{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4050655364990234, "min": 1.4050655364990234, "max": 1.4275835752487183, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71658.34375, "min": 68164.296875, "max": 76319.6875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 109.08388520971303, "min": 109.08388520971303, "max": 409.5655737704918, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49415.0, "min": 48896.0, "max": 50216.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999951.0, "min": 49756.0, "max": 1999951.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999951.0, "min": 49756.0, "max": 1999951.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3036346435546875, "min": 0.04339339956641197, "max": 2.354236125946045, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1043.5465087890625, "min": 5.250601291656494, "max": 1043.5465087890625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5170360511501895, "min": 1.825417925134178, "max": 3.7441841437575523, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1593.2173311710358, "min": 220.87556894123554, "max": 1597.9442261457443, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5170360511501895, "min": 1.825417925134178, "max": 3.7441841437575523, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1593.2173311710358, "min": 220.87556894123554, "max": 1597.9442261457443, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01848723339838519, "min": 0.012645991696687514, "max": 0.020057105260073312, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03697446679677038, "min": 0.02714947332521357, "max": 0.06017131578021994, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05151868686079979, "min": 0.02264400615046422, "max": 0.052607195576032, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.10303737372159957, "min": 0.04528801230092844, "max": 0.15467828040321668, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.2971485676499966e-06, "min": 4.2971485676499966e-06, "max": 0.00029538082653972494, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.594297135299993e-06, "min": 8.594297135299993e-06, "max": 0.0008442487685837501, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10143234999999998, "min": 0.10143234999999998, "max": 0.198460275, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20286469999999995, "min": 0.20286469999999995, "max": 0.5814162500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.147426499999997e-05, "min": 8.147426499999997e-05, "max": 0.0049231677225, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00016294852999999994, "min": 0.00016294852999999994, "max": 0.014072670874999998, "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": "1724098118", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1724100599" }, "total": 2481.052506058, "count": 1, "self": 0.43948966600009953, "children": { "run_training.setup": { "total": 0.057794674999968265, "count": 1, "self": 0.057794674999968265 }, "TrainerController.start_learning": { "total": 2480.5552217169998, "count": 1, "self": 4.417476474943669, "children": { "TrainerController._reset_env": { "total": 2.8751400510000167, "count": 1, "self": 2.8751400510000167 }, "TrainerController.advance": { "total": 2473.142328398056, "count": 230546, "self": 4.894269309115771, "children": { "env_step": { "total": 1975.391582021968, "count": 230546, "self": 1630.4084170330998, "children": { "SubprocessEnvManager._take_step": { "total": 341.9934028869543, "count": 230546, "self": 17.5706716998136, "children": { "TorchPolicy.evaluate": { "total": 324.4227311871407, "count": 223014, "self": 324.4227311871407 } } }, "workers": { "total": 2.9897621019138114, "count": 230546, "self": 0.0, "children": { "worker_root": { "total": 2473.1753941359534, "count": 230546, "is_parallel": true, "self": 1158.9358357510237, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000983000000019274, "count": 1, "is_parallel": true, "self": 0.0002655480000157695, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007174520000035045, "count": 2, "is_parallel": true, "self": 0.0007174520000035045 } } }, "UnityEnvironment.step": { "total": 0.03092436600002202, "count": 1, "is_parallel": true, "self": 0.00035524099996564473, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022749900006147072, "count": 1, "is_parallel": true, "self": 0.00022749900006147072 }, "communicator.exchange": { "total": 0.029570927999998275, "count": 1, "is_parallel": true, "self": 0.029570927999998275 }, "steps_from_proto": { "total": 0.0007706979999966279, "count": 1, "is_parallel": true, "self": 0.0001974680000103035, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005732299999863244, "count": 2, "is_parallel": true, "self": 0.0005732299999863244 } } } } } } }, "UnityEnvironment.step": { "total": 1314.2395583849298, "count": 230545, "is_parallel": true, "self": 39.95795090079605, "children": { "UnityEnvironment._generate_step_input": { "total": 84.18346778204852, "count": 230545, "is_parallel": true, "self": 84.18346778204852 }, "communicator.exchange": { "total": 1096.6560545760003, "count": 230545, "is_parallel": true, "self": 1096.6560545760003 }, "steps_from_proto": { "total": 93.44208512608498, "count": 230545, "is_parallel": true, "self": 35.135789820122454, "children": { "_process_rank_one_or_two_observation": { "total": 58.30629530596252, "count": 461090, "is_parallel": true, "self": 58.30629530596252 } } } } } } } } } } }, "trainer_advance": { "total": 492.8564770669724, "count": 230546, "self": 7.402507055020806, "children": { "process_trajectory": { "total": 150.5777372589513, "count": 230546, "self": 149.26713025095148, "children": { "RLTrainer._checkpoint": { "total": 1.3106070079998062, "count": 10, "self": 1.3106070079998062 } } }, "_update_policy": { "total": 334.8762327530003, "count": 96, "self": 270.47969891698483, "children": { "TorchPPOOptimizer.update": { "total": 64.39653383601546, "count": 2880, "self": 64.39653383601546 } } } } } } }, "trainer_threads": { "total": 9.88000010693213e-07, "count": 1, "self": 9.88000010693213e-07 }, "TrainerController._save_models": { "total": 0.12027580499989199, "count": 1, "self": 0.001772232999883272, "children": { "RLTrainer._checkpoint": { "total": 0.11850357200000872, "count": 1, "self": 0.11850357200000872 } } } } } } }