{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4008177518844604, "min": 1.4008177518844604, "max": 1.4280157089233398, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69986.2578125, "min": 67774.8984375, "max": 77193.578125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 85.97565217391305, "min": 82.92398648648648, "max": 400.712, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49436.0, "min": 49091.0, "max": 50089.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999997.0, "min": 49621.0, "max": 1999997.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999997.0, "min": 49621.0, "max": 1999997.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4987056255340576, "min": 0.12661874294281006, "max": 2.512430429458618, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1436.7557373046875, "min": 15.700724601745605, "max": 1436.7557373046875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.859986280876657, "min": 1.9066035387016111, "max": 3.939363604175373, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2219.492111504078, "min": 236.4188387989998, "max": 2265.297887504101, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.859986280876657, "min": 1.9066035387016111, "max": 3.939363604175373, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2219.492111504078, "min": 236.4188387989998, "max": 2265.297887504101, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015355134943577773, "min": 0.013280546634814528, "max": 0.02037427671845459, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04606540483073332, "min": 0.026561093269629056, "max": 0.05869277207433091, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.052851752315958345, "min": 0.021292391885071996, "max": 0.06311339769098494, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15855525694787503, "min": 0.04258478377014399, "max": 0.1893401930729548, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.525698824800007e-06, "min": 3.525698824800007e-06, "max": 0.00029535765154745, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0577096474400021e-05, "min": 1.0577096474400021e-05, "max": 0.0008443215185595, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10117520000000003, "min": 0.10117520000000003, "max": 0.19845255000000006, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3035256000000001, "min": 0.20748535000000007, "max": 0.5814405, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.864248000000013e-05, "min": 6.864248000000013e-05, "max": 0.004922782245000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020592744000000036, "min": 0.00020592744000000036, "max": 0.014073880950000003, "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": "1713443418", "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": "1713446070" }, "total": 2651.82892942, "count": 1, "self": 0.4293209309998929, "children": { "run_training.setup": { "total": 0.05711900300002526, "count": 1, "self": 0.05711900300002526 }, "TrainerController.start_learning": { "total": 2651.342489486, "count": 1, "self": 5.195909679001943, "children": { "TrainerController._reset_env": { "total": 2.907927633999975, "count": 1, "self": 2.907927633999975 }, "TrainerController.advance": { "total": 2643.1136598619983, "count": 232281, "self": 5.314855447902119, "children": { "env_step": { "total": 2136.461182433965, "count": 232281, "self": 1768.9918955459416, "children": { "SubprocessEnvManager._take_step": { "total": 364.0396888008869, "count": 232281, "self": 19.33679880883949, "children": { "TorchPolicy.evaluate": { "total": 344.7028899920474, "count": 222976, "self": 344.7028899920474 } } }, "workers": { "total": 3.4295980871363554, "count": 232281, "self": 0.0, "children": { "worker_root": { "total": 2643.0556089109486, "count": 232281, "is_parallel": true, "self": 1220.5823617059827, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009735359999467619, "count": 1, "is_parallel": true, "self": 0.00026046200002838304, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007130739999183788, "count": 2, "is_parallel": true, "self": 0.0007130739999183788 } } }, "UnityEnvironment.step": { "total": 0.03149750599993695, "count": 1, "is_parallel": true, "self": 0.00037522899992836756, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022681699999793636, "count": 1, "is_parallel": true, "self": 0.00022681699999793636 }, "communicator.exchange": { "total": 0.03011596900000768, "count": 1, "is_parallel": true, "self": 0.03011596900000768 }, "steps_from_proto": { "total": 0.0007794910000029631, "count": 1, "is_parallel": true, "self": 0.00022894400001405302, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005505469999889101, "count": 2, "is_parallel": true, "self": 0.0005505469999889101 } } } } } } }, "UnityEnvironment.step": { "total": 1422.473247204966, "count": 232280, "is_parallel": true, "self": 42.24548512804495, "children": { "UnityEnvironment._generate_step_input": { "total": 92.72926845805046, "count": 232280, "is_parallel": true, "self": 92.72926845805046 }, "communicator.exchange": { "total": 1186.1179304759708, "count": 232280, "is_parallel": true, "self": 1186.1179304759708 }, "steps_from_proto": { "total": 101.38056314289975, "count": 232280, "is_parallel": true, "self": 38.68314235087496, "children": { "_process_rank_one_or_two_observation": { "total": 62.697420792024786, "count": 464560, "is_parallel": true, "self": 62.697420792024786 } } } } } } } } } } }, "trainer_advance": { "total": 501.3376219801313, "count": 232281, "self": 7.335905327153455, "children": { "process_trajectory": { "total": 170.7872854889772, "count": 232281, "self": 169.39237893697725, "children": { "RLTrainer._checkpoint": { "total": 1.3949065519999522, "count": 10, "self": 1.3949065519999522 } } }, "_update_policy": { "total": 323.21443116400064, "count": 97, "self": 259.15546562498616, "children": { "TorchPPOOptimizer.update": { "total": 64.05896553901448, "count": 2910, "self": 64.05896553901448 } } } } } } }, "trainer_threads": { "total": 9.420000424142927e-07, "count": 1, "self": 9.420000424142927e-07 }, "TrainerController._save_models": { "total": 0.12499136899987207, "count": 1, "self": 0.0025461330001235183, "children": { "RLTrainer._checkpoint": { "total": 0.12244523599974855, "count": 1, "self": 0.12244523599974855 } } } } } } }