{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.14053481817245483, "min": 0.13928773999214172, "max": 1.4065355062484741, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 4202.55322265625, "min": 4196.4609375, "max": 42668.66015625, "count": 50 }, "Pyramids.Step.mean": { "value": 1499986.0, "min": 29952.0, "max": 1499986.0, "count": 50 }, "Pyramids.Step.sum": { "value": 1499986.0, "min": 29952.0, "max": 1499986.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7051174640655518, "min": -0.0933782309293747, "max": 0.707065999507904, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 203.77894592285156, "min": -22.504154205322266, "max": 203.80322265625, "count": 50 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.03919528052210808, "min": -0.03919528052210808, "max": 0.41959497332572937, "count": 50 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -11.327436447143555, "min": -11.327436447143555, "max": 99.44400787353516, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0674659584571297, "min": 0.06262744817391244, "max": 0.07514230743179033, "count": 50 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9445234183998159, "min": 0.5259961520225324, "max": 1.069288924258823, "count": 50 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016326619165955066, "min": 0.0005750133386977813, "max": 0.017437707847594058, "count": 50 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22857266832337092, "min": 0.007475173403071156, "max": 0.24412790986631683, "count": 50 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.8425133382428602e-06, "min": 2.8425133382428602e-06, "max": 0.00029676708679192377, "count": 50 }, "Pyramids.Policy.LearningRate.sum": { "value": 3.9795186735400046e-05, "min": 3.9795186735400046e-05, "max": 0.003822241525919532, "count": 50 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10094747142857144, "min": 0.10094747142857144, "max": 0.19892236190476195, "count": 50 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4132646000000002, "min": 1.3924565333333336, "max": 2.674080466666666, "count": 50 }, "Pyramids.Policy.Beta.mean": { "value": 0.00010465239571428584, "min": 0.00010465239571428584, "max": 0.009892343954285714, "count": 50 }, "Pyramids.Policy.Beta.sum": { "value": 0.0014651335400000017, "min": 0.0014651335400000017, "max": 0.12742063862, "count": 50 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00916439201682806, "min": 0.00916439201682806, "max": 0.5181770324707031, "count": 50 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1283014863729477, "min": 0.1283014863729477, "max": 3.627239227294922, "count": 50 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 272.76146788990826, "min": 272.76146788990826, "max": 999.0, "count": 50 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29731.0, "min": 15984.0, "max": 33803.0, "count": 50 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6734618039293723, "min": -1.0000000521540642, "max": 1.6886396261754337, "count": 50 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 184.08079843223095, "min": -30.40180167555809, "max": 187.43899850547314, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6734618039293723, "min": -1.0000000521540642, "max": 1.6886396261754337, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 184.08079843223095, "min": -30.40180167555809, "max": 187.43899850547314, "count": 50 }, "Pyramids.Policy.RndReward.mean": { "value": 0.025649223635131918, "min": 0.025649223635131918, "max": 10.681833160109818, "count": 50 }, "Pyramids.Policy.RndReward.sum": { "value": 2.821414599864511, "min": 2.7977606503118295, "max": 170.9093305617571, "count": 50 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1688754042", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --force --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": "1688757826" }, "total": 3784.205946556, "count": 1, "self": 0.48168068499990113, "children": { "run_training.setup": { "total": 0.06879656699993575, "count": 1, "self": 0.06879656699993575 }, "TrainerController.start_learning": { "total": 3783.6554693040002, "count": 1, "self": 2.5166038870070224, "children": { "TrainerController._reset_env": { "total": 4.4145211469999595, "count": 1, "self": 4.4145211469999595 }, "TrainerController.advance": { "total": 3776.586164051993, "count": 96604, "self": 2.525025175974406, "children": { "env_step": { "total": 2708.578499910981, "count": 96604, "self": 2511.7418109112964, "children": { "SubprocessEnvManager._take_step": { "total": 195.379112822769, "count": 96604, "self": 8.057525883777544, "children": { "TorchPolicy.evaluate": { "total": 187.32158693899146, "count": 93814, "self": 187.32158693899146 } } }, "workers": { "total": 1.4575761769156088, "count": 96604, "self": 0.0, "children": { "worker_root": { "total": 3775.0063772899825, "count": 96604, "is_parallel": true, "self": 1459.7662628709631, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019624050000857096, "count": 1, "is_parallel": true, "self": 0.0006006399999023415, "children": { "_process_rank_one_or_two_observation": { "total": 0.001361765000183368, "count": 8, "is_parallel": true, "self": 0.001361765000183368 } } }, "UnityEnvironment.step": { "total": 0.05161068999996132, "count": 1, "is_parallel": true, "self": 0.0006188759998622118, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005636890000459971, "count": 1, "is_parallel": true, "self": 0.0005636890000459971 }, "communicator.exchange": { "total": 0.048234598000362894, "count": 1, "is_parallel": true, "self": 0.048234598000362894 }, "steps_from_proto": { "total": 0.0021935269996902207, "count": 1, "is_parallel": true, "self": 0.0004325119989516679, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017610150007385528, "count": 8, "is_parallel": true, "self": 0.0017610150007385528 } } } } } } }, "UnityEnvironment.step": { "total": 2315.2401144190194, "count": 96603, "is_parallel": true, "self": 53.763775315941075, "children": { "UnityEnvironment._generate_step_input": { "total": 38.22856370390946, "count": 96603, "is_parallel": true, "self": 38.22856370390946 }, "communicator.exchange": { "total": 2045.5248481610647, "count": 96603, "is_parallel": true, "self": 2045.5248481610647 }, "steps_from_proto": { "total": 177.72292723810415, "count": 96603, "is_parallel": true, "self": 35.45905996062629, "children": { "_process_rank_one_or_two_observation": { "total": 142.26386727747786, "count": 772824, "is_parallel": true, "self": 142.26386727747786 } } } } } } } } } } }, "trainer_advance": { "total": 1065.4826389650375, "count": 96604, "self": 4.503068927032473, "children": { "process_trajectory": { "total": 189.3618999700052, "count": 96604, "self": 188.85254729900544, "children": { "RLTrainer._checkpoint": { "total": 0.5093526709997604, "count": 3, "self": 0.5093526709997604 } } }, "_update_policy": { "total": 871.6176700679998, "count": 692, "self": 545.8149057210476, "children": { "TorchPPOOptimizer.update": { "total": 325.80276434695224, "count": 34119, "self": 325.80276434695224 } } } } } } }, "trainer_threads": { "total": 1.0090006981045008e-06, "count": 1, "self": 1.0090006981045008e-06 }, "TrainerController._save_models": { "total": 0.1381792089996452, "count": 1, "self": 0.003581619999749819, "children": { "RLTrainer._checkpoint": { "total": 0.13459758899989538, "count": 1, "self": 0.13459758899989538 } } } } } } }