{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.40752285718917847, "min": 0.40752285718917847, "max": 1.49339759349823, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12206.125, "min": 12206.125, "max": 45303.7109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989948.0, "min": 29912.0, "max": 989948.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989948.0, "min": 29912.0, "max": 989948.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3860066831111908, "min": -0.10693488270044327, "max": 0.4617581367492676, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 100.36174011230469, "min": -25.87824249267578, "max": 125.1364517211914, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.023606572300195694, "min": -0.008749131113290787, "max": 0.3732135593891144, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.13770866394043, "min": -2.2922723293304443, "max": 88.45161437988281, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07030392752078894, "min": 0.06607135672155502, "max": 0.0743340314427094, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9842549852910452, "min": 0.5203382200989658, "max": 1.1073169790152289, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013754318370566967, "min": 0.00029005192281029605, "max": 0.015066435062792398, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19256045718793754, "min": 0.003480623073723553, "max": 0.21093009087909356, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.678640297628573e-06, "min": 7.678640297628573e-06, "max": 0.0002952346301598857, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010750096416680001, "min": 0.00010750096416680001, "max": 0.0035080280306573996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255951428571428, "min": 0.10255951428571428, "max": 0.19841154285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358331999999998, "min": 1.3888808, "max": 2.5693426, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002656954771428572, "min": 0.0002656954771428572, "max": 0.00984131313142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003719736680000001, "min": 0.003719736680000001, "max": 0.11695732573999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009198606014251709, "min": 0.009112351574003696, "max": 0.3367597758769989, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12878048419952393, "min": 0.1275729238986969, "max": 2.35731840133667, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 444.42028985507244, "min": 385.3943661971831, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30665.0, "min": 16711.0, "max": 33170.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2989352684029762, "min": -0.9999500517733395, "max": 1.4908816716830495, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 88.32759825140238, "min": -31.998401656746864, "max": 107.45699825882912, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2989352684029762, "min": -0.9999500517733395, "max": 1.4908816716830495, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 88.32759825140238, "min": -31.998401656746864, "max": 107.45699825882912, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04261775434732793, "min": 0.03818512734378109, "max": 6.163425108965705, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8980072956182994, "min": 2.8256994234398007, "max": 104.77822685241699, "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": "1692412996", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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 1 --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": "1692415406" }, "total": 2409.825752377, "count": 1, "self": 1.3926586269999461, "children": { "run_training.setup": { "total": 0.045228499000131706, "count": 1, "self": 0.045228499000131706 }, "TrainerController.start_learning": { "total": 2408.3878652509998, "count": 1, "self": 1.5227404922102323, "children": { "TrainerController._reset_env": { "total": 4.372809562999919, "count": 1, "self": 4.372809562999919 }, "TrainerController.advance": { "total": 2402.31347861079, "count": 63613, "self": 1.5426062917786112, "children": { "env_step": { "total": 1654.100119175012, "count": 63613, "self": 1533.5483556158597, "children": { "SubprocessEnvManager._take_step": { "total": 119.6537796502198, "count": 63613, "self": 5.315162956189852, "children": { "TorchPolicy.evaluate": { "total": 114.33861669402995, "count": 62564, "self": 114.33861669402995 } } }, "workers": { "total": 0.8979839089324742, "count": 63613, "self": 0.0, "children": { "worker_root": { "total": 2402.473869754956, "count": 63613, "is_parallel": true, "self": 995.5665797390566, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020417639998413506, "count": 1, "is_parallel": true, "self": 0.0006419350002033752, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013998289996379754, "count": 8, "is_parallel": true, "self": 0.0013998289996379754 } } }, "UnityEnvironment.step": { "total": 0.05427327000006699, "count": 1, "is_parallel": true, "self": 0.0006510250004794216, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005587609998656262, "count": 1, "is_parallel": true, "self": 0.0005587609998656262 }, "communicator.exchange": { "total": 0.050948230999892985, "count": 1, "is_parallel": true, "self": 0.050948230999892985 }, "steps_from_proto": { "total": 0.0021152529998289538, "count": 1, "is_parallel": true, "self": 0.00040692199900149717, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017083310008274566, "count": 8, "is_parallel": true, "self": 0.0017083310008274566 } } } } } } }, "UnityEnvironment.step": { "total": 1406.9072900158994, "count": 63612, "is_parallel": true, "self": 37.35189973191518, "children": { "UnityEnvironment._generate_step_input": { "total": 24.770873719022802, "count": 63612, "is_parallel": true, "self": 24.770873719022802 }, "communicator.exchange": { "total": 1227.4933341469978, "count": 63612, "is_parallel": true, "self": 1227.4933341469978 }, "steps_from_proto": { "total": 117.29118241796368, "count": 63612, "is_parallel": true, "self": 22.880441734859687, "children": { "_process_rank_one_or_two_observation": { "total": 94.410740683104, "count": 508896, "is_parallel": true, "self": 94.410740683104 } } } } } } } } } } }, "trainer_advance": { "total": 746.6707531439993, "count": 63613, "self": 2.7814571399553643, "children": { "process_trajectory": { "total": 124.43886888404768, "count": 63613, "self": 124.21180837704742, "children": { "RLTrainer._checkpoint": { "total": 0.22706050700026026, "count": 2, "self": 0.22706050700026026 } } }, "_update_policy": { "total": 619.4504271199962, "count": 450, "self": 407.0061091980242, "children": { "TorchPPOOptimizer.update": { "total": 212.44431792197202, "count": 22776, "self": 212.44431792197202 } } } } } } }, "trainer_threads": { "total": 1.4739998732693493e-06, "count": 1, "self": 1.4739998732693493e-06 }, "TrainerController._save_models": { "total": 0.17883511099989846, "count": 1, "self": 0.0022213660004126723, "children": { "RLTrainer._checkpoint": { "total": 0.1766137449994858, "count": 1, "self": 0.1766137449994858 } } } } } } }