{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.29647567868232727, "min": 0.29647567868232727, "max": 1.4916387796401978, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8955.9375, "min": 8955.9375, "max": 45250.35546875, "count": 33 }, "Pyramids.Step.mean": { "value": 989991.0, "min": 29952.0, "max": 989991.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989991.0, "min": 29952.0, "max": 989991.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6594275236129761, "min": -0.1945982724428177, "max": 0.7162800431251526, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 191.23397827148438, "min": -46.119789123535156, "max": 211.3026123046875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.005772356875240803, "min": -0.013938176445662975, "max": 0.23727571964263916, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.6739834547042847, "min": -4.083885669708252, "max": 57.183448791503906, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06920070065479236, "min": 0.06352034539024952, "max": 0.07214130268368449, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9688098091670931, "min": 0.5046308236547891, "max": 1.0796975416619805, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016100112914933733, "min": 0.0011643038653663226, "max": 0.018321873531455087, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22540158080907227, "min": 0.015135950249762196, "max": 0.2565062294403712, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.668011729742859e-06, "min": 7.668011729742859e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010735216421640002, "min": 0.00010735216421640002, "max": 0.0036355825881392, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255597142857144, "min": 0.10255597142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357836000000002, "min": 1.3886848, "max": 2.6174260000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026534154571428576, "min": 0.00026534154571428576, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003714781640000001, "min": 0.003714781640000001, "max": 0.12120489392000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010668734088540077, "min": 0.010668734088540077, "max": 0.4124008119106293, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14936228096485138, "min": 0.14936228096485138, "max": 2.886805772781372, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 290.0952380952381, "min": 257.70940170940173, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30460.0, "min": 15984.0, "max": 32898.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6908476015641576, "min": -1.0000000521540642, "max": 1.735118169947104, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 177.53899816423655, "min": -30.708801709115505, "max": 199.84679836034775, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6908476015641576, "min": -1.0000000521540642, "max": 1.735118169947104, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 177.53899816423655, "min": -30.708801709115505, "max": 199.84679836034775, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03210255836657736, "min": 0.02860736421062651, "max": 8.053750473074615, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.370768628490623, "min": 3.252941712969914, "max": 128.86000756919384, "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": "1679571907", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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=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": "1679574106" }, "total": 2198.7420537519997, "count": 1, "self": 0.42431822399976227, "children": { "run_training.setup": { "total": 0.09987653500002125, "count": 1, "self": 0.09987653500002125 }, "TrainerController.start_learning": { "total": 2198.217858993, "count": 1, "self": 1.3537848780129025, "children": { "TrainerController._reset_env": { "total": 5.790097968000055, "count": 1, "self": 5.790097968000055 }, "TrainerController.advance": { "total": 2190.983232499987, "count": 64396, "self": 1.3554528030590518, "children": { "env_step": { "total": 1583.803061964959, "count": 64396, "self": 1480.2166194618683, "children": { "SubprocessEnvManager._take_step": { "total": 102.78410198710299, "count": 64396, "self": 4.723805587114384, "children": { "TorchPolicy.evaluate": { "total": 98.0602963999886, "count": 62573, "self": 98.0602963999886 } } }, "workers": { "total": 0.8023405159876802, "count": 64396, "self": 0.0, "children": { "worker_root": { "total": 2193.9162377049593, "count": 64396, "is_parallel": true, "self": 826.0847698099224, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00165366900000663, "count": 1, "is_parallel": true, "self": 0.0004965800001173193, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011570889998893108, "count": 8, "is_parallel": true, "self": 0.0011570889998893108 } } }, "UnityEnvironment.step": { "total": 0.043367934999878344, "count": 1, "is_parallel": true, "self": 0.00052695199997288, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004536079998160858, "count": 1, "is_parallel": true, "self": 0.0004536079998160858 }, "communicator.exchange": { "total": 0.04087550600002032, "count": 1, "is_parallel": true, "self": 0.04087550600002032 }, "steps_from_proto": { "total": 0.0015118690000690549, "count": 1, "is_parallel": true, "self": 0.0003358490002938197, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011760199997752352, "count": 8, "is_parallel": true, "self": 0.0011760199997752352 } } } } } } }, "UnityEnvironment.step": { "total": 1367.831467895037, "count": 64395, "is_parallel": true, "self": 30.289322151082388, "children": { "UnityEnvironment._generate_step_input": { "total": 21.6339413909227, "count": 64395, "is_parallel": true, "self": 21.6339413909227 }, "communicator.exchange": { "total": 1227.1208622180166, "count": 64395, "is_parallel": true, "self": 1227.1208622180166 }, "steps_from_proto": { "total": 88.78734213501525, "count": 64395, "is_parallel": true, "self": 18.659352859125192, "children": { "_process_rank_one_or_two_observation": { "total": 70.12798927589006, "count": 515160, "is_parallel": true, "self": 70.12798927589006 } } } } } } } } } } }, "trainer_advance": { "total": 605.8247177319688, "count": 64396, "self": 2.512723633920359, "children": { "process_trajectory": { "total": 114.38573728904817, "count": 64396, "self": 114.19005943204797, "children": { "RLTrainer._checkpoint": { "total": 0.19567785700019158, "count": 2, "self": 0.19567785700019158 } } }, "_update_policy": { "total": 488.9262568090003, "count": 454, "self": 311.18844605602476, "children": { "TorchPPOOptimizer.update": { "total": 177.73781075297552, "count": 22782, "self": 177.73781075297552 } } } } } } }, "trainer_threads": { "total": 9.420000424142927e-07, "count": 1, "self": 9.420000424142927e-07 }, "TrainerController._save_models": { "total": 0.09074270500013881, "count": 1, "self": 0.0013556400003835734, "children": { "RLTrainer._checkpoint": { "total": 0.08938706499975524, "count": 1, "self": 0.08938706499975524 } } } } } } }