyramids.Policy.Entropy.sum": { "value": 7769.435546875, "min": 7769.435546875, "max": 43512.921875, "count": 52 }, "Pyramids.Step.mean": { "value": 1559910.0, "min": 29932.0, "max": 1559910.0, "count": 52 }, "Pyramids.Step.sum": { "value": 1559910.0, "min": 29932.0, "max": 1559910.0, "count": 52 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7120975852012634, "min": -0.0966479554772377, "max": 0.8078252673149109, "count": 52 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 204.37200927734375, "min": -23.388805389404297, "max": 239.11627197265625, "count": 52 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02349431812763214, "min": -0.010132369585335255, "max": 0.5131722688674927, "count": 52 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.7428693771362305, "min": -2.6040189266204834, "max": 121.62183380126953, "count": 52 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06929148523473176, "min": 0.06591292409066023, "max": 0.07444632382070564, "count": 52 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9700807932862446, "min": 0.49046260858742097, "max": 1.1166948573105846, "count": 52 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013823598967304227, "min": 0.00075751971279787, "max": 0.015891998541812547, "count": 52 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19353038554225918, "min": 0.00909023655357444, "max": 0.22750905266730115, "count": 52 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0001454535158012262, "min": 0.0001454535158012262, "max": 0.00029838354339596195, "count": 52 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0020363492212171668, "min": 0.0020363492212171668, "max": 0.0041178469273844, "count": 52 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1484844880952381, "min": 0.1484844880952381, "max": 0.19946118095238097, "count": 52 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.0787828333333334, "min": 1.3962282666666668, "max": 2.8726156, "count": 52 }, "Pyramids.Policy.Beta.mean": { "value": 0.004853600360714285, "min": 0.004853600360714285, "max": 0.009946171977142856, "count": 52 }, "Pyramids.Policy.Beta.sum": { "value": 0.06795040505, "min": 0.06795040505, "max": 0.13727429844, "count": 52 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01134662888944149, "min": 0.010678512044250965, "max": 0.6673876643180847, "count": 52 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15885280072689056, "min": 0.14949916303157806, "max": 4.671713829040527, "count": 52 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 280.14285714285717, "min": 237.66935483870967, "max": 991.7058823529412, "count": 52 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29415.0, "min": 16859.0, "max": 32546.0, "count": 52 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6652339439628259, "min": -0.9266000515781343, "max": 1.7623306316954475, "count": 52 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 176.51479806005955, "min": -30.575001657009125, "max": 218.52899833023548, "count": 52 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6652339439628259, "min": -0.9266000515781343, "max": 1.7623306316954475, "count": 52 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 176.51479806005955, "min": -30.575001657009125, "max": 218.52899833023548, "count": 52 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03314085415208093, "min": 0.03157237428538979, "max": 13.340079325086931, "count": 52 }, "Pyramids.Policy.RndReward.sum": { "value": 3.5129305401205784, "min": 3.3496761987917125, "max": 226.7813485264778, "count": 52 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 52 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 52 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1713159301", "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": "1713163489" }, "total": 4187.753306795999, "count": 1, "self": 0.42962933299986616, "children": { "run_training.setup": { "total": 0.09357171800002106, "count": 1, "self": 0.09357171800002106 }, "TrainerController.start_learning": { "total": 4187.2301057449995, "count": 1, "self": 2.798326442052712, "children": { "TrainerController._reset_env": { "total": 2.850449174000005, "count": 1, "self": 2.850449174000005 }, "TrainerController.advance": { "total": 4181.428096397947, "count": 101517, "self": 2.8603124938854307, "children": { "env_step": { "total": 3062.942711217058, "count": 101517, "self": 2815.252957749914, "children": { "SubprocessEnvManager._take_step": { "total": 245.9881999682275, "count": 101517, "self": 9.095964646128778, "children": { "TorchPolicy.evaluate": { "total": 236.8922353220987, "count": 98487, "self": 236.8922353220987 } } }, "workers": { "total": 1.7015534989163825, "count": 101516, "self": 0.0, "children": { "worker_root": { "total": 4177.676120085969, "count": 101516, "is_parallel": true, "self": 1595.9008368888772, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0036257440001463692, "count": 1, "is_parallel": true, "self": 0.0009711320003589208, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026546119997874484, "count": 8, "is_parallel": true, "self": 0.0026546119997874484 } } }, "UnityEnvironment.step": { "total": 0.05932383699973798, "count": 1, "is_parallel": true, "self": 0.0006929509995643457, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005419970002549235, "count": 1, "is_parallel": true, "self": 0.0005419970002549235 }, "communicator.exchange": { "total": 0.056292797999958566, "count": 1, "is_parallel": true, "self": 0.056292797999958566 }, "steps_from_proto": { "total": 0.0017960909999601427, "count": 1, "is_parallel": true, "self": 0.00039285499951802194, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014032360004421207, "count": 8, "is_parallel": true, "self": 0.0014032360004421207 } } } } } } }, "UnityEnvironment.step": { "total": 2581.775283197092, "count": 101515, "is_parallel": true, "self": 63.775332475256164, "children": { "UnityEnvironment._generate_step_input": { "total": 45.14642791294318, "count": 101515, "is_parallel": true, "self": 45.14642791294318 }, "communicator.exchange": { "total": 2280.219568807065, "count": 101515, "is_parallel": true, "self": 2280.219568807065 }, "steps_from_proto": { "total": 192.63395400182753, "count": 101515, "is_parallel": true, "self": 40.19532957305819, "children": { "_process_rank_one_or_two_observation": { "total": 152.43862442876934, "count": 812120, "is_parallel": true, "self": 152.43862442876934 } } } } } } } } } } }, "trainer_advance": { "total": 1115.625072687004, "count": 101516, "self": 5.421500640120939, "children": { "process_trajectory": { "total": 235.5162257248785, "count": 101516, "self": 235.1938868888774, "children": { "RLTrainer._checkpoint": { "total": 0.3223388360011086, "count": 3, "self": 0.3223388360011086 } } }, "_update_policy": { "total": 874.6873463220045, "count": 725, "self": 517.2746742849613, "children": { "TorchPPOOptimizer.update": { "total": 357.4126720370432, "count": 35907, "self": 357.4126720370432 } } } } } } }, "trainer_threads": { "total": 1.574999259901233e-06, "count": 1, "self": 1.574999259901233e-06 }, "TrainerController._save_models": { "total": 0.15323215599983087, "count": 1, "self": 0.0022455429998444743, "children": { "RLTrainer._checkpoint": { "total": 0.1509866129999864, "count": 1, "self": 0.1509866129999864 } } } } } } }