{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5147733688354492, "min": 0.5147733688354492, "max": 1.3915784358978271, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15533.8017578125, "min": 15496.7490234375, "max": 42214.921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989941.0, "min": 29952.0, "max": 989941.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989941.0, "min": 29952.0, "max": 989941.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3318574130535126, "min": -0.1150316521525383, "max": 0.33768603205680847, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 86.28292846679688, "min": -27.556777954101562, "max": 88.8114242553711, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.19503264129161835, "min": -0.41228023171424866, "max": 0.5452406406402588, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -50.70848846435547, "min": -108.42970275878906, "max": 129.22203063964844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0690451192798622, "min": 0.06519956953121855, "max": 0.07267262038112166, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9666316699180708, "min": 0.49768081643292816, "max": 1.0502006309300973, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016139083400731308, "min": 0.0004566777733421893, "max": 0.026887191072586046, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2259471676102383, "min": 0.00639348882679065, "max": 0.37642067501620463, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.507233211907138e-06, "min": 7.507233211907138e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010510126496669993, "min": 0.00010510126496669993, "max": 0.003633186188938, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250237857142856, "min": 0.10250237857142856, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350333, "min": 1.3886848, "max": 2.6110620000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025998761928571417, "min": 0.00025998761928571417, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036398266699999987, "min": 0.0036398266699999987, "max": 0.1211250938, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015248218551278114, "min": 0.015248218551278114, "max": 0.6263422966003418, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2134750634431839, "min": 0.2134750634431839, "max": 4.384396076202393, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 543.2280701754386, "min": 516.457627118644, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30964.0, "min": 15984.0, "max": 33185.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.176003475199666, "min": -1.0000000521540642, "max": 1.2940841834796102, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 67.03219808638096, "min": -30.178401708602905, "max": 73.76279845833778, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.176003475199666, "min": -1.0000000521540642, "max": 1.2940841834796102, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 67.03219808638096, "min": -30.178401708602905, "max": 73.76279845833778, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08676831916091032, "min": 0.08512498271059789, "max": 12.522377313114703, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.945794192171888, "min": 4.630836577533046, "max": 200.35803700983524, "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": "1704144425", "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": "1704146714" }, "total": 2288.9394708699997, "count": 1, "self": 0.48836045599909994, "children": { "run_training.setup": { "total": 0.048447914000007586, "count": 1, "self": 0.048447914000007586 }, "TrainerController.start_learning": { "total": 2288.4026625000006, "count": 1, "self": 1.9298669879885892, "children": { "TrainerController._reset_env": { "total": 2.0680211459998645, "count": 1, "self": 2.0680211459998645 }, "TrainerController.advance": { "total": 2284.309719242011, "count": 63378, "self": 2.0623450781777137, "children": { "env_step": { "total": 1627.9333346039411, "count": 63378, "self": 1467.1519761338936, "children": { "SubprocessEnvManager._take_step": { "total": 159.61010757702888, "count": 63378, "self": 5.67159414404432, "children": { "TorchPolicy.evaluate": { "total": 153.93851343298456, "count": 62565, "self": 153.93851343298456 } } }, "workers": { "total": 1.1712508930186232, "count": 63378, "self": 0.0, "children": { "worker_root": { "total": 2282.239479110946, "count": 63378, "is_parallel": true, "self": 958.1015344209409, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016421860000264132, "count": 1, "is_parallel": true, "self": 0.0005345989993656985, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011075870006607147, "count": 8, "is_parallel": true, "self": 0.0011075870006607147 } } }, "UnityEnvironment.step": { "total": 0.050174135000361275, "count": 1, "is_parallel": true, "self": 0.0006168850004542037, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00050783999995474, "count": 1, "is_parallel": true, "self": 0.00050783999995474 }, "communicator.exchange": { "total": 0.04726238400007787, "count": 1, "is_parallel": true, "self": 0.04726238400007787 }, "steps_from_proto": { "total": 0.0017870259998744586, "count": 1, "is_parallel": true, "self": 0.00039355099897875334, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013934750008957053, "count": 8, "is_parallel": true, "self": 0.0013934750008957053 } } } } } } }, "UnityEnvironment.step": { "total": 1324.137944690005, "count": 63377, "is_parallel": true, "self": 38.34160748796148, "children": { "UnityEnvironment._generate_step_input": { "total": 26.994674370017947, "count": 63377, "is_parallel": true, "self": 26.994674370017947 }, "communicator.exchange": { "total": 1147.7730831430135, "count": 63377, "is_parallel": true, "self": 1147.7730831430135 }, "steps_from_proto": { "total": 111.02857968901208, "count": 63377, "is_parallel": true, "self": 23.82401518008828, "children": { "_process_rank_one_or_two_observation": { "total": 87.2045645089238, "count": 507016, "is_parallel": true, "self": 87.2045645089238 } } } } } } } } } } }, "trainer_advance": { "total": 654.3140395598921, "count": 63378, "self": 3.5409865218221057, "children": { "process_trajectory": { "total": 135.4733876830678, "count": 63378, "self": 135.21789240206817, "children": { "RLTrainer._checkpoint": { "total": 0.25549528099963936, "count": 2, "self": 0.25549528099963936 } } }, "_update_policy": { "total": 515.2996653550022, "count": 446, "self": 304.63733262791493, "children": { "TorchPPOOptimizer.update": { "total": 210.66233272708723, "count": 22818, "self": 210.66233272708723 } } } } } } }, "trainer_threads": { "total": 9.10000380827114e-07, "count": 1, "self": 9.10000380827114e-07 }, "TrainerController._save_models": { "total": 0.09505421400081104, "count": 1, "self": 0.0015733880009065615, "children": { "RLTrainer._checkpoint": { "total": 0.09348082599990448, "count": 1, "self": 0.09348082599990448 } } } } } } }