{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.400333046913147, "min": 1.400333046913147, "max": 1.4260997772216797, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69142.84375, "min": 68472.421875, "max": 76921.6015625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 84.36923076923077, "min": 81.67933884297521, "max": 365.0652173913044, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49356.0, "min": 48697.0, "max": 50379.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999995.0, "min": 49864.0, "max": 1999995.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999995.0, "min": 49864.0, "max": 1999995.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.454421281814575, "min": 0.10832172632217407, "max": 2.459948778152466, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1435.83642578125, "min": 14.840076446533203, "max": 1458.5693359375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.847910755719894, "min": 1.8444304364006014, "max": 3.9321149037920544, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2251.027792096138, "min": 252.6869697868824, "max": 2308.112186253071, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.847910755719894, "min": 1.8444304364006014, "max": 3.9321149037920544, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2251.027792096138, "min": 252.6869697868824, "max": 2308.112186253071, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.0173363102179994, "min": 0.010469665343407542, "max": 0.021075139252934603, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0520089306539982, "min": 0.020939330686815083, "max": 0.056549897853134704, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05974018855227364, "min": 0.022797067929059268, "max": 0.061905471173425514, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17922056565682093, "min": 0.045594135858118535, "max": 0.18105556977291903, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.644698785133331e-06, "min": 3.644698785133331e-06, "max": 0.00029533305155565, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0934096355399993e-05, "min": 1.0934096355399993e-05, "max": 0.0008439310686896498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10121486666666664, "min": 0.10121486666666664, "max": 0.19844435000000007, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30364459999999993, "min": 0.2075663000000001, "max": 0.5813103500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.062184666666663e-05, "min": 7.062184666666663e-05, "max": 0.004922373065, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002118655399999999, "min": 0.0002118655399999999, "max": 0.014067386464999998, "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": "1728501612", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1728504068" }, "total": 2456.7454826919998, "count": 1, "self": 0.4782486929998413, "children": { "run_training.setup": { "total": 0.0531704869999885, "count": 1, "self": 0.0531704869999885 }, "TrainerController.start_learning": { "total": 2456.214063512, "count": 1, "self": 4.549294559937152, "children": { "TrainerController._reset_env": { "total": 2.641294743000003, "count": 1, "self": 2.641294743000003 }, "TrainerController.advance": { "total": 2448.8984768140626, "count": 232081, "self": 4.585644228016918, "children": { "env_step": { "total": 1942.1851096939668, "count": 232081, "self": 1530.553175141927, "children": { "SubprocessEnvManager._take_step": { "total": 408.7378744590576, "count": 232081, "self": 15.943703233111194, "children": { "TorchPolicy.evaluate": { "total": 392.7941712259464, "count": 222878, "self": 392.7941712259464 } } }, "workers": { "total": 2.8940600929820164, "count": 232081, "self": 0.0, "children": { "worker_root": { "total": 2448.6698922859814, "count": 232081, "is_parallel": true, "self": 1214.757528127894, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008608779999974558, "count": 1, "is_parallel": true, "self": 0.00023016000000097847, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006307179999964774, "count": 2, "is_parallel": true, "self": 0.0006307179999964774 } } }, "UnityEnvironment.step": { "total": 0.042793705999997655, "count": 1, "is_parallel": true, "self": 0.00035746200001085526, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000189906000002793, "count": 1, "is_parallel": true, "self": 0.000189906000002793 }, "communicator.exchange": { "total": 0.041535418999984586, "count": 1, "is_parallel": true, "self": 0.041535418999984586 }, "steps_from_proto": { "total": 0.0007109189999994214, "count": 1, "is_parallel": true, "self": 0.00017954000000486303, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005313789999945584, "count": 2, "is_parallel": true, "self": 0.0005313789999945584 } } } } } } }, "UnityEnvironment.step": { "total": 1233.9123641580875, "count": 232080, "is_parallel": true, "self": 38.60730855205588, "children": { "UnityEnvironment._generate_step_input": { "total": 80.1922030580129, "count": 232080, "is_parallel": true, "self": 80.1922030580129 }, "communicator.exchange": { "total": 1025.7806763779781, "count": 232080, "is_parallel": true, "self": 1025.7806763779781 }, "steps_from_proto": { "total": 89.33217617004055, "count": 232080, "is_parallel": true, "self": 31.752563018017668, "children": { "_process_rank_one_or_two_observation": { "total": 57.57961315202289, "count": 464160, "is_parallel": true, "self": 57.57961315202289 } } } } } } } } } } }, "trainer_advance": { "total": 502.12772289207896, "count": 232081, "self": 6.88801186800481, "children": { "process_trajectory": { "total": 159.3928727880739, "count": 232081, "self": 158.15174439707388, "children": { "RLTrainer._checkpoint": { "total": 1.241128391000018, "count": 10, "self": 1.241128391000018 } } }, "_update_policy": { "total": 335.8468382360003, "count": 97, "self": 267.9128009779985, "children": { "TorchPPOOptimizer.update": { "total": 67.93403725800181, "count": 2910, "self": 67.93403725800181 } } } } } } }, "trainer_threads": { "total": 1.3869998838345055e-06, "count": 1, "self": 1.3869998838345055e-06 }, "TrainerController._save_models": { "total": 0.12499600800038024, "count": 1, "self": 0.003185294000104477, "children": { "RLTrainer._checkpoint": { "total": 0.12181071400027577, "count": 1, "self": 0.12181071400027577 } } } } } } }