{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.47493547201156616, "min": 0.4532872140407562, "max": 1.4788527488708496, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14384.845703125, "min": 13678.39453125, "max": 44862.4765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5821881890296936, "min": -0.09894806891679764, "max": 0.5996379256248474, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 161.8483123779297, "min": -23.846485137939453, "max": 169.097900390625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01789037510752678, "min": -0.2430124431848526, "max": 0.2063317745923996, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.97352409362793, "min": -65.37034606933594, "max": 58.18556213378906, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06872760164800898, "min": 0.06585078158463789, "max": 0.07490946340843833, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9621864230721258, "min": 0.4946663592548656, "max": 1.0360535283837762, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016930629484011746, "min": 9.949903439294299e-05, "max": 0.02376030554033944, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23702881277616444, "min": 0.001293487447108259, "max": 0.3564045831050916, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.380268968514289e-06, "min": 7.380268968514289e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010332376555920004, "min": 0.00010332376555920004, "max": 0.0037583341472219997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246005714285715, "min": 0.10246005714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344408000000002, "min": 1.3886848, "max": 2.652778, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002557597085714287, "min": 0.0002557597085714287, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035806359200000015, "min": 0.0035806359200000015, "max": 0.12529252219999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009821332059800625, "min": 0.009821332059800625, "max": 0.3626667857170105, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1374986469745636, "min": 0.1374986469745636, "max": 2.5386674404144287, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 334.95604395604397, "min": 315.63157894736844, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30481.0, "min": 15984.0, "max": 32596.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6210747054972492, "min": -1.0000000521540642, "max": 1.663311563510644, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 147.51779820024967, "min": -30.989801570773125, "max": 158.01459853351116, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6210747054972492, "min": -1.0000000521540642, "max": 1.663311563510644, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 147.51779820024967, "min": -30.989801570773125, "max": 158.01459853351116, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.033968257678130255, "min": 0.03333062254762473, "max": 7.419936299324036, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.091111448709853, "min": 3.091111448709853, "max": 118.71898078918457, "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": "1679610724", "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": "1679612814" }, "total": 2090.498308592, "count": 1, "self": 0.4884931799997503, "children": { "run_training.setup": { "total": 0.10559386300002416, "count": 1, "self": 0.10559386300002416 }, "TrainerController.start_learning": { "total": 2089.904221549, "count": 1, "self": 1.2651364339822067, "children": { "TrainerController._reset_env": { "total": 9.535622603999968, "count": 1, "self": 9.535622603999968 }, "TrainerController.advance": { "total": 2079.005559728018, "count": 63759, "self": 1.338772748055817, "children": { "env_step": { "total": 1459.4485326339875, "count": 63759, "self": 1355.485393834021, "children": { "SubprocessEnvManager._take_step": { "total": 103.20231278596935, "count": 63759, "self": 4.490495255994858, "children": { "TorchPolicy.evaluate": { "total": 98.7118175299745, "count": 62554, "self": 98.7118175299745 } } }, "workers": { "total": 0.7608260139973027, "count": 63759, "self": 0.0, "children": { "worker_root": { "total": 2085.4694389180236, "count": 63759, "is_parallel": true, "self": 840.9421633510105, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004436797999971986, "count": 1, "is_parallel": true, "self": 0.003127632000087033, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013091659998849536, "count": 8, "is_parallel": true, "self": 0.0013091659998849536 } } }, "UnityEnvironment.step": { "total": 0.05836178800001335, "count": 1, "is_parallel": true, "self": 0.0005200150000064241, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004611200000113058, "count": 1, "is_parallel": true, "self": 0.0004611200000113058 }, "communicator.exchange": { "total": 0.055850523000003705, "count": 1, "is_parallel": true, "self": 0.055850523000003705 }, "steps_from_proto": { "total": 0.0015301299999919138, "count": 1, "is_parallel": true, "self": 0.00036033700001780744, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011697929999741064, "count": 8, "is_parallel": true, "self": 0.0011697929999741064 } } } } } } }, "UnityEnvironment.step": { "total": 1244.527275567013, "count": 63758, "is_parallel": true, "self": 30.784473716957336, "children": { "UnityEnvironment._generate_step_input": { "total": 21.982547870017754, "count": 63758, "is_parallel": true, "self": 21.982547870017754 }, "communicator.exchange": { "total": 1102.9273557740357, "count": 63758, "is_parallel": true, "self": 1102.9273557740357 }, "steps_from_proto": { "total": 88.83289820600231, "count": 63758, "is_parallel": true, "self": 18.532680835093856, "children": { "_process_rank_one_or_two_observation": { "total": 70.30021737090846, "count": 510064, "is_parallel": true, "self": 70.30021737090846 } } } } } } } } } } }, "trainer_advance": { "total": 618.2182543459744, "count": 63759, "self": 2.4217223919733897, "children": { "process_trajectory": { "total": 116.19285698800093, "count": 63759, "self": 115.98753140800056, "children": { "RLTrainer._checkpoint": { "total": 0.2053255800003626, "count": 2, "self": 0.2053255800003626 } } }, "_update_policy": { "total": 499.6036749660001, "count": 456, "self": 315.16363107298946, "children": { "TorchPPOOptimizer.update": { "total": 184.44004389301062, "count": 22797, "self": 184.44004389301062 } } } } } } }, "trainer_threads": { "total": 9.149998732027598e-07, "count": 1, "self": 9.149998732027598e-07 }, "TrainerController._save_models": { "total": 0.09790186800000811, "count": 1, "self": 0.0013349249998100277, "children": { "RLTrainer._checkpoint": { "total": 0.09656694300019808, "count": 1, "self": 0.09656694300019808 } } } } } } }