{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.47279247641563416, "min": 0.4178948700428009, "max": 1.4185428619384766, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14319.9384765625, "min": 12637.140625, "max": 43032.91796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989928.0, "min": 29952.0, "max": 989928.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989928.0, "min": 29952.0, "max": 989928.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.30013856291770935, "min": -0.1011304035782814, "max": 0.32417041063308716, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 78.33616638183594, "min": -24.574687957763672, "max": 82.6634521484375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01891472004354, "min": -0.008884472772479057, "max": 0.530904233455658, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.936741828918457, "min": -2.2300026416778564, "max": 125.82431030273438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06907439248780499, "min": 0.06519431874651008, "max": 0.07250073319459979, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9670414948292698, "min": 0.5004072993791037, "max": 1.0639333067448724, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012836584298687134, "min": 0.001032163744821085, "max": 0.013490871821153412, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17971218018161988, "min": 0.01445029242749519, "max": 0.17971218018161988, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.628176028735713e-06, "min": 7.628176028735713e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010679446440229999, "min": 0.00010679446440229999, "max": 0.0035100608299798, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254269285714288, "min": 0.10254269285714288, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355977000000002, "min": 1.3886848, "max": 2.5700201999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026401501642857143, "min": 0.00026401501642857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00369621023, "min": 0.00369621023, "max": 0.11702501798, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013187086209654808, "min": 0.013187086209654808, "max": 0.5414832830429077, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18461920320987701, "min": 0.18461920320987701, "max": 3.7903831005096436, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 495.31666666666666, "min": 495.31666666666666, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29719.0, "min": 15984.0, "max": 33103.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1379133120179177, "min": -1.0000000521540642, "max": 1.1379133120179177, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 68.27479872107506, "min": -30.55340174585581, "max": 68.27479872107506, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1379133120179177, "min": -1.0000000521540642, "max": 1.1379133120179177, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 68.27479872107506, "min": -30.55340174585581, "max": 68.27479872107506, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06875781047468384, "min": 0.06875781047468384, "max": 11.062360726296902, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.1254686284810305, "min": 4.1254686284810305, "max": 176.99777162075043, "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": "1696075760", "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": "1696078139" }, "total": 2379.6060095440002, "count": 1, "self": 0.8324307400002908, "children": { "run_training.setup": { "total": 0.06700835800006644, "count": 1, "self": 0.06700835800006644 }, "TrainerController.start_learning": { "total": 2378.7065704459997, "count": 1, "self": 1.4917470259906622, "children": { "TrainerController._reset_env": { "total": 5.732007365999948, "count": 1, "self": 5.732007365999948 }, "TrainerController.advance": { "total": 2371.320962509009, "count": 63371, "self": 1.4980920709981547, "children": { "env_step": { "total": 1683.2579724810091, "count": 63371, "self": 1563.4989808639973, "children": { "SubprocessEnvManager._take_step": { "total": 118.82265431297253, "count": 63371, "self": 5.202258866964144, "children": { "TorchPolicy.evaluate": { "total": 113.62039544600839, "count": 62549, "self": 113.62039544600839 } } }, "workers": { "total": 0.9363373040392844, "count": 63371, "self": 0.0, "children": { "worker_root": { "total": 2372.6305492679785, "count": 63371, "is_parallel": true, "self": 936.4508953629747, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006433812999944166, "count": 1, "is_parallel": true, "self": 0.004285684000137735, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021481289998064312, "count": 8, "is_parallel": true, "self": 0.0021481289998064312 } } }, "UnityEnvironment.step": { "total": 0.04931185999998888, "count": 1, "is_parallel": true, "self": 0.0005894969999644672, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005608280000615196, "count": 1, "is_parallel": true, "self": 0.0005608280000615196 }, "communicator.exchange": { "total": 0.04505801999994219, "count": 1, "is_parallel": true, "self": 0.04505801999994219 }, "steps_from_proto": { "total": 0.003103515000020707, "count": 1, "is_parallel": true, "self": 0.00044619300024351105, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026573219997771957, "count": 8, "is_parallel": true, "self": 0.0026573219997771957 } } } } } } }, "UnityEnvironment.step": { "total": 1436.1796539050038, "count": 63370, "is_parallel": true, "self": 35.997094507026304, "children": { "UnityEnvironment._generate_step_input": { "total": 25.197515946029625, "count": 63370, "is_parallel": true, "self": 25.197515946029625 }, "communicator.exchange": { "total": 1258.4460322979721, "count": 63370, "is_parallel": true, "self": 1258.4460322979721 }, "steps_from_proto": { "total": 116.53901115397582, "count": 63370, "is_parallel": true, "self": 23.423667293047515, "children": { "_process_rank_one_or_two_observation": { "total": 93.1153438609283, "count": 506960, "is_parallel": true, "self": 93.1153438609283 } } } } } } } } } } }, "trainer_advance": { "total": 686.5648979570017, "count": 63371, "self": 2.908465069980025, "children": { "process_trajectory": { "total": 120.76876528702132, "count": 63371, "self": 120.48044940202112, "children": { "RLTrainer._checkpoint": { "total": 0.2883158850002019, "count": 2, "self": 0.2883158850002019 } } }, "_update_policy": { "total": 562.8876676000003, "count": 451, "self": 367.2283938479824, "children": { "TorchPPOOptimizer.update": { "total": 195.65927375201795, "count": 22809, "self": 195.65927375201795 } } } } } } }, "trainer_threads": { "total": 1.6320000213454477e-06, "count": 1, "self": 1.6320000213454477e-06 }, "TrainerController._save_models": { "total": 0.16185191300019142, "count": 1, "self": 0.0017780830003175652, "children": { "RLTrainer._checkpoint": { "total": 0.16007382999987385, "count": 1, "self": 0.16007382999987385 } } } } } } }