{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.400299072265625, "min": 1.400299072265625, "max": 1.4274228811264038, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69986.9453125, "min": 68474.5234375, "max": 78513.921875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 86.40034965034965, "min": 73.76347305389221, "max": 404.26612903225805, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49421.0, "min": 48724.0, "max": 50129.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999980.0, "min": 49895.0, "max": 1999980.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999980.0, "min": 49895.0, "max": 1999980.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4926910400390625, "min": 0.1457328200340271, "max": 2.506725549697876, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1425.8192138671875, "min": 17.92513656616211, "max": 1632.32763671875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.846360136162151, "min": 1.7908403829830448, "max": 4.018891125725162, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2200.1179978847504, "min": 220.27336710691452, "max": 2633.8355873823166, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.846360136162151, "min": 1.7908403829830448, "max": 4.018891125725162, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2200.1179978847504, "min": 220.27336710691452, "max": 2633.8355873823166, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015821519006779756, "min": 0.012488718456976737, "max": 0.0205345105927942, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04746455702033927, "min": 0.024977436913953474, "max": 0.058720966811718726, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.058217582354942954, "min": 0.02047190396115184, "max": 0.06092919040885236, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17465274706482886, "min": 0.04094380792230368, "max": 0.1827875712265571, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.8421487193166635e-06, "min": 3.8421487193166635e-06, "max": 0.00029530747656417503, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.152644615794999e-05, "min": 1.152644615794999e-05, "max": 0.0008442117185960999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10128068333333334, "min": 0.10128068333333334, "max": 0.19843582499999995, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30384205000000003, "min": 0.20769769999999993, "max": 0.5814039, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.390609833333329e-05, "min": 7.390609833333329e-05, "max": 0.004921947667499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022171829499999989, "min": 0.00022171829499999989, "max": 0.014072054609999999, "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": "1672036747", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.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": "1672038996" }, "total": 2248.8344034300003, "count": 1, "self": 0.45002841100040314, "children": { "run_training.setup": { "total": 0.11391925300006278, "count": 1, "self": 0.11391925300006278 }, "TrainerController.start_learning": { "total": 2248.270455766, "count": 1, "self": 3.8074966100803067, "children": { "TrainerController._reset_env": { "total": 9.545143664999955, "count": 1, "self": 9.545143664999955 }, "TrainerController.advance": { "total": 2234.80112889892, "count": 233215, "self": 3.914636908841203, "children": { "env_step": { "total": 1749.9959939420407, "count": 233215, "self": 1471.2259382900697, "children": { "SubprocessEnvManager._take_step": { "total": 276.2135089940499, "count": 233215, "self": 14.070031714941024, "children": { "TorchPolicy.evaluate": { "total": 262.1434772791089, "count": 222964, "self": 65.42770486709765, "children": { "TorchPolicy.sample_actions": { "total": 196.71577241201123, "count": 222964, "self": 196.71577241201123 } } } } }, "workers": { "total": 2.5565466579211034, "count": 233215, "self": 0.0, "children": { "worker_root": { "total": 2240.70013061396, "count": 233215, "is_parallel": true, "self": 1027.336393327867, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023734279999416685, "count": 1, "is_parallel": true, "self": 0.0003770519998624877, "children": { "_process_rank_one_or_two_observation": { "total": 0.001996376000079181, "count": 2, "is_parallel": true, "self": 0.001996376000079181 } } }, "UnityEnvironment.step": { "total": 0.02716755199992349, "count": 1, "is_parallel": true, "self": 0.00033922199986591295, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019188700002814585, "count": 1, "is_parallel": true, "self": 0.00019188700002814585 }, "communicator.exchange": { "total": 0.025847496999972464, "count": 1, "is_parallel": true, "self": 0.025847496999972464 }, "steps_from_proto": { "total": 0.000788946000056967, "count": 1, "is_parallel": true, "self": 0.0002749049999692943, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005140410000876727, "count": 2, "is_parallel": true, "self": 0.0005140410000876727 } } } } } } }, "UnityEnvironment.step": { "total": 1213.363737286093, "count": 233214, "is_parallel": true, "self": 34.963868368045496, "children": { "UnityEnvironment._generate_step_input": { "total": 76.43656320104185, "count": 233214, "is_parallel": true, "self": 76.43656320104185 }, "communicator.exchange": { "total": 1008.1058482859477, "count": 233214, "is_parallel": true, "self": 1008.1058482859477 }, "steps_from_proto": { "total": 93.85745743105804, "count": 233214, "is_parallel": true, "self": 38.54955233610963, "children": { "_process_rank_one_or_two_observation": { "total": 55.30790509494841, "count": 466428, "is_parallel": true, "self": 55.30790509494841 } } } } } } } } } } }, "trainer_advance": { "total": 480.8904980480379, "count": 233215, "self": 5.945233951227692, "children": { "process_trajectory": { "total": 153.4257775728105, "count": 233215, "self": 152.18474056881053, "children": { "RLTrainer._checkpoint": { "total": 1.2410370039999634, "count": 10, "self": 1.2410370039999634 } } }, "_update_policy": { "total": 321.5194865239997, "count": 97, "self": 268.2412857119938, "children": { "TorchPPOOptimizer.update": { "total": 53.278200812005934, "count": 2910, "self": 53.278200812005934 } } } } } } }, "trainer_threads": { "total": 8.089996299531776e-07, "count": 1, "self": 8.089996299531776e-07 }, "TrainerController._save_models": { "total": 0.1166857829998662, "count": 1, "self": 0.002079122999930405, "children": { "RLTrainer._checkpoint": { "total": 0.1146066599999358, "count": 1, "self": 0.1146066599999358 } } } } } } }