{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5755035281181335, "min": 0.5755035281181335, "max": 1.3457599878311157, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17274.314453125, "min": 17274.314453125, "max": 40824.9765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989965.0, "min": 29934.0, "max": 989965.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989965.0, "min": 29934.0, "max": 989965.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3740314245223999, "min": -0.09790082275867462, "max": 0.4331112802028656, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 99.86638641357422, "min": -23.496196746826172, "max": 114.77449035644531, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.014618164859712124, "min": 0.007712248247116804, "max": 0.2608974575996399, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.903049945831299, "min": 1.858651876449585, "max": 62.87628936767578, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06874456165297445, "min": 0.06553845572866127, "max": 0.07280256075164009, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9624238631416422, "min": 0.6499889588550746, "max": 1.0629590376338456, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014459529346606274, "min": 0.0005788153134915513, "max": 0.014459529346606274, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20243341085248784, "min": 0.008103414388881718, "max": 0.21385399750336848, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.36304040282857e-06, "min": 7.36304040282857e-06, "max": 0.00029534923488358885, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010308256563959998, "min": 0.00010308256563959998, "max": 0.003632483589172199, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024543142857143, "min": 0.1024543142857143, "max": 0.19844974444444446, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343604000000003, "min": 1.4343604000000003, "max": 2.6108278000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025518599714285706, "min": 0.00025518599714285706, "max": 0.00984512947, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003572603959999999, "min": 0.003572603959999999, "max": 0.12110169722, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01083696074783802, "min": 0.01083696074783802, "max": 0.40983912348747253, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15171745419502258, "min": 0.15171745419502258, "max": 3.688552141189575, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 475.25, "min": 443.33846153846156, "max": 997.2903225806451, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28515.0, "min": 16988.0, "max": 33145.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3971186167860434, "min": -0.9336710178082989, "max": 1.4653085454234056, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 82.42999839037657, "min": -28.943801552057266, "max": 102.57159817963839, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3971186167860434, "min": -0.9336710178082989, "max": 1.4653085454234056, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 82.42999839037657, "min": -28.943801552057266, "max": 102.57159817963839, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05348837014075104, "min": 0.052162178997449314, "max": 6.805311347047488, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1558138383043115, "min": 3.1558138383043115, "max": 122.49560424685478, "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": "1714987523", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/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": "1714989618" }, "total": 2095.4815599820004, "count": 1, "self": 0.532393592000517, "children": { "run_training.setup": { "total": 0.06479178799963847, "count": 1, "self": 0.06479178799963847 }, "TrainerController.start_learning": { "total": 2094.884374602, "count": 1, "self": 1.243420371938555, "children": { "TrainerController._reset_env": { "total": 2.150551863999681, "count": 1, "self": 2.150551863999681 }, "TrainerController.advance": { "total": 2091.4049414150622, "count": 63491, "self": 1.2697004688734523, "children": { "env_step": { "total": 1476.5017367411574, "count": 63491, "self": 1349.9055700841163, "children": { "SubprocessEnvManager._take_step": { "total": 125.846002401031, "count": 63491, "self": 4.517726816969116, "children": { "TorchPolicy.evaluate": { "total": 121.32827558406188, "count": 62561, "self": 121.32827558406188 } } }, "workers": { "total": 0.7501642560100663, "count": 63491, "self": 0.0, "children": { "worker_root": { "total": 2090.2356305689736, "count": 63491, "is_parallel": true, "self": 855.2621999869398, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020729819998450694, "count": 1, "is_parallel": true, "self": 0.0006209369985299418, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014520450013151276, "count": 8, "is_parallel": true, "self": 0.0014520450013151276 } } }, "UnityEnvironment.step": { "total": 0.0717715840000892, "count": 1, "is_parallel": true, "self": 0.0009076659998754621, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004552059999696212, "count": 1, "is_parallel": true, "self": 0.0004552059999696212 }, "communicator.exchange": { "total": 0.06827417400018021, "count": 1, "is_parallel": true, "self": 0.06827417400018021 }, "steps_from_proto": { "total": 0.0021345380000639125, "count": 1, "is_parallel": true, "self": 0.0007419100002152845, "children": { "_process_rank_one_or_two_observation": { "total": 0.001392627999848628, "count": 8, "is_parallel": true, "self": 0.001392627999848628 } } } } } } }, "UnityEnvironment.step": { "total": 1234.9734305820339, "count": 63490, "is_parallel": true, "self": 33.61027658319199, "children": { "UnityEnvironment._generate_step_input": { "total": 22.601945954059374, "count": 63490, "is_parallel": true, "self": 22.601945954059374 }, "communicator.exchange": { "total": 1081.6372338398232, "count": 63490, "is_parallel": true, "self": 1081.6372338398232 }, "steps_from_proto": { "total": 97.12397420495927, "count": 63490, "is_parallel": true, "self": 19.03926692532241, "children": { "_process_rank_one_or_two_observation": { "total": 78.08470727963686, "count": 507920, "is_parallel": true, "self": 78.08470727963686 } } } } } } } } } } }, "trainer_advance": { "total": 613.6335042050314, "count": 63491, "self": 2.451564287121073, "children": { "process_trajectory": { "total": 121.22475816592305, "count": 63491, "self": 121.03044891592253, "children": { "RLTrainer._checkpoint": { "total": 0.19430925000051502, "count": 2, "self": 0.19430925000051502 } } }, "_update_policy": { "total": 489.95718175198726, "count": 457, "self": 288.8557027069446, "children": { "TorchPPOOptimizer.update": { "total": 201.10147904504265, "count": 22785, "self": 201.10147904504265 } } } } } } }, "trainer_threads": { "total": 8.679999154992402e-07, "count": 1, "self": 8.679999154992402e-07 }, "TrainerController._save_models": { "total": 0.08546008299981622, "count": 1, "self": 0.0014393500005098758, "children": { "RLTrainer._checkpoint": { "total": 0.08402073299930635, "count": 1, "self": 0.08402073299930635 } } } } } } }