{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.421501636505127, "min": 1.419641137123108, "max": 1.4283298254013062, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71123.4140625, "min": 69530.4921875, "max": 77560.671875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 118.55023923444976, "min": 108.88716814159292, "max": 409.72131147540983, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49554.0, "min": 48944.0, "max": 50184.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999891.0, "min": 49430.0, "max": 1999891.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999891.0, "min": 49430.0, "max": 1999891.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.2462823390960693, "min": 0.20366232097148895, "max": 2.299947738647461, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 938.946044921875, "min": 24.64314079284668, "max": 1023.0962524414062, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.272681702409635, "min": 1.7334351430008235, "max": 3.702108436910977, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1367.9809516072273, "min": 209.74565230309963, "max": 1535.6491479873657, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.272681702409635, "min": 1.7334351430008235, "max": 3.702108436910977, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1367.9809516072273, "min": 209.74565230309963, "max": 1535.6491479873657, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.02239243977952204, "min": 0.020555553326054604, "max": 0.028435924806399268, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04478487955904408, "min": 0.04111110665210921, "max": 0.08058194544206951, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.058475721379121146, "min": 0.019410797798385223, "max": 0.07435120747735102, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.11695144275824229, "min": 0.038821595596770446, "max": 0.20392057591428359, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 1.3362736638250007e-06, "min": 1.3362736638250007e-06, "max": 9.843765156235e-05, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 2.6725473276500013e-06, "min": 2.6725473276500013e-06, "max": 0.0002812676187324, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.101336175, "min": 0.101336175, "max": 0.19843764999999997, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20267235, "min": 0.20267235, "max": 0.5812676000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.667513250000005e-05, "min": 7.667513250000005e-05, "max": 0.004922038735, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001533502650000001, "min": 0.0001533502650000001, "max": 0.01406525324, "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": "1719776285", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719778643" }, "total": 2357.920766067, "count": 1, "self": 0.43564098599972567, "children": { "run_training.setup": { "total": 0.058938295000075414, "count": 1, "self": 0.058938295000075414 }, "TrainerController.start_learning": { "total": 2357.426186786, "count": 1, "self": 4.12892713711517, "children": { "TrainerController._reset_env": { "total": 3.0258808180000187, "count": 1, "self": 3.0258808180000187 }, "TrainerController.advance": { "total": 2350.1574296918843, "count": 230005, "self": 4.4736962369474895, "children": { "env_step": { "total": 1853.1280762170027, "count": 230005, "self": 1525.028010375123, "children": { "SubprocessEnvManager._take_step": { "total": 325.409023331046, "count": 230005, "self": 18.071190485065017, "children": { "TorchPolicy.evaluate": { "total": 307.337832845981, "count": 222954, "self": 307.337832845981 } } }, "workers": { "total": 2.6910425108337677, "count": 230005, "self": 0.0, "children": { "worker_root": { "total": 2350.548162672934, "count": 230005, "is_parallel": true, "self": 1123.6322580508236, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008689430000003995, "count": 1, "is_parallel": true, "self": 0.00023397300003580312, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006349699999645964, "count": 2, "is_parallel": true, "self": 0.0006349699999645964 } } }, "UnityEnvironment.step": { "total": 0.0470178880000276, "count": 1, "is_parallel": true, "self": 0.0004008330000715432, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022628700003224367, "count": 1, "is_parallel": true, "self": 0.00022628700003224367 }, "communicator.exchange": { "total": 0.04565471199998683, "count": 1, "is_parallel": true, "self": 0.04565471199998683 }, "steps_from_proto": { "total": 0.0007360559999369798, "count": 1, "is_parallel": true, "self": 0.00019415399992794846, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005419020000090313, "count": 2, "is_parallel": true, "self": 0.0005419020000090313 } } } } } } }, "UnityEnvironment.step": { "total": 1226.9159046221102, "count": 230004, "is_parallel": true, "self": 38.189255873051934, "children": { "UnityEnvironment._generate_step_input": { "total": 79.45040893999567, "count": 230004, "is_parallel": true, "self": 79.45040893999567 }, "communicator.exchange": { "total": 1022.2803212870464, "count": 230004, "is_parallel": true, "self": 1022.2803212870464 }, "steps_from_proto": { "total": 86.99591852201638, "count": 230004, "is_parallel": true, "self": 30.903369754098776, "children": { "_process_rank_one_or_two_observation": { "total": 56.092548767917606, "count": 460008, "is_parallel": true, "self": 56.092548767917606 } } } } } } } } } } }, "trainer_advance": { "total": 492.55565723793404, "count": 230005, "self": 6.512332595875364, "children": { "process_trajectory": { "total": 140.24750831805818, "count": 230005, "self": 138.84322778005753, "children": { "RLTrainer._checkpoint": { "total": 1.4042805380006484, "count": 10, "self": 1.4042805380006484 } } }, "_update_policy": { "total": 345.7958163240005, "count": 96, "self": 264.81137970899283, "children": { "TorchPPOOptimizer.update": { "total": 80.98443661500767, "count": 5760, "self": 80.98443661500767 } } } } } } }, "trainer_threads": { "total": 8.840002010401804e-07, "count": 1, "self": 8.840002010401804e-07 }, "TrainerController._save_models": { "total": 0.11394825500019579, "count": 1, "self": 0.0018558940000730217, "children": { "RLTrainer._checkpoint": { "total": 0.11209236100012276, "count": 1, "self": 0.11209236100012276 } } } } } } }