{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.15203063189983368, "min": 0.14053276181221008, "max": 1.4103035926818848, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4577.9462890625, "min": 4202.49169921875, "max": 42782.96875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999918.0, "min": 29952.0, "max": 2999918.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999918.0, "min": 29952.0, "max": 2999918.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8177449107170105, "min": -0.1107979565858841, "max": 0.8652896285057068, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 237.96376037597656, "min": -26.25911521911621, "max": 263.913330078125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.01927817612886429, "min": -0.029643071815371513, "max": 0.46698787808418274, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -5.609949111938477, "min": -8.833635330200195, "max": 110.6761245727539, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0691473407960508, "min": 0.06403176272611341, "max": 0.07347600741180275, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9680627711447112, "min": 0.5026552027113798, "max": 1.1021401111770412, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016618662770183402, "min": 0.0008706926021077818, "max": 0.01783035955318779, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23266127878256765, "min": 0.007140129523389172, "max": 0.24962503374462908, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5186709223809515e-06, "min": 1.5186709223809515e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.126139291333332e-05, "min": 2.126139291333332e-05, "max": 0.004027539657486833, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050619047619049, "min": 0.10050619047619049, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4070866666666668, "min": 1.3897045333333333, "max": 2.842513166666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.056842857142855e-05, "min": 6.056842857142855e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008479579999999997, "min": 0.0008479579999999997, "max": 0.13426706535, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.004635983612388372, "min": 0.004360624123364687, "max": 0.46898937225341797, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.06490377336740494, "min": 0.061048734933137894, "max": 3.282925605773926, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 229.91666666666666, "min": 212.5144927536232, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30349.0, "min": 15984.0, "max": 34083.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7397772594157495, "min": -1.0000000521540642, "max": 1.7874855026602745, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 229.6505982428789, "min": -32.000001668930054, "max": 254.66079790890217, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7397772594157495, "min": -1.0000000521540642, "max": 1.7874855026602745, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 229.6505982428789, "min": -32.000001668930054, "max": 254.66079790890217, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.011160180321067774, "min": 0.010439053346287794, "max": 10.495910690166056, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.473143802380946, "min": 1.354887372115627, "max": 167.9345710426569, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1706347339", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706354489" }, "total": 7149.72313752, "count": 1, "self": 0.5499679280001146, "children": { "run_training.setup": { "total": 0.05339519000006021, "count": 1, "self": 0.05339519000006021 }, "TrainerController.start_learning": { "total": 7149.119774402, "count": 1, "self": 4.089980641777402, "children": { "TrainerController._reset_env": { "total": 3.5298714709999786, "count": 1, "self": 3.5298714709999786 }, "TrainerController.advance": { "total": 7141.415326915222, "count": 194988, "self": 4.398533105972092, "children": { "env_step": { "total": 5281.456918374316, "count": 194988, "self": 4894.947816831289, "children": { "SubprocessEnvManager._take_step": { "total": 383.9678097149273, "count": 194988, "self": 13.989858812946068, "children": { "TorchPolicy.evaluate": { "total": 369.9779509019812, "count": 187562, "self": 369.9779509019812 } } }, "workers": { "total": 2.541291828099588, "count": 194988, "self": 0.0, "children": { "worker_root": { "total": 7133.16226059805, "count": 194988, "is_parallel": true, "self": 2589.9879491201546, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004638128999999935, "count": 1, "is_parallel": true, "self": 0.0034053889999086095, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012327400000913258, "count": 8, "is_parallel": true, "self": 0.0012327400000913258 } } }, "UnityEnvironment.step": { "total": 0.049273633999973754, "count": 1, "is_parallel": true, "self": 0.0006697079998048139, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004945230000430456, "count": 1, "is_parallel": true, "self": 0.0004945230000430456 }, "communicator.exchange": { "total": 0.04637342700004865, "count": 1, "is_parallel": true, "self": 0.04637342700004865 }, "steps_from_proto": { "total": 0.001735976000077244, "count": 1, "is_parallel": true, "self": 0.0003494359999649532, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013865400001122907, "count": 8, "is_parallel": true, "self": 0.0013865400001122907 } } } } } } }, "UnityEnvironment.step": { "total": 4543.174311477896, "count": 194987, "is_parallel": true, "self": 107.60928455516296, "children": { "UnityEnvironment._generate_step_input": { "total": 71.56180219894202, "count": 194987, "is_parallel": true, "self": 71.56180219894202 }, "communicator.exchange": { "total": 4066.689801674847, "count": 194987, "is_parallel": true, "self": 4066.689801674847 }, "steps_from_proto": { "total": 297.3134230489437, "count": 194987, "is_parallel": true, "self": 59.514508636176515, "children": { "_process_rank_one_or_two_observation": { "total": 237.7989144127672, "count": 1559896, "is_parallel": true, "self": 237.7989144127672 } } } } } } } } } } }, "trainer_advance": { "total": 1855.559875434934, "count": 194988, "self": 8.397914517819572, "children": { "process_trajectory": { "total": 382.78367352210887, "count": 194988, "self": 382.1682975781083, "children": { "RLTrainer._checkpoint": { "total": 0.6153759440005615, "count": 6, "self": 0.6153759440005615 } } }, "_update_policy": { "total": 1464.3782873950054, "count": 1394, "self": 862.6105566310114, "children": { "TorchPPOOptimizer.update": { "total": 601.767730763994, "count": 68385, "self": 601.767730763994 } } } } } } }, "trainer_threads": { "total": 9.10000380827114e-07, "count": 1, "self": 9.10000380827114e-07 }, "TrainerController._save_models": { "total": 0.08459446400047455, "count": 1, "self": 0.0017620660000829957, "children": { "RLTrainer._checkpoint": { "total": 0.08283239800039155, "count": 1, "self": 0.08283239800039155 } } } } } } }