{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.398431658744812, "min": 1.398431658744812, "max": 1.4240044355392456, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 67099.546875, "min": 67099.546875, "max": 78344.109375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 105.85042735042735, "min": 86.02409638554217, "max": 369.65441176470586, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49538.0, "min": 48886.0, "max": 50273.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999968.0, "min": 49897.0, "max": 1999968.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999968.0, "min": 49897.0, "max": 1999968.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.363431692123413, "min": 0.12198834121227264, "max": 2.4276421070098877, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1106.0860595703125, "min": 16.468425750732422, "max": 1397.197021484375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.578485259388247, "min": 1.8796319449389423, "max": 3.9106340042309466, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1674.7311013936996, "min": 253.7503125667572, "max": 2191.1711953878403, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.578485259388247, "min": 1.8796319449389423, "max": 3.9106340042309466, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1674.7311013936996, "min": 253.7503125667572, "max": 2191.1711953878403, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017450851236935707, "min": 0.01250910960904245, "max": 0.020396836054715095, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05235255371080712, "min": 0.0250182192180849, "max": 0.05606057652476011, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0461119541277488, "min": 0.021757023719449837, "max": 0.060382589263220626, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1383358623832464, "min": 0.043514047438899674, "max": 0.1607322908937931, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.099648966816663e-06, "min": 3.099648966816663e-06, "max": 0.00029529165156945, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.298946900449988e-06, "min": 9.298946900449988e-06, "max": 0.0008439732186756, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10103318333333332, "min": 0.10103318333333332, "max": 0.19843054999999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30309954999999994, "min": 0.20725859999999996, "max": 0.5813244000000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.155584833333326e-05, "min": 6.155584833333326e-05, "max": 0.004921684444999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00018466754499999979, "min": 0.00018466754499999979, "max": 0.01406808756, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1708417218", "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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1708419581" }, "total": 2362.432552364, "count": 1, "self": 0.4270175410001684, "children": { "run_training.setup": { "total": 0.053749740000000656, "count": 1, "self": 0.053749740000000656 }, "TrainerController.start_learning": { "total": 2361.951785083, "count": 1, "self": 4.455048316977809, "children": { "TrainerController._reset_env": { "total": 4.203484107999998, "count": 1, "self": 4.203484107999998 }, "TrainerController.advance": { "total": 2353.165035757022, "count": 232187, "self": 4.561431756958427, "children": { "env_step": { "total": 1860.9512419150612, "count": 232187, "self": 1539.8694124681351, "children": { "SubprocessEnvManager._take_step": { "total": 318.30668188497197, "count": 232187, "self": 16.268355266973686, "children": { "TorchPolicy.evaluate": { "total": 302.0383266179983, "count": 222896, "self": 302.0383266179983 } } }, "workers": { "total": 2.7751475619542134, "count": 232187, "self": 0.0, "children": { "worker_root": { "total": 2354.919834876975, "count": 232187, "is_parallel": true, "self": 1097.4163015280276, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009693439999978182, "count": 1, "is_parallel": true, "self": 0.00030220200005715014, "children": { "_process_rank_one_or_two_observation": { "total": 0.000667141999940668, "count": 2, "is_parallel": true, "self": 0.000667141999940668 } } }, "UnityEnvironment.step": { "total": 0.02961237799996752, "count": 1, "is_parallel": true, "self": 0.0003619499999558684, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00024220400001695452, "count": 1, "is_parallel": true, "self": 0.00024220400001695452 }, "communicator.exchange": { "total": 0.0282655980000186, "count": 1, "is_parallel": true, "self": 0.0282655980000186 }, "steps_from_proto": { "total": 0.0007426259999760987, "count": 1, "is_parallel": true, "self": 0.000200315999961731, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005423100000143677, "count": 2, "is_parallel": true, "self": 0.0005423100000143677 } } } } } } }, "UnityEnvironment.step": { "total": 1257.5035333489475, "count": 232186, "is_parallel": true, "self": 40.56701634484284, "children": { "UnityEnvironment._generate_step_input": { "total": 82.65228899707972, "count": 232186, "is_parallel": true, "self": 82.65228899707972 }, "communicator.exchange": { "total": 1042.7148564710242, "count": 232186, "is_parallel": true, "self": 1042.7148564710242 }, "steps_from_proto": { "total": 91.56937153600086, "count": 232186, "is_parallel": true, "self": 31.870957882966366, "children": { "_process_rank_one_or_two_observation": { "total": 59.69841365303449, "count": 464372, "is_parallel": true, "self": 59.69841365303449 } } } } } } } } } } }, "trainer_advance": { "total": 487.6523620850023, "count": 232187, "self": 6.570943276044602, "children": { "process_trajectory": { "total": 148.42332261195918, "count": 232187, "self": 147.18992148095924, "children": { "RLTrainer._checkpoint": { "total": 1.2334011309999369, "count": 10, "self": 1.2334011309999369 } } }, "_update_policy": { "total": 332.65809619699854, "count": 97, "self": 268.64470969799623, "children": { "TorchPPOOptimizer.update": { "total": 64.01338649900231, "count": 2910, "self": 64.01338649900231 } } } } } } }, "trainer_threads": { "total": 9.40000063565094e-07, "count": 1, "self": 9.40000063565094e-07 }, "TrainerController._save_models": { "total": 0.12821596100002353, "count": 1, "self": 0.003180402999987564, "children": { "RLTrainer._checkpoint": { "total": 0.12503555800003596, "count": 1, "self": 0.12503555800003596 } } } } } } }