{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4849931299686432, "min": 0.4849931299686432, "max": 1.4617489576339722, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14534.2744140625, "min": 14534.2744140625, "max": 44343.6171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989944.0, "min": 29952.0, "max": 989944.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989944.0, "min": 29952.0, "max": 989944.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.44973358511924744, "min": -0.10290933400392532, "max": 0.570103645324707, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 123.22700500488281, "min": -24.801149368286133, "max": 157.34860229492188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.05136988312005997, "min": -0.05136988312005997, "max": 0.3580794930458069, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -14.075347900390625, "min": -14.075347900390625, "max": 84.86483764648438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0680983506345434, "min": 0.06509623204004125, "max": 0.0729792808483992, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9533769088836077, "min": 0.5073702113385762, "max": 1.0666662966250442, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01531557868327668, "min": 0.00031360778427866494, "max": 0.016716500662109217, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21441810156587351, "min": 0.0028224700585079846, "max": 0.24823321242001842, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.247347584250002e-06, "min": 7.247347584250002e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010146286617950002, "min": 0.00010146286617950002, "max": 0.0031368077543975, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10241575000000003, "min": 0.10241575000000003, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4338205000000004, "min": 1.3886848, "max": 2.4013283999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002513334250000001, "min": 0.0002513334250000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035186679500000015, "min": 0.0035186679500000015, "max": 0.10458568974999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0048655057325959206, "min": 0.004860612563788891, "max": 0.4736633598804474, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.06811708211898804, "min": 0.06811708211898804, "max": 3.315643548965454, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 368.71604938271605, "min": 350.54545454545456, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29866.0, "min": 15984.0, "max": 35167.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.483088873234796, "min": -1.0000000521540642, "max": 1.6379761695861816, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 120.13019873201847, "min": -30.999201610684395, "max": 137.58999824523926, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.483088873234796, "min": -1.0000000521540642, "max": 1.6379761695861816, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 120.13019873201847, "min": -30.999201610684395, "max": 137.58999824523926, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.018742875021416694, "min": 0.01831325851283812, "max": 10.621151620522141, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 1.5181728767347522, "min": 1.4725718807749217, "max": 169.93842592835426, "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": "1741648031", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1741650320" }, "total": 2288.4332473330005, "count": 1, "self": 0.47578670400116607, "children": { "run_training.setup": { "total": 0.020574058999955014, "count": 1, "self": 0.020574058999955014 }, "TrainerController.start_learning": { "total": 2287.9368865699994, "count": 1, "self": 1.4758147910238222, "children": { "TrainerController._reset_env": { "total": 2.099275698999918, "count": 1, "self": 2.099275698999918 }, "TrainerController.advance": { "total": 2284.273111573976, "count": 63723, "self": 1.6630028159202084, "children": { "env_step": { "total": 1599.7098786010465, "count": 63723, "self": 1437.0821860721494, "children": { "SubprocessEnvManager._take_step": { "total": 161.77856773892654, "count": 63723, "self": 4.987737537873272, "children": { "TorchPolicy.evaluate": { "total": 156.79083020105327, "count": 62550, "self": 156.79083020105327 } } }, "workers": { "total": 0.8491247899705741, "count": 63723, "self": 0.0, "children": { "worker_root": { "total": 2282.369480734049, "count": 63723, "is_parallel": true, "self": 963.1068658810123, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021109549998072907, "count": 1, "is_parallel": true, "self": 0.000699127999268967, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014118270005383238, "count": 8, "is_parallel": true, "self": 0.0014118270005383238 } } }, "UnityEnvironment.step": { "total": 0.051930184999946505, "count": 1, "is_parallel": true, "self": 0.0006210209999153449, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004708159999609052, "count": 1, "is_parallel": true, "self": 0.0004708159999609052 }, "communicator.exchange": { "total": 0.04891846300006364, "count": 1, "is_parallel": true, "self": 0.04891846300006364 }, "steps_from_proto": { "total": 0.0019198850000066159, "count": 1, "is_parallel": true, "self": 0.0004255870003362361, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014942979996703798, "count": 8, "is_parallel": true, "self": 0.0014942979996703798 } } } } } } }, "UnityEnvironment.step": { "total": 1319.2626148530367, "count": 63722, "is_parallel": true, "self": 32.1315479059931, "children": { "UnityEnvironment._generate_step_input": { "total": 23.022852285060708, "count": 63722, "is_parallel": true, "self": 23.022852285060708 }, "communicator.exchange": { "total": 1166.3759513868672, "count": 63722, "is_parallel": true, "self": 1166.3759513868672 }, "steps_from_proto": { "total": 97.73226327511566, "count": 63722, "is_parallel": true, "self": 20.348952180821016, "children": { "_process_rank_one_or_two_observation": { "total": 77.38331109429464, "count": 509776, "is_parallel": true, "self": 77.38331109429464 } } } } } } } } } } }, "trainer_advance": { "total": 682.9002301570094, "count": 63723, "self": 2.770866145983291, "children": { "process_trajectory": { "total": 129.33958363203647, "count": 63723, "self": 129.13331545803567, "children": { "RLTrainer._checkpoint": { "total": 0.20626817400079744, "count": 2, "self": 0.20626817400079744 } } }, "_update_policy": { "total": 550.7897803789897, "count": 442, "self": 301.2279141460226, "children": { "TorchPPOOptimizer.update": { "total": 249.56186623296708, "count": 22848, "self": 249.56186623296708 } } } } } } }, "trainer_threads": { "total": 8.139995770761743e-07, "count": 1, "self": 8.139995770761743e-07 }, "TrainerController._save_models": { "total": 0.08868369199990411, "count": 1, "self": 0.001496696999311098, "children": { "RLTrainer._checkpoint": { "total": 0.08718699500059301, "count": 1, "self": 0.08718699500059301 } } } } } } }