{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3648156523704529, "min": 0.35036709904670715, "max": 1.3936642408370972, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10874.4248046875, "min": 10544.6484375, "max": 42278.19921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989897.0, "min": 29952.0, "max": 989897.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989897.0, "min": 29952.0, "max": 989897.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6825043559074402, "min": -0.12101759761571884, "max": 0.7415227293968201, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 191.10122680664062, "min": -29.286258697509766, "max": 219.49072265625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.004908254835754633, "min": -0.11720054596662521, "max": 0.59010910987854, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.3743113279342651, "min": -30.70654296875, "max": 139.85586547851562, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06593194806880477, "min": 0.06593007962103152, "max": 0.07525484353841638, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9230472729632667, "min": 0.5118857781194022, "max": 1.0724650570647976, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015125824388554213, "min": 0.000559834270158916, "max": 0.01737124411840382, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21176154143975898, "min": 0.005199744586928373, "max": 0.2593937749043107, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.587054613871425e-06, "min": 7.587054613871425e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010621876459419996, "min": 0.00010621876459419996, "max": 0.0032557202147599994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252898571428573, "min": 0.10252898571428573, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354058000000003, "min": 1.3886848, "max": 2.5725439999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026264567285714277, "min": 0.00026264567285714277, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036770394199999988, "min": 0.0036770394199999988, "max": 0.10854547599999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012187100015580654, "min": 0.012187100015580654, "max": 0.5229538679122925, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.170619398355484, "min": 0.170619398355484, "max": 3.660676956176758, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 271.05882352941177, "min": 246.2, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27648.0, "min": 15984.0, "max": 32506.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7293106609756508, "min": -1.0000000521540642, "max": 1.7469915846566193, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 178.11899808049202, "min": -31.998401656746864, "max": 215.45759807527065, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7293106609756508, "min": -1.0000000521540642, "max": 1.7469915846566193, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 178.11899808049202, "min": -31.998401656746864, "max": 215.45759807527065, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.034040624395892186, "min": 0.031686061287004005, "max": 10.957106669433415, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.5061843127768952, "min": 3.5061843127768952, "max": 175.31370671093464, "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": "1683242061", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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=Pyramids4 --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": "1683244463" }, "total": 2402.5922183230005, "count": 1, "self": 0.474707118999504, "children": { "run_training.setup": { "total": 0.057119492999845534, "count": 1, "self": 0.057119492999845534 }, "TrainerController.start_learning": { "total": 2402.060391711001, "count": 1, "self": 1.502984708123222, "children": { "TrainerController._reset_env": { "total": 4.918993723999847, "count": 1, "self": 4.918993723999847 }, "TrainerController.advance": { "total": 2395.5435084398787, "count": 64191, "self": 1.5152197509123653, "children": { "env_step": { "total": 1743.9130005340148, "count": 64191, "self": 1625.613628198118, "children": { "SubprocessEnvManager._take_step": { "total": 117.44642171893884, "count": 64191, "self": 5.202547920883262, "children": { "TorchPolicy.evaluate": { "total": 112.24387379805557, "count": 62555, "self": 112.24387379805557 } } }, "workers": { "total": 0.852950616957969, "count": 64191, "self": 0.0, "children": { "worker_root": { "total": 2396.3326593088714, "count": 64191, "is_parallel": true, "self": 893.9743578048665, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002567057999840472, "count": 1, "is_parallel": true, "self": 0.0005550819978452637, "children": { "_process_rank_one_or_two_observation": { "total": 0.002011976001995208, "count": 8, "is_parallel": true, "self": 0.002011976001995208 } } }, "UnityEnvironment.step": { "total": 0.05816764199971658, "count": 1, "is_parallel": true, "self": 0.000635472999420017, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047215599988703616, "count": 1, "is_parallel": true, "self": 0.00047215599988703616 }, "communicator.exchange": { "total": 0.054921074000048975, "count": 1, "is_parallel": true, "self": 0.054921074000048975 }, "steps_from_proto": { "total": 0.0021389390003605513, "count": 1, "is_parallel": true, "self": 0.0004684570003519184, "children": { "_process_rank_one_or_two_observation": { "total": 0.001670482000008633, "count": 8, "is_parallel": true, "self": 0.001670482000008633 } } } } } } }, "UnityEnvironment.step": { "total": 1502.3583015040049, "count": 64190, "is_parallel": true, "self": 33.23282283485514, "children": { "UnityEnvironment._generate_step_input": { "total": 25.061296451979615, "count": 64190, "is_parallel": true, "self": 25.061296451979615 }, "communicator.exchange": { "total": 1336.1386266651853, "count": 64190, "is_parallel": true, "self": 1336.1386266651853 }, "steps_from_proto": { "total": 107.92555555198487, "count": 64190, "is_parallel": true, "self": 22.60062777093208, "children": { "_process_rank_one_or_two_observation": { "total": 85.32492778105279, "count": 513520, "is_parallel": true, "self": 85.32492778105279 } } } } } } } } } } }, "trainer_advance": { "total": 650.1152881549515, "count": 64191, "self": 2.6734349971102347, "children": { "process_trajectory": { "total": 117.48467422883186, "count": 64191, "self": 117.25563822483218, "children": { "RLTrainer._checkpoint": { "total": 0.22903600399968127, "count": 2, "self": 0.22903600399968127 } } }, "_update_policy": { "total": 529.9571789290094, "count": 444, "self": 338.6599236010179, "children": { "TorchPPOOptimizer.update": { "total": 191.29725532799148, "count": 22806, "self": 191.29725532799148 } } } } } } }, "trainer_threads": { "total": 9.4600000011269e-07, "count": 1, "self": 9.4600000011269e-07 }, "TrainerController._save_models": { "total": 0.09490389299935487, "count": 1, "self": 0.0013939969994680723, "children": { "RLTrainer._checkpoint": { "total": 0.0935098959998868, "count": 1, "self": 0.0935098959998868 } } } } } } }