{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.405837893486023, "min": 1.4058339595794678, "max": 1.4262365102767944, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70651.7890625, "min": 68903.578125, "max": 78616.09375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 84.984375, "min": 79.34726688102894, "max": 373.6119402985075, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48951.0, "min": 48841.0, "max": 50064.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999999.0, "min": 49603.0, "max": 1999999.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999999.0, "min": 49603.0, "max": 1999999.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.364847183227539, "min": 0.04370806738734245, "max": 2.480018138885498, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1362.1519775390625, "min": 5.813172817230225, "max": 1487.855224609375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.642579498804278, "min": 1.775083649427371, "max": 3.972241052372489, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2098.125791311264, "min": 236.08612537384033, "max": 2353.7240110635757, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.642579498804278, "min": 1.775083649427371, "max": 3.972241052372489, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2098.125791311264, "min": 236.08612537384033, "max": 2353.7240110635757, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016220566683720485, "min": 0.013456320580250272, "max": 0.020434885129927555, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04866170005116146, "min": 0.026912641160500544, "max": 0.061304655389782664, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.052796984381145905, "min": 0.023547920895119506, "max": 0.06764710110922655, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1583909531434377, "min": 0.04709584179023901, "max": 0.19310510804255804, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3824988725333296e-06, "min": 3.3824988725333296e-06, "max": 0.0002953525515491499, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0147496617599989e-05, "min": 1.0147496617599989e-05, "max": 0.0008440641186452999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10112746666666665, "min": 0.10112746666666665, "max": 0.19845085, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30338239999999994, "min": 0.20749104999999995, "max": 0.5813547000000003, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.62605866666666e-05, "min": 6.62605866666666e-05, "max": 0.004922697415, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019878175999999982, "min": 0.00019878175999999982, "max": 0.01406959953, "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": "1713655344", "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": "1713657803" }, "total": 2458.673666606, "count": 1, "self": 0.43585305300030086, "children": { "run_training.setup": { "total": 0.0556143300000258, "count": 1, "self": 0.0556143300000258 }, "TrainerController.start_learning": { "total": 2458.1821992229998, "count": 1, "self": 4.710714225032461, "children": { "TrainerController._reset_env": { "total": 2.9057533650000096, "count": 1, "self": 2.9057533650000096 }, "TrainerController.advance": { "total": 2450.437487672967, "count": 232634, "self": 5.004118031979942, "children": { "env_step": { "total": 1959.870924064061, "count": 232634, "self": 1627.747245508916, "children": { "SubprocessEnvManager._take_step": { "total": 329.14931499506895, "count": 232634, "self": 17.285936001954724, "children": { "TorchPolicy.evaluate": { "total": 311.8633789931142, "count": 222986, "self": 311.8633789931142 } } }, "workers": { "total": 2.9743635600759717, "count": 232634, "self": 0.0, "children": { "worker_root": { "total": 2450.7193992710068, "count": 232634, "is_parallel": true, "self": 1137.1943484629605, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009026090000361364, "count": 1, "is_parallel": true, "self": 0.00024551600006361696, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006570929999725195, "count": 2, "is_parallel": true, "self": 0.0006570929999725195 } } }, "UnityEnvironment.step": { "total": 0.02884926199999427, "count": 1, "is_parallel": true, "self": 0.0003772379999418263, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002032580000559392, "count": 1, "is_parallel": true, "self": 0.0002032580000559392 }, "communicator.exchange": { "total": 0.027523728000005576, "count": 1, "is_parallel": true, "self": 0.027523728000005576 }, "steps_from_proto": { "total": 0.0007450379999909273, "count": 1, "is_parallel": true, "self": 0.0001958469999863155, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005491910000046119, "count": 2, "is_parallel": true, "self": 0.0005491910000046119 } } } } } } }, "UnityEnvironment.step": { "total": 1313.5250508080462, "count": 232633, "is_parallel": true, "self": 40.45645119101073, "children": { "UnityEnvironment._generate_step_input": { "total": 83.90284661603835, "count": 232633, "is_parallel": true, "self": 83.90284661603835 }, "communicator.exchange": { "total": 1095.8140312429655, "count": 232633, "is_parallel": true, "self": 1095.8140312429655 }, "steps_from_proto": { "total": 93.35172175803166, "count": 232633, "is_parallel": true, "self": 33.19465344915659, "children": { "_process_rank_one_or_two_observation": { "total": 60.15706830887507, "count": 465266, "is_parallel": true, "self": 60.15706830887507 } } } } } } } } } } }, "trainer_advance": { "total": 485.56244557692617, "count": 232634, "self": 7.16383060876376, "children": { "process_trajectory": { "total": 155.13000979616072, "count": 232634, "self": 153.77212275816157, "children": { "RLTrainer._checkpoint": { "total": 1.3578870379991486, "count": 10, "self": 1.3578870379991486 } } }, "_update_policy": { "total": 323.2686051720017, "count": 97, "self": 258.9387618799967, "children": { "TorchPPOOptimizer.update": { "total": 64.32984329200497, "count": 2910, "self": 64.32984329200497 } } } } } } }, "trainer_threads": { "total": 1.0339999789721332e-06, "count": 1, "self": 1.0339999789721332e-06 }, "TrainerController._save_models": { "total": 0.12824292599998444, "count": 1, "self": 0.0023691309997957433, "children": { "RLTrainer._checkpoint": { "total": 0.1258737950001887, "count": 1, "self": 0.1258737950001887 } } } } } } }