{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.49067816138267517, "min": 0.47010570764541626, "max": 1.3977667093276978, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14736.046875, "min": 14148.3017578125, "max": 42402.65234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989971.0, "min": 29952.0, "max": 989971.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989971.0, "min": 29952.0, "max": 989971.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2955031394958496, "min": -0.11607566475868225, "max": 0.38129210472106934, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 77.1263198852539, "min": -27.97423553466797, "max": 98.75465393066406, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02113688364624977, "min": -0.08313251286745071, "max": 0.4561222791671753, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.516726493835449, "min": -21.19879150390625, "max": 108.10098266601562, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06948826840798693, "min": 0.06613091380603339, "max": 0.07313576118735947, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.042324026119804, "min": 0.5119503283115163, "max": 1.0654247421965315, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011591984607856431, "min": 0.00211964380509966, "max": 0.015226574582994881, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17387976911784647, "min": 0.020656749539671445, "max": 0.21317204416192834, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4201575266466665e-06, "min": 7.4201575266466665e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001113023628997, "min": 0.0001113023628997, "max": 0.0035106779297740995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247335333333336, "min": 0.10247335333333336, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5371003000000005, "min": 1.3886848, "max": 2.6173457000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025708799800000005, "min": 0.00025708799800000005, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038563199700000004, "min": 0.0038563199700000004, "max": 0.11704556741, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009972487576305866, "min": 0.009972487576305866, "max": 0.5932093858718872, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14958731830120087, "min": 0.14064815640449524, "max": 4.1524658203125, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 486.91379310344826, "min": 486.91379310344826, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28241.0, "min": 15984.0, "max": 32737.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2026516953162079, "min": -1.0000000521540642, "max": 1.3008766404042642, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 69.75379832834005, "min": -30.67500166594982, "max": 78.05259842425585, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2026516953162079, "min": -1.0000000521540642, "max": 1.3008766404042642, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 69.75379832834005, "min": -30.67500166594982, "max": 78.05259842425585, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05070910793086835, "min": 0.05070910793086835, "max": 12.821752052754164, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9411282599903643, "min": 2.9411282599903643, "max": 205.14803284406662, "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": "1695971692", "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": "1695973912" }, "total": 2220.8687361660004, "count": 1, "self": 0.4752938780011391, "children": { "run_training.setup": { "total": 0.03981967099980466, "count": 1, "self": 0.03981967099980466 }, "TrainerController.start_learning": { "total": 2220.3536226169995, "count": 1, "self": 1.387152187026004, "children": { "TrainerController._reset_env": { "total": 4.154826706999756, "count": 1, "self": 4.154826706999756 }, "TrainerController.advance": { "total": 2214.7084487439733, "count": 63567, "self": 1.3501266299858798, "children": { "env_step": { "total": 1545.1091291449702, "count": 63567, "self": 1435.1927097280327, "children": { "SubprocessEnvManager._take_step": { "total": 109.09746598502261, "count": 63567, "self": 4.702635941995595, "children": { "TorchPolicy.evaluate": { "total": 104.39483004302701, "count": 62573, "self": 104.39483004302701 } } }, "workers": { "total": 0.8189534319149061, "count": 63567, "self": 0.0, "children": { "worker_root": { "total": 2215.3223143760238, "count": 63567, "is_parallel": true, "self": 894.4810994099871, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001786682000329165, "count": 1, "is_parallel": true, "self": 0.0005371090001062839, "children": { "_process_rank_one_or_two_observation": { "total": 0.001249573000222881, "count": 8, "is_parallel": true, "self": 0.001249573000222881 } } }, "UnityEnvironment.step": { "total": 0.052097139000125026, "count": 1, "is_parallel": true, "self": 0.0006265090000852069, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004606219999914174, "count": 1, "is_parallel": true, "self": 0.0004606219999914174 }, "communicator.exchange": { "total": 0.047920781999891915, "count": 1, "is_parallel": true, "self": 0.047920781999891915 }, "steps_from_proto": { "total": 0.0030892260001564864, "count": 1, "is_parallel": true, "self": 0.0004060060009578592, "children": { "_process_rank_one_or_two_observation": { "total": 0.002683219999198627, "count": 8, "is_parallel": true, "self": 0.002683219999198627 } } } } } } }, "UnityEnvironment.step": { "total": 1320.8412149660367, "count": 63566, "is_parallel": true, "self": 34.19498160625426, "children": { "UnityEnvironment._generate_step_input": { "total": 22.726782820961034, "count": 63566, "is_parallel": true, "self": 22.726782820961034 }, "communicator.exchange": { "total": 1157.888797390976, "count": 63566, "is_parallel": true, "self": 1157.888797390976 }, "steps_from_proto": { "total": 106.03065314784544, "count": 63566, "is_parallel": true, "self": 20.889841236806205, "children": { "_process_rank_one_or_two_observation": { "total": 85.14081191103924, "count": 508528, "is_parallel": true, "self": 85.14081191103924 } } } } } } } } } } }, "trainer_advance": { "total": 668.2491929690173, "count": 63567, "self": 2.686325727058829, "children": { "process_trajectory": { "total": 110.56744735696202, "count": 63567, "self": 110.29166796496247, "children": { "RLTrainer._checkpoint": { "total": 0.27577939199954926, "count": 2, "self": 0.27577939199954926 } } }, "_update_policy": { "total": 554.9954198849964, "count": 453, "self": 362.39000522799506, "children": { "TorchPPOOptimizer.update": { "total": 192.60541465700135, "count": 22743, "self": 192.60541465700135 } } } } } } }, "trainer_threads": { "total": 9.490004231338389e-07, "count": 1, "self": 9.490004231338389e-07 }, "TrainerController._save_models": { "total": 0.10319402999994054, "count": 1, "self": 0.001486217000092438, "children": { "RLTrainer._checkpoint": { "total": 0.1017078129998481, "count": 1, "self": 0.1017078129998481 } } } } } } }