{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5430715680122375, "min": 0.5403998494148254, "max": 1.5356767177581787, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16396.416015625, "min": 16226.873046875, "max": 46586.2890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989972.0, "min": 29952.0, "max": 989972.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989972.0, "min": 29952.0, "max": 989972.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6008288860321045, "min": -0.15741822123527527, "max": 0.6525148153305054, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 169.43374633789062, "min": -37.3081169128418, "max": 185.314208984375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.017631975933909416, "min": -0.015849707648158073, "max": 0.1572844386100769, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.972217082977295, "min": -4.231872081756592, "max": 37.905548095703125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06644938790885221, "min": 0.06539722719937054, "max": 0.07244533984800403, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.930291430723931, "min": 0.4938564800510809, "max": 1.0481661860608522, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01443157536587456, "min": 0.0007922115109313758, "max": 0.015847796152229417, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20204205512224385, "min": 0.010000805916912088, "max": 0.23771694228344128, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.487583218457144e-06, "min": 7.487583218457144e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010482616505840001, "min": 0.00010482616505840001, "max": 0.0035088803303732993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249582857142857, "min": 0.10249582857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4349416, "min": 1.3691136000000002, "max": 2.5696267, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025933327428571436, "min": 0.00025933327428571436, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003630665840000001, "min": 0.003630665840000001, "max": 0.11698570733, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009175741113722324, "min": 0.009175741113722324, "max": 0.28511667251586914, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1284603774547577, "min": 0.1284603774547577, "max": 1.995816707611084, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 333.7340425531915, "min": 290.4270833333333, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31371.0, "min": 15984.0, "max": 33222.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5844595529773133, "min": -1.0000000521540642, "max": 1.684756231494248, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 148.93919797986746, "min": -32.000001668930054, "max": 161.7365982234478, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5844595529773133, "min": -1.0000000521540642, "max": 1.684756231494248, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 148.93919797986746, "min": -32.000001668930054, "max": 161.7365982234478, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.030938343851185563, "min": 0.0281731246329097, "max": 5.722280306741595, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.908204322011443, "min": 2.704619964759331, "max": 91.55648490786552, "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": "1659090163", "python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1659092163" }, "total": 1999.7478218160002, "count": 1, "self": 0.48119585200038273, "children": { "run_training.setup": { "total": 0.041433439999991606, "count": 1, "self": 0.041433439999991606 }, "TrainerController.start_learning": { "total": 1999.2251925239998, "count": 1, "self": 1.2952241349653377, "children": { "TrainerController._reset_env": { "total": 9.982592898999997, "count": 1, "self": 9.982592898999997 }, "TrainerController.advance": { "total": 1987.8559386770344, "count": 63958, "self": 1.3849396150685607, "children": { "env_step": { "total": 1292.910904829967, "count": 63958, "self": 1190.3789859030132, "children": { "SubprocessEnvManager._take_step": { "total": 101.8549709739774, "count": 63958, "self": 4.619035221993272, "children": { "TorchPolicy.evaluate": { "total": 97.23593575198413, "count": 62561, "self": 33.399556241014466, "children": { "TorchPolicy.sample_actions": { "total": 63.836379510969664, "count": 62561, "self": 63.836379510969664 } } } } }, "workers": { "total": 0.6769479529763203, "count": 63958, "self": 0.0, "children": { "worker_root": { "total": 1995.360890769995, "count": 63958, "is_parallel": true, "self": 901.4789255730395, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.009251977999952032, "count": 1, "is_parallel": true, "self": 0.004771930999822871, "children": { "_process_rank_one_or_two_observation": { "total": 0.0044800470001291615, "count": 8, "is_parallel": true, "self": 0.0044800470001291615 } } }, "UnityEnvironment.step": { "total": 0.05625449799993021, "count": 1, "is_parallel": true, "self": 0.0004985639999404157, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004578549999223469, "count": 1, "is_parallel": true, "self": 0.0004578549999223469 }, "communicator.exchange": { "total": 0.04546531599999071, "count": 1, "is_parallel": true, "self": 0.04546531599999071 }, "steps_from_proto": { "total": 0.009832763000076739, "count": 1, "is_parallel": true, "self": 0.008097870000028706, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017348930000480323, "count": 8, "is_parallel": true, "self": 0.0017348930000480323 } } } } } } }, "UnityEnvironment.step": { "total": 1093.8819651969554, "count": 63957, "is_parallel": true, "self": 26.574679885016167, "children": { "UnityEnvironment._generate_step_input": { "total": 22.38909954195435, "count": 63957, "is_parallel": true, "self": 22.38909954195435 }, "communicator.exchange": { "total": 955.0587233659969, "count": 63957, "is_parallel": true, "self": 955.0587233659969 }, "steps_from_proto": { "total": 89.85946240398789, "count": 63957, "is_parallel": true, "self": 21.967423703942586, "children": { "_process_rank_one_or_two_observation": { "total": 67.8920387000453, "count": 511656, "is_parallel": true, "self": 67.8920387000453 } } } } } } } } } } }, "trainer_advance": { "total": 693.5600942319987, "count": 63958, "self": 2.400740247999238, "children": { "process_trajectory": { "total": 157.28593802299974, "count": 63958, "self": 157.08765719199982, "children": { "RLTrainer._checkpoint": { "total": 0.19828083099992, "count": 2, "self": 0.19828083099992 } } }, "_update_policy": { "total": 533.8734159609998, "count": 448, "self": 211.780137931009, "children": { "TorchPPOOptimizer.update": { "total": 322.09327802999076, "count": 22812, "self": 322.09327802999076 } } } } } } }, "trainer_threads": { "total": 1.294999947276665e-06, "count": 1, "self": 1.294999947276665e-06 }, "TrainerController._save_models": { "total": 0.09143551800025307, "count": 1, "self": 0.0015524960003858723, "children": { "RLTrainer._checkpoint": { "total": 0.0898830219998672, "count": 1, "self": 0.0898830219998672 } } } } } } }