{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4049642086029053, "min": 1.4049642086029053, "max": 1.428556203842163, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70902.921875, "min": 68327.734375, "max": 76707.4296875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 97.7775590551181, "min": 78.8738019169329, "max": 387.5658914728682, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49671.0, "min": 48750.0, "max": 50095.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999371.0, "min": 49668.0, "max": 1999371.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999371.0, "min": 49668.0, "max": 1999371.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.42022967338562, "min": 0.04760807007551193, "max": 2.468768835067749, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1227.056396484375, "min": 6.093832969665527, "max": 1510.866455078125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.642876012203021, "min": 1.8204811442410573, "max": 4.024749713494875, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1846.9381381869316, "min": 233.02158646285534, "max": 2420.6470046639442, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.642876012203021, "min": 1.8204811442410573, "max": 4.024749713494875, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1846.9381381869316, "min": 233.02158646285534, "max": 2420.6470046639442, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01835786722467674, "min": 0.014030101658742447, "max": 0.019640963254399443, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05507360167403021, "min": 0.02846602340723621, "max": 0.05516846326257413, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.052006659077273476, "min": 0.023063652962446213, "max": 0.05807067733258009, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15601997723182043, "min": 0.04612730592489243, "max": 0.1688065224637588, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.434998855033329e-06, "min": 3.434998855033329e-06, "max": 0.0002953128015623999, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0304996565099987e-05, "min": 1.0304996565099987e-05, "max": 0.0008441994186002, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10114496666666668, "min": 0.10114496666666668, "max": 0.19843760000000005, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30343490000000006, "min": 0.20748390000000005, "max": 0.5813998, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.713383666666661e-05, "min": 6.713383666666661e-05, "max": 0.00492203624, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020140150999999984, "min": 0.00020140150999999984, "max": 0.014071850020000002, "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": "1712952308", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1712955211" }, "total": 2902.572627037065, "count": 1, "self": 0.3214407730847597, "children": { "run_training.setup": { "total": 0.06065420003142208, "count": 1, "self": 0.06065420003142208 }, "TrainerController.start_learning": { "total": 2902.190532063949, "count": 1, "self": 5.324948667665012, "children": { "TrainerController._reset_env": { "total": 1.625615639030002, "count": 1, "self": 1.625615639030002 }, "TrainerController.advance": { "total": 2895.1339675892377, "count": 232607, "self": 4.545792457647622, "children": { "env_step": { "total": 2084.809494332527, "count": 232607, "self": 1784.9638197409222, "children": { "SubprocessEnvManager._take_step": { "total": 296.40793879167177, "count": 232607, "self": 16.653408057638444, "children": { "TorchPolicy.evaluate": { "total": 279.7545307340333, "count": 223024, "self": 279.7545307340333 } } }, "workers": { "total": 3.4377357999328524, "count": 232607, "self": 0.0, "children": { "worker_root": { "total": 2893.366999729653, "count": 232607, "is_parallel": true, "self": 1437.6284927389352, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010186409344896674, "count": 1, "is_parallel": true, "self": 0.00022984587121754885, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007887950632721186, "count": 2, "is_parallel": true, "self": 0.0007887950632721186 } } }, "UnityEnvironment.step": { "total": 0.021587357972748578, "count": 1, "is_parallel": true, "self": 0.0004103288520127535, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023256998974829912, "count": 1, "is_parallel": true, "self": 0.00023256998974829912 }, "communicator.exchange": { "total": 0.020270582055673003, "count": 1, "is_parallel": true, "self": 0.020270582055673003 }, "steps_from_proto": { "total": 0.0006738770753145218, "count": 1, "is_parallel": true, "self": 0.00019165303092449903, "children": { "_process_rank_one_or_two_observation": { "total": 0.00048222404439002275, "count": 2, "is_parallel": true, "self": 0.00048222404439002275 } } } } } } }, "UnityEnvironment.step": { "total": 1455.7385069907177, "count": 232606, "is_parallel": true, "self": 43.20328108756803, "children": { "UnityEnvironment._generate_step_input": { "total": 86.466388052213, "count": 232606, "is_parallel": true, "self": 86.466388052213 }, "communicator.exchange": { "total": 1227.5477296621539, "count": 232606, "is_parallel": true, "self": 1227.5477296621539 }, "steps_from_proto": { "total": 98.52110818878282, "count": 232606, "is_parallel": true, "self": 33.308417696272954, "children": { "_process_rank_one_or_two_observation": { "total": 65.21269049250986, "count": 465212, "is_parallel": true, "self": 65.21269049250986 } } } } } } } } } } }, "trainer_advance": { "total": 805.7786807990633, "count": 232607, "self": 8.536577785154805, "children": { "process_trajectory": { "total": 170.06571254250593, "count": 232607, "self": 169.02236655459274, "children": { "RLTrainer._checkpoint": { "total": 1.0433459879131988, "count": 10, "self": 1.0433459879131988 } } }, "_update_policy": { "total": 627.1763904714026, "count": 97, "self": 201.83014878607355, "children": { "TorchPPOOptimizer.update": { "total": 425.346241685329, "count": 2910, "self": 425.346241685329 } } } } } } }, "trainer_threads": { "total": 8.010538294911385e-07, "count": 1, "self": 8.010538294911385e-07 }, "TrainerController._save_models": { "total": 0.1059993669623509, "count": 1, "self": 0.0030439679976552725, "children": { "RLTrainer._checkpoint": { "total": 0.10295539896469563, "count": 1, "self": 0.10295539896469563 } } } } } } }