{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4033032655715942, "min": 1.4033032655715942, "max": 1.4249807596206665, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70492.1328125, "min": 68802.046875, "max": 76380.78125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 78.578025477707, "min": 73.26386806596702, "max": 434.4869565217391, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49347.0, "min": 48787.0, "max": 50188.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999972.0, "min": 49684.0, "max": 1999972.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999972.0, "min": 49684.0, "max": 1999972.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.5732479095458984, "min": 0.13948076963424683, "max": 2.5819976329803467, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1615.9996337890625, "min": 15.90080738067627, "max": 1661.6212158203125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.942289831532035, "min": 1.8745373069194324, "max": 4.082796751472511, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2475.758014202118, "min": 213.6972529888153, "max": 2604.3514647483826, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.942289831532035, "min": 1.8745373069194324, "max": 4.082796751472511, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2475.758014202118, "min": 213.6972529888153, "max": 2604.3514647483826, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01712366182796864, "min": 0.014203698992949083, "max": 0.020757563427226462, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05137098548390592, "min": 0.02861826415901305, "max": 0.05961408666626085, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05998276794950167, "min": 0.021939164493232965, "max": 0.06578516252338887, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17994830384850502, "min": 0.04387832898646593, "max": 0.18790790637334187, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.824448725216665e-06, "min": 3.824448725216665e-06, "max": 0.00029530185156604997, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1473346175649995e-05, "min": 1.1473346175649995e-05, "max": 0.00084410566863145, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10127478333333335, "min": 0.10127478333333335, "max": 0.19843395000000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3038243500000001, "min": 0.20768175, "max": 0.58136855, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.361168833333331e-05, "min": 7.361168833333331e-05, "max": 0.004921854105, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002208350649999999, "min": 0.0002208350649999999, "max": 0.014070290644999997, "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": "1692588373", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --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": "1692591229" }, "total": 2855.823684252, "count": 1, "self": 0.48961422400043375, "children": { "run_training.setup": { "total": 0.04447024799998189, "count": 1, "self": 0.04447024799998189 }, "TrainerController.start_learning": { "total": 2855.2895997799997, "count": 1, "self": 5.412460870029463, "children": { "TrainerController._reset_env": { "total": 4.3527883670000165, "count": 1, "self": 4.3527883670000165 }, "TrainerController.advance": { "total": 2845.39381210197, "count": 233285, "self": 5.727603472927967, "children": { "env_step": { "total": 2207.3491729929747, "count": 233285, "self": 1862.3848405699678, "children": { "SubprocessEnvManager._take_step": { "total": 341.3665046609953, "count": 233285, "self": 19.628891260032276, "children": { "TorchPolicy.evaluate": { "total": 321.737613400963, "count": 222988, "self": 321.737613400963 } } }, "workers": { "total": 3.5978277620116614, "count": 233285, "self": 0.0, "children": { "worker_root": { "total": 2846.2022013600845, "count": 233285, "is_parallel": true, "self": 1331.380868313142, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009948740000140788, "count": 1, "is_parallel": true, "self": 0.00028838499997618783, "children": { "_process_rank_one_or_two_observation": { "total": 0.000706489000037891, "count": 2, "is_parallel": true, "self": 0.000706489000037891 } } }, "UnityEnvironment.step": { "total": 0.034967052000013155, "count": 1, "is_parallel": true, "self": 0.00047572799996942194, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000222890000031839, "count": 1, "is_parallel": true, "self": 0.000222890000031839 }, "communicator.exchange": { "total": 0.03321638400001348, "count": 1, "is_parallel": true, "self": 0.03321638400001348 }, "steps_from_proto": { "total": 0.0010520499999984168, "count": 1, "is_parallel": true, "self": 0.0003035969999700683, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007484530000283485, "count": 2, "is_parallel": true, "self": 0.0007484530000283485 } } } } } } }, "UnityEnvironment.step": { "total": 1514.8213330469425, "count": 233284, "is_parallel": true, "self": 45.73659288073782, "children": { "UnityEnvironment._generate_step_input": { "total": 96.3550253270397, "count": 233284, "is_parallel": true, "self": 96.3550253270397 }, "communicator.exchange": { "total": 1257.6739276020603, "count": 233284, "is_parallel": true, "self": 1257.6739276020603 }, "steps_from_proto": { "total": 115.05578723710477, "count": 233284, "is_parallel": true, "self": 42.87632490210245, "children": { "_process_rank_one_or_two_observation": { "total": 72.17946233500231, "count": 466568, "is_parallel": true, "self": 72.17946233500231 } } } } } } } } } } }, "trainer_advance": { "total": 632.3170356360674, "count": 233285, "self": 8.147276750107949, "children": { "process_trajectory": { "total": 168.21273297896124, "count": 233285, "self": 166.63160614696102, "children": { "RLTrainer._checkpoint": { "total": 1.5811268320002227, "count": 10, "self": 1.5811268320002227 } } }, "_update_policy": { "total": 455.95702590699824, "count": 97, "self": 391.3517937909936, "children": { "TorchPPOOptimizer.update": { "total": 64.60523211600463, "count": 2910, "self": 64.60523211600463 } } } } } } }, "trainer_threads": { "total": 1.0960002327919938e-06, "count": 1, "self": 1.0960002327919938e-06 }, "TrainerController._save_models": { "total": 0.13053734499999337, "count": 1, "self": 0.0019406910000725475, "children": { "RLTrainer._checkpoint": { "total": 0.12859665399992082, "count": 1, "self": 0.12859665399992082 } } } } } } }