{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.36540231108665466, "min": 0.35237109661102295, "max": 1.4025382995605469, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10921.14453125, "min": 10599.322265625, "max": 42547.40234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989991.0, "min": 29952.0, "max": 989991.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989991.0, "min": 29952.0, "max": 989991.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4872588515281677, "min": -0.16494891047477722, "max": 0.5501914620399475, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 132.04714965820312, "min": -39.092891693115234, "max": 150.75245666503906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0103200264275074, "min": -0.059089384973049164, "max": 0.5623935461044312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.796727180480957, "min": -15.895044326782227, "max": 133.2872772216797, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06771961427321437, "min": 0.06619681207204227, "max": 0.07259268245117802, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9480745998250011, "min": 0.4962719691095702, "max": 1.0552266287416512, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015742233409366146, "min": 0.00015430757161889494, "max": 0.015742233409366146, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22039126773112605, "min": 0.002160306002664529, "max": 0.22039126773112605, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.259926151485717e-06, "min": 7.259926151485717e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010163896612080004, "min": 0.00010163896612080004, "max": 0.0036326446891184992, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10241994285714284, "min": 0.10241994285714284, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4338791999999998, "min": 1.3886848, "max": 2.6108814999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025175229142857154, "min": 0.00025175229142857154, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035245320800000018, "min": 0.0035245320800000018, "max": 0.12110706185, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012736918404698372, "min": 0.012736918404698372, "max": 0.4962150752544403, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1783168613910675, "min": 0.1783168613910675, "max": 3.4735054969787598, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 393.2962962962963, "min": 342.0, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31857.0, "min": 15984.0, "max": 32735.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5325925772388775, "min": -1.0000000521540642, "max": 1.6350091748881614, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 124.13999875634909, "min": -30.99120159447193, "max": 142.24579821527004, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5325925772388775, "min": -1.0000000521540642, "max": 1.6350091748881614, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 124.13999875634909, "min": -30.99120159447193, "max": 142.24579821527004, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05251682504550209, "min": 0.051719465093779504, "max": 9.475311921909451, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.253862828685669, "min": 4.0633804200042505, "max": 151.60499075055122, "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": "1680099905", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1680102146" }, "total": 2240.934384835, "count": 1, "self": 0.47697263200007, "children": { "run_training.setup": { "total": 0.12030924700002288, "count": 1, "self": 0.12030924700002288 }, "TrainerController.start_learning": { "total": 2240.337102956, "count": 1, "self": 1.6590303649873022, "children": { "TrainerController._reset_env": { "total": 6.1382265900001585, "count": 1, "self": 6.1382265900001585 }, "TrainerController.advance": { "total": 2232.4418423110114, "count": 63669, "self": 1.7986669300603353, "children": { "env_step": { "total": 1588.3292310240759, "count": 63669, "self": 1462.7798970060157, "children": { "SubprocessEnvManager._take_step": { "total": 124.53532377808324, "count": 63669, "self": 5.374395466144051, "children": { "TorchPolicy.evaluate": { "total": 119.16092831193919, "count": 62556, "self": 119.16092831193919 } } }, "workers": { "total": 1.0140102399768693, "count": 63669, "self": 0.0, "children": { "worker_root": { "total": 2234.6997151060555, "count": 63669, "is_parallel": true, "self": 905.7528433140515, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018630849999681232, "count": 1, "is_parallel": true, "self": 0.0006120389998613973, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012510460001067258, "count": 8, "is_parallel": true, "self": 0.0012510460001067258 } } }, "UnityEnvironment.step": { "total": 0.04632593799988172, "count": 1, "is_parallel": true, "self": 0.0005560229997172428, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004958439999427355, "count": 1, "is_parallel": true, "self": 0.0004958439999427355 }, "communicator.exchange": { "total": 0.043483212999944953, "count": 1, "is_parallel": true, "self": 0.043483212999944953 }, "steps_from_proto": { "total": 0.0017908580002767849, "count": 1, "is_parallel": true, "self": 0.0004002970003966766, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013905609998801083, "count": 8, "is_parallel": true, "self": 0.0013905609998801083 } } } } } } }, "UnityEnvironment.step": { "total": 1328.946871792004, "count": 63668, "is_parallel": true, "self": 33.197774520190706, "children": { "UnityEnvironment._generate_step_input": { "total": 25.705521032912202, "count": 63668, "is_parallel": true, "self": 25.705521032912202 }, "communicator.exchange": { "total": 1167.1486335849859, "count": 63668, "is_parallel": true, "self": 1167.1486335849859 }, "steps_from_proto": { "total": 102.89494265391522, "count": 63668, "is_parallel": true, "self": 22.53683426210864, "children": { "_process_rank_one_or_two_observation": { "total": 80.35810839180658, "count": 509344, "is_parallel": true, "self": 80.35810839180658 } } } } } } } } } } }, "trainer_advance": { "total": 642.3139443568753, "count": 63669, "self": 3.140440655949533, "children": { "process_trajectory": { "total": 128.10260485293838, "count": 63669, "self": 127.88154415993813, "children": { "RLTrainer._checkpoint": { "total": 0.2210606930002541, "count": 2, "self": 0.2210606930002541 } } }, "_update_policy": { "total": 511.07089884798734, "count": 450, "self": 323.42897816295545, "children": { "TorchPPOOptimizer.update": { "total": 187.6419206850319, "count": 22815, "self": 187.6419206850319 } } } } } } }, "trainer_threads": { "total": 1.082000380847603e-06, "count": 1, "self": 1.082000380847603e-06 }, "TrainerController._save_models": { "total": 0.09800260800057004, "count": 1, "self": 0.0014748430003237445, "children": { "RLTrainer._checkpoint": { "total": 0.09652776500024629, "count": 1, "self": 0.09652776500024629 } } } } } } }