{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.403439998626709, "min": 1.403439998626709, "max": 1.4244681596755981, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70066.7421875, "min": 68974.9375, "max": 77271.9453125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 70.90647482014388, "min": 70.90647482014388, "max": 406.38709677419354, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49280.0, "min": 48769.0, "max": 50392.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999945.0, "min": 49901.0, "max": 1999945.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999945.0, "min": 49901.0, "max": 1999945.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.505805730819702, "min": 0.048853449523448944, "max": 2.584773063659668, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1741.5350341796875, "min": 6.008974075317383, "max": 1741.5350341796875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8617424060114853, "min": 1.8565165886307151, "max": 4.090605696740041, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2683.9109721779823, "min": 228.35154040157795, "max": 2689.3197382688522, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8617424060114853, "min": 1.8565165886307151, "max": 4.090605696740041, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2683.9109721779823, "min": 228.35154040157795, "max": 2689.3197382688522, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017147809871676144, "min": 0.011161911057327719, "max": 0.019129289959043186, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05144342961502844, "min": 0.022323822114655438, "max": 0.05518393944560861, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06017634636825986, "min": 0.021711290813982487, "max": 0.06638118258366982, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18052903910477958, "min": 0.04342258162796497, "max": 0.1871425696959098, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.851548716183334e-06, "min": 3.851548716183334e-06, "max": 0.000295354276548575, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1554646148550001e-05, "min": 1.1554646148550001e-05, "max": 0.0008440179186606997, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10128381666666665, "min": 0.10128381666666665, "max": 0.19845142500000001, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30385144999999997, "min": 0.20769945000000006, "max": 0.5813393, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.406245166666667e-05, "min": 7.406245166666667e-05, "max": 0.0049227261075, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.000222187355, "min": 0.000222187355, "max": 0.014068831070000003, "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": "1677489096", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "1.22.4", "end_time_seconds": "1677491556" }, "total": 2459.524642706, "count": 1, "self": 0.4438703280002301, "children": { "run_training.setup": { "total": 0.11794571399991582, "count": 1, "self": 0.11794571399991582 }, "TrainerController.start_learning": { "total": 2458.962826664, "count": 1, "self": 4.512183997808279, "children": { "TrainerController._reset_env": { "total": 10.2040178929999, "count": 1, "self": 10.2040178929999 }, "TrainerController.advance": { "total": 2444.1327445681923, "count": 233501, "self": 4.5674677113070175, "children": { "env_step": { "total": 1899.5905139060665, "count": 233501, "self": 1591.7194520769267, "children": { "SubprocessEnvManager._take_step": { "total": 304.8797597591499, "count": 233501, "self": 15.881425741083149, "children": { "TorchPolicy.evaluate": { "total": 288.99833401806677, "count": 222906, "self": 73.10165056308233, "children": { "TorchPolicy.sample_actions": { "total": 215.89668345498444, "count": 222906, "self": 215.89668345498444 } } } } }, "workers": { "total": 2.9913020699898425, "count": 233501, "self": 0.0, "children": { "worker_root": { "total": 2450.6087872069656, "count": 233501, "is_parallel": true, "self": 1151.904158835017, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009485929999755172, "count": 1, "is_parallel": true, "self": 0.00031145399998422363, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006371389999912935, "count": 2, "is_parallel": true, "self": 0.0006371389999912935 } } }, "UnityEnvironment.step": { "total": 0.0293614479999178, "count": 1, "is_parallel": true, "self": 0.0003073429998039501, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041190199999618926, "count": 1, "is_parallel": true, "self": 0.00041190199999618926 }, "communicator.exchange": { "total": 0.027920846999904825, "count": 1, "is_parallel": true, "self": 0.027920846999904825 }, "steps_from_proto": { "total": 0.0007213560002128361, "count": 1, "is_parallel": true, "self": 0.00025420600036341057, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004671499998494255, "count": 2, "is_parallel": true, "self": 0.0004671499998494255 } } } } } } }, "UnityEnvironment.step": { "total": 1298.7046283719487, "count": 233500, "is_parallel": true, "self": 39.992361281921376, "children": { "UnityEnvironment._generate_step_input": { "total": 81.12472420894323, "count": 233500, "is_parallel": true, "self": 81.12472420894323 }, "communicator.exchange": { "total": 1083.3870804390278, "count": 233500, "is_parallel": true, "self": 1083.3870804390278 }, "steps_from_proto": { "total": 94.20046244205628, "count": 233500, "is_parallel": true, "self": 38.0582799189649, "children": { "_process_rank_one_or_two_observation": { "total": 56.14218252309138, "count": 467000, "is_parallel": true, "self": 56.14218252309138 } } } } } } } } } } }, "trainer_advance": { "total": 539.974762950819, "count": 233501, "self": 6.634980813766106, "children": { "process_trajectory": { "total": 171.55158689505447, "count": 233501, "self": 170.25979737905436, "children": { "RLTrainer._checkpoint": { "total": 1.291789516000108, "count": 10, "self": 1.291789516000108 } } }, "_update_policy": { "total": 361.78819524199844, "count": 97, "self": 302.7442654520048, "children": { "TorchPPOOptimizer.update": { "total": 59.043929789993626, "count": 2910, "self": 59.043929789993626 } } } } } } }, "trainer_threads": { "total": 1.0270005077472888e-06, "count": 1, "self": 1.0270005077472888e-06 }, "TrainerController._save_models": { "total": 0.113879177999479, "count": 1, "self": 0.0020443139992494253, "children": { "RLTrainer._checkpoint": { "total": 0.11183486400022957, "count": 1, "self": 0.11183486400022957 } } } } } } }