{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5377862453460693, "min": 0.5339899063110352, "max": 1.4641063213348389, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16056.146484375, "min": 15994.06640625, "max": 44415.12890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989960.0, "min": 29952.0, "max": 989960.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989960.0, "min": 29952.0, "max": 989960.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.490449458360672, "min": -0.1685100793838501, "max": 0.490449458360672, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 132.91180419921875, "min": -39.9368896484375, "max": 132.91180419921875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.031083092093467712, "min": 0.0017590807983651757, "max": 0.3812294602394104, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.423518180847168, "min": 0.47846996784210205, "max": 90.35137939453125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06968653184733177, "min": 0.06399057386165839, "max": 0.07271759007124463, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9756114458626448, "min": 0.49534367418519476, "max": 1.041801266787076, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013322375571685068, "min": 0.00014493401065075333, "max": 0.014514499527562985, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18651325800359095, "min": 0.0018841421384597932, "max": 0.20621203235493213, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.548418912464285e-06, "min": 7.548418912464285e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010567786477449999, "min": 0.00010567786477449999, "max": 0.0035069396310201994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251610714285717, "min": 0.10251610714285717, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352255000000003, "min": 1.3886848, "max": 2.5689798, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002613591035714286, "min": 0.0002613591035714286, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036590274500000004, "min": 0.0036590274500000004, "max": 0.11692108201999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008882459253072739, "min": 0.008882459253072739, "max": 0.3361237049102783, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12435442954301834, "min": 0.12435442954301834, "max": 2.3528659343719482, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 399.1216216216216, "min": 365.0921052631579, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29535.0, "min": 15984.0, "max": 32469.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.519767545667049, "min": -1.0000000521540642, "max": 1.519767545667049, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 112.46279837936163, "min": -30.995201602578163, "max": 114.75679833441973, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.519767545667049, "min": -1.0000000521540642, "max": 1.519767545667049, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 112.46279837936163, "min": -30.995201602578163, "max": 114.75679833441973, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03660280250148168, "min": 0.03633225751276002, "max": 6.572053727693856, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7086073851096444, "min": 2.7086073851096444, "max": 105.15285964310169, "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": "1686451759", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1686453805" }, "total": 2045.5725532710003, "count": 1, "self": 0.4746431000003213, "children": { "run_training.setup": { "total": 0.057743971000036254, "count": 1, "self": 0.057743971000036254 }, "TrainerController.start_learning": { "total": 2045.0401662, "count": 1, "self": 1.3524510599768291, "children": { "TrainerController._reset_env": { "total": 4.648525200000222, "count": 1, "self": 4.648525200000222 }, "TrainerController.advance": { "total": 2038.946222163022, "count": 63592, "self": 1.4072234729874253, "children": { "env_step": { "total": 1403.8896083400991, "count": 63592, "self": 1295.5969404061889, "children": { "SubprocessEnvManager._take_step": { "total": 107.48739777896299, "count": 63592, "self": 4.647674318901863, "children": { "TorchPolicy.evaluate": { "total": 102.83972346006112, "count": 62546, "self": 102.83972346006112 } } }, "workers": { "total": 0.8052701549472658, "count": 63592, "self": 0.0, "children": { "worker_root": { "total": 2040.3241720709698, "count": 63592, "is_parallel": true, "self": 855.9329733190166, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025429860002077476, "count": 1, "is_parallel": true, "self": 0.000741494000521925, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018014919996858225, "count": 8, "is_parallel": true, "self": 0.0018014919996858225 } } }, "UnityEnvironment.step": { "total": 0.04497618000004877, "count": 1, "is_parallel": true, "self": 0.0005187310002838785, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048310700003639795, "count": 1, "is_parallel": true, "self": 0.00048310700003639795 }, "communicator.exchange": { "total": 0.04222326499984774, "count": 1, "is_parallel": true, "self": 0.04222326499984774 }, "steps_from_proto": { "total": 0.0017510769998807518, "count": 1, "is_parallel": true, "self": 0.0003836180007965595, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013674589990841923, "count": 8, "is_parallel": true, "self": 0.0013674589990841923 } } } } } } }, "UnityEnvironment.step": { "total": 1184.3911987519532, "count": 63591, "is_parallel": true, "self": 30.932262386043476, "children": { "UnityEnvironment._generate_step_input": { "total": 22.46154976400794, "count": 63591, "is_parallel": true, "self": 22.46154976400794 }, "communicator.exchange": { "total": 1036.1864800709536, "count": 63591, "is_parallel": true, "self": 1036.1864800709536 }, "steps_from_proto": { "total": 94.81090653094816, "count": 63591, "is_parallel": true, "self": 19.147296034881492, "children": { "_process_rank_one_or_two_observation": { "total": 75.66361049606667, "count": 508728, "is_parallel": true, "self": 75.66361049606667 } } } } } } } } } } }, "trainer_advance": { "total": 633.6493903499354, "count": 63592, "self": 2.5837247709209805, "children": { "process_trajectory": { "total": 107.05427928900963, "count": 63592, "self": 106.85140203600986, "children": { "RLTrainer._checkpoint": { "total": 0.20287725299976955, "count": 2, "self": 0.20287725299976955 } } }, "_update_policy": { "total": 524.0113862900048, "count": 449, "self": 336.67703746705547, "children": { "TorchPPOOptimizer.update": { "total": 187.33434882294932, "count": 22857, "self": 187.33434882294932 } } } } } } }, "trainer_threads": { "total": 8.420001904596575e-07, "count": 1, "self": 8.420001904596575e-07 }, "TrainerController._save_models": { "total": 0.09296693500073161, "count": 1, "self": 0.0014761490010641865, "children": { "RLTrainer._checkpoint": { "total": 0.09149078599966742, "count": 1, "self": 0.09149078599966742 } } } } } } }