{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4069550037384033, "min": 1.4069550037384033, "max": 1.4291449785232544, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69676.6328125, "min": 67468.7890625, "max": 79168.40625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 99.27254509018036, "min": 85.36960276338515, "max": 400.104, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49537.0, "min": 48948.0, "max": 50265.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999988.0, "min": 49662.0, "max": 1999988.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999988.0, "min": 49662.0, "max": 1999988.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.373408555984497, "min": 0.12964287400245667, "max": 2.4387221336364746, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1184.330810546875, "min": 16.075716018676758, "max": 1358.935791015625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.644252548834126, "min": 1.845403320486507, "max": 3.891535632170652, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1818.482021868229, "min": 228.83001174032688, "max": 2147.0735501646996, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.644252548834126, "min": 1.845403320486507, "max": 3.891535632170652, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1818.482021868229, "min": 228.83001174032688, "max": 2147.0735501646996, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015420427258868585, "min": 0.013037971539112429, "max": 0.020694163004130434, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04626128177660575, "min": 0.026075943078224858, "max": 0.05716715367743745, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04658467976583375, "min": 0.02014391797905167, "max": 0.059873149357736105, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.13975403929750124, "min": 0.04028783595810334, "max": 0.17063110110660396, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.332748889116671e-06, "min": 3.332748889116671e-06, "max": 0.0002953308015564, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.998246667350013e-06, "min": 9.998246667350013e-06, "max": 0.0008442975185674999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10111088333333333, "min": 0.10111088333333333, "max": 0.19844360000000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30333265, "min": 0.20736140000000003, "max": 0.5814325, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.54330783333334e-05, "min": 6.54330783333334e-05, "max": 0.004922335639999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019629923500000018, "min": 0.00019629923500000018, "max": 0.014073481749999998, "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": "1710398284", "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": "1710400882" }, "total": 2597.734648609, "count": 1, "self": 0.4346435410002414, "children": { "run_training.setup": { "total": 0.08154230200000256, "count": 1, "self": 0.08154230200000256 }, "TrainerController.start_learning": { "total": 2597.218462766, "count": 1, "self": 4.708363151927188, "children": { "TrainerController._reset_env": { "total": 3.1564010380000127, "count": 1, "self": 3.1564010380000127 }, "TrainerController.advance": { "total": 2589.2127543600723, "count": 231573, "self": 4.936838989038733, "children": { "env_step": { "total": 2105.187220401982, "count": 231573, "self": 1744.7295666619193, "children": { "SubprocessEnvManager._take_step": { "total": 357.2523121999992, "count": 231573, "self": 18.32544649299973, "children": { "TorchPolicy.evaluate": { "total": 338.9268657069995, "count": 222950, "self": 338.9268657069995 } } }, "workers": { "total": 3.2053415400635004, "count": 231573, "self": 0.0, "children": { "worker_root": { "total": 2589.223823378056, "count": 231573, "is_parallel": true, "self": 1182.9201934460807, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010197199999311124, "count": 1, "is_parallel": true, "self": 0.00027524999995875987, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007444699999723525, "count": 2, "is_parallel": true, "self": 0.0007444699999723525 } } }, "UnityEnvironment.step": { "total": 0.03377215199998318, "count": 1, "is_parallel": true, "self": 0.00041952700007641397, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023784999996223632, "count": 1, "is_parallel": true, "self": 0.00023784999996223632 }, "communicator.exchange": { "total": 0.03228447200001483, "count": 1, "is_parallel": true, "self": 0.03228447200001483 }, "steps_from_proto": { "total": 0.0008303029999296996, "count": 1, "is_parallel": true, "self": 0.000230776999956106, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005995259999735936, "count": 2, "is_parallel": true, "self": 0.0005995259999735936 } } } } } } }, "UnityEnvironment.step": { "total": 1406.3036299319751, "count": 231572, "is_parallel": true, "self": 41.98321078991489, "children": { "UnityEnvironment._generate_step_input": { "total": 91.58433723296037, "count": 231572, "is_parallel": true, "self": 91.58433723296037 }, "communicator.exchange": { "total": 1172.3151714751016, "count": 231572, "is_parallel": true, "self": 1172.3151714751016 }, "steps_from_proto": { "total": 100.42091043399819, "count": 231572, "is_parallel": true, "self": 37.63926806186282, "children": { "_process_rank_one_or_two_observation": { "total": 62.781642372135366, "count": 463144, "is_parallel": true, "self": 62.781642372135366 } } } } } } } } } } }, "trainer_advance": { "total": 479.0886949690515, "count": 231573, "self": 7.617989376027367, "children": { "process_trajectory": { "total": 166.36067559102162, "count": 231573, "self": 164.84121470602167, "children": { "RLTrainer._checkpoint": { "total": 1.519460884999944, "count": 10, "self": 1.519460884999944 } } }, "_update_policy": { "total": 305.11003000200253, "count": 97, "self": 252.26647844400134, "children": { "TorchPPOOptimizer.update": { "total": 52.843551558001195, "count": 2910, "self": 52.843551558001195 } } } } } } }, "trainer_threads": { "total": 9.88000010693213e-07, "count": 1, "self": 9.88000010693213e-07 }, "TrainerController._save_models": { "total": 0.14094322800019654, "count": 1, "self": 0.0022882130001562473, "children": { "RLTrainer._checkpoint": { "total": 0.1386550150000403, "count": 1, "self": 0.1386550150000403 } } } } } } }