{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4332011044025421, "min": 0.4332011044025421, "max": 1.5011484622955322, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13093.0703125, "min": 13093.0703125, "max": 45538.83984375, "count": 33 }, "Pyramids.Step.mean": { "value": 989996.0, "min": 29950.0, "max": 989996.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989996.0, "min": 29950.0, "max": 989996.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5503509640693665, "min": -0.09999842941761017, "max": 0.5503509640693665, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 154.0982666015625, "min": -24.099620819091797, "max": 154.0982666015625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0070169465616345406, "min": -0.06382633745670319, "max": 0.279434472322464, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.964745044708252, "min": -16.913978576660156, "max": 66.22596740722656, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06797092534058416, "min": 0.06478668869046013, "max": 0.0729894188421202, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9515929547681783, "min": 0.4788390514919208, "max": 1.07616608220269, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014726526627782732, "min": 0.000625693951179309, "max": 0.015665211693842485, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20617137278895825, "min": 0.008134021365331017, "max": 0.21931296371379477, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.510661782192856e-06, "min": 7.510661782192856e-06, "max": 0.000295233001589, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010514926495069999, "min": 0.00010514926495069999, "max": 0.0036090558969814005, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250352142857144, "min": 0.10250352142857144, "max": 0.19841099999999998, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350493000000002, "min": 1.388877, "max": 2.527856400000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026010179071428576, "min": 0.00026010179071428576, "max": 0.009841258899999998, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036414250700000004, "min": 0.0036414250700000004, "max": 0.12031155814000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010898577980697155, "min": 0.010751202702522278, "max": 0.5214666724205017, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15258009731769562, "min": 0.1505168378353119, "max": 3.6502668857574463, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 344.6363636363636, "min": 344.6363636363636, "max": 985.2352941176471, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30328.0, "min": 16749.0, "max": 33294.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6098931619728154, "min": -0.9189939898523417, "max": 1.6098931619728154, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 141.67059825360775, "min": -30.326801665127277, "max": 141.67059825360775, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6098931619728154, "min": -0.9189939898523417, "max": 1.6098931619728154, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 141.67059825360775, "min": -30.326801665127277, "max": 141.67059825360775, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03915074377172542, "min": 0.03915074377172542, "max": 10.01576786970391, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.445265451911837, "min": 3.2470914640580304, "max": 170.26805378496647, "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": "1694723653", "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 --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": "1694725938" }, "total": 2284.8017667310005, "count": 1, "self": 0.4788402040007895, "children": { "run_training.setup": { "total": 0.04378895600029864, "count": 1, "self": 0.04378895600029864 }, "TrainerController.start_learning": { "total": 2284.2791375709994, "count": 1, "self": 1.4367187229631782, "children": { "TrainerController._reset_env": { "total": 4.326937135999742, "count": 1, "self": 4.326937135999742 }, "TrainerController.advance": { "total": 2278.417209707037, "count": 63745, "self": 1.4378788890312535, "children": { "env_step": { "total": 1577.4545915920494, "count": 63745, "self": 1464.2107897620153, "children": { "SubprocessEnvManager._take_step": { "total": 112.38931551898713, "count": 63745, "self": 4.93246534607988, "children": { "TorchPolicy.evaluate": { "total": 107.45685017290725, "count": 62567, "self": 107.45685017290725 } } }, "workers": { "total": 0.8544863110469123, "count": 63745, "self": 0.0, "children": { "worker_root": { "total": 2278.925166069942, "count": 63745, "is_parallel": true, "self": 932.1877765429058, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019251339999755146, "count": 1, "is_parallel": true, "self": 0.0005996950003464008, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013254389996291138, "count": 8, "is_parallel": true, "self": 0.0013254389996291138 } } }, "UnityEnvironment.step": { "total": 0.05127174199969886, "count": 1, "is_parallel": true, "self": 0.0006866999997328094, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005019109999011562, "count": 1, "is_parallel": true, "self": 0.0005019109999011562 }, "communicator.exchange": { "total": 0.04724548900003356, "count": 1, "is_parallel": true, "self": 0.04724548900003356 }, "steps_from_proto": { "total": 0.0028376420000313374, "count": 1, "is_parallel": true, "self": 0.00037577500006591436, "children": { "_process_rank_one_or_two_observation": { "total": 0.002461866999965423, "count": 8, "is_parallel": true, "self": 0.002461866999965423 } } } } } } }, "UnityEnvironment.step": { "total": 1346.7373895270362, "count": 63744, "is_parallel": true, "self": 35.24956976490466, "children": { "UnityEnvironment._generate_step_input": { "total": 23.72633934804253, "count": 63744, "is_parallel": true, "self": 23.72633934804253 }, "communicator.exchange": { "total": 1177.7676377300959, "count": 63744, "is_parallel": true, "self": 1177.7676377300959 }, "steps_from_proto": { "total": 109.99384268399308, "count": 63744, "is_parallel": true, "self": 21.376581687653925, "children": { "_process_rank_one_or_two_observation": { "total": 88.61726099633916, "count": 509952, "is_parallel": true, "self": 88.61726099633916 } } } } } } } } } } }, "trainer_advance": { "total": 699.5247392259562, "count": 63745, "self": 2.786190356955103, "children": { "process_trajectory": { "total": 116.48062051000261, "count": 63745, "self": 116.20586107900226, "children": { "RLTrainer._checkpoint": { "total": 0.27475943100034783, "count": 2, "self": 0.27475943100034783 } } }, "_update_policy": { "total": 580.2579283589985, "count": 456, "self": 380.2165612849508, "children": { "TorchPPOOptimizer.update": { "total": 200.04136707404768, "count": 22776, "self": 200.04136707404768 } } } } } } }, "trainer_threads": { "total": 1.020999661704991e-06, "count": 1, "self": 1.020999661704991e-06 }, "TrainerController._save_models": { "total": 0.09827098400000978, "count": 1, "self": 0.0013932179999756045, "children": { "RLTrainer._checkpoint": { "total": 0.09687776600003417, "count": 1, "self": 0.09687776600003417 } } } } } } }