{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5535457134246826, "min": 0.5535457134246826, "max": 1.4745616912841797, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16526.66015625, "min": 16526.66015625, "max": 44732.3046875, "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": 0.35023078322410583, "min": -0.1144992932677269, "max": 0.35023078322410583, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 91.76046752929688, "min": -27.594329833984375, "max": 91.76046752929688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0004190222534816712, "min": -0.0004190222534816712, "max": 0.35449734330177307, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.1097838282585144, "min": -0.1097838282585144, "max": 84.015869140625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06860575317807074, "min": 0.06259277691509958, "max": 0.07322617392851107, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9604805444929904, "min": 0.4982663270587171, "max": 1.0897080612268444, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011853492382215334, "min": 0.0005287973702003898, "max": 0.012316144136493474, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16594889335101468, "min": 0.005043216571224569, "max": 0.17890678551852676, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.25268329675714e-06, "min": 7.25268329675714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010153756615459997, "min": 0.00010153756615459997, "max": 0.0030057732980757006, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10241752857142858, "min": 0.10241752857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4338454, "min": 1.3691136000000002, "max": 2.4019243, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002515111042857143, "min": 0.0002515111042857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035211554599999997, "min": 0.0035211554599999997, "max": 0.10023223757, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010278454050421715, "min": 0.010278454050421715, "max": 0.48938798904418945, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1438983529806137, "min": 0.1438983529806137, "max": 3.425715923309326, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 511.271186440678, "min": 502.51666666666665, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30165.0, "min": 15984.0, "max": 33702.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3191728679052854, "min": -1.0000000521540642, "max": 1.3641166374087335, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 77.83119920641184, "min": -32.000001668930054, "max": 81.846998244524, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3191728679052854, "min": -1.0000000521540642, "max": 1.3641166374087335, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 77.83119920641184, "min": -32.000001668930054, "max": 81.846998244524, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05487600586799336, "min": 0.05487600586799336, "max": 10.391977360472083, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2376843462116085, "min": 3.2376843462116085, "max": 166.27163776755333, "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": "1703175014", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703177211" }, "total": 2197.851266036, "count": 1, "self": 0.47599694500013356, "children": { "run_training.setup": { "total": 0.07093509300011647, "count": 1, "self": 0.07093509300011647 }, "TrainerController.start_learning": { "total": 2197.304333998, "count": 1, "self": 1.4537739760344266, "children": { "TrainerController._reset_env": { "total": 2.232617993999611, "count": 1, "self": 2.232617993999611 }, "TrainerController.advance": { "total": 2193.5318336249657, "count": 63403, "self": 1.468862188919502, "children": { "env_step": { "total": 1566.016204508092, "count": 63403, "self": 1433.603659619218, "children": { "SubprocessEnvManager._take_step": { "total": 131.5500175119828, "count": 63403, "self": 4.853619912929844, "children": { "TorchPolicy.evaluate": { "total": 126.69639759905294, "count": 62577, "self": 126.69639759905294 } } }, "workers": { "total": 0.8625273768911939, "count": 63403, "self": 0.0, "children": { "worker_root": { "total": 2192.056339243994, "count": 63403, "is_parallel": true, "self": 880.8666079998761, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016709649999029352, "count": 1, "is_parallel": true, "self": 0.0005023979997531569, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011685670001497783, "count": 8, "is_parallel": true, "self": 0.0011685670001497783 } } }, "UnityEnvironment.step": { "total": 0.052397217999896384, "count": 1, "is_parallel": true, "self": 0.0006090150004638417, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005454329998428875, "count": 1, "is_parallel": true, "self": 0.0005454329998428875 }, "communicator.exchange": { "total": 0.049471731999801705, "count": 1, "is_parallel": true, "self": 0.049471731999801705 }, "steps_from_proto": { "total": 0.00177103799978795, "count": 1, "is_parallel": true, "self": 0.00037757399968540994, "children": { "_process_rank_one_or_two_observation": { "total": 0.00139346400010254, "count": 8, "is_parallel": true, "self": 0.00139346400010254 } } } } } } }, "UnityEnvironment.step": { "total": 1311.1897312441179, "count": 63402, "is_parallel": true, "self": 35.278884253183605, "children": { "UnityEnvironment._generate_step_input": { "total": 25.138991849048125, "count": 63402, "is_parallel": true, "self": 25.138991849048125 }, "communicator.exchange": { "total": 1149.2807449889265, "count": 63402, "is_parallel": true, "self": 1149.2807449889265 }, "steps_from_proto": { "total": 101.49111015295966, "count": 63402, "is_parallel": true, "self": 20.78277449207644, "children": { "_process_rank_one_or_two_observation": { "total": 80.70833566088322, "count": 507216, "is_parallel": true, "self": 80.70833566088322 } } } } } } } } } } }, "trainer_advance": { "total": 626.0467669279542, "count": 63403, "self": 2.6185832319724796, "children": { "process_trajectory": { "total": 126.86745678298394, "count": 63403, "self": 126.62077571198415, "children": { "RLTrainer._checkpoint": { "total": 0.24668107099978442, "count": 2, "self": 0.24668107099978442 } } }, "_update_policy": { "total": 496.5607269129978, "count": 433, "self": 296.4529802809984, "children": { "TorchPPOOptimizer.update": { "total": 200.10774663199936, "count": 22806, "self": 200.10774663199936 } } } } } } }, "trainer_threads": { "total": 1.0140001904801466e-06, "count": 1, "self": 1.0140001904801466e-06 }, "TrainerController._save_models": { "total": 0.08610738900006254, "count": 1, "self": 0.0014629239994974341, "children": { "RLTrainer._checkpoint": { "total": 0.0846444650005651, "count": 1, "self": 0.0846444650005651 } } } } } } }