{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4056755304336548, "min": 1.4056755304336548, "max": 1.4298067092895508, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68516.84375, "min": 68516.84375, "max": 75597.5234375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 121.28361858190709, "min": 89.0, "max": 421.8655462184874, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49605.0, "min": 48865.0, "max": 50202.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999951.0, "min": 49747.0, "max": 1999951.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999951.0, "min": 49747.0, "max": 1999951.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3972010612487793, "min": 0.034198097884655, "max": 2.412503480911255, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 980.4552612304688, "min": 4.035375595092773, "max": 1326.0322265625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.72951836414034, "min": 1.8274070004285392, "max": 3.9022320450456056, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1525.3730109333992, "min": 215.63402605056763, "max": 2167.2171370983124, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.72951836414034, "min": 1.8274070004285392, "max": 3.9022320450456056, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1525.3730109333992, "min": 215.63402605056763, "max": 2167.2171370983124, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.020497101777679442, "min": 0.013027220501195794, "max": 0.020497101777679442, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.040994203555358884, "min": 0.026054441002391588, "max": 0.05777468646798904, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04334554563586911, "min": 0.02317493309577306, "max": 0.057824516834484196, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.08669109127173821, "min": 0.04634986619154612, "max": 0.1734735505034526, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.405748531449987e-06, "min": 4.405748531449987e-06, "max": 0.00029526457657847496, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.811497062899974e-06, "min": 8.811497062899974e-06, "max": 0.0008439937686687499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10146854999999996, "min": 0.10146854999999996, "max": 0.19842152499999993, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20293709999999993, "min": 0.20293709999999993, "max": 0.5813312500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.328064499999982e-05, "min": 8.328064499999982e-05, "max": 0.0049212340974999986, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00016656128999999965, "min": 0.00016656128999999965, "max": 0.014068429375000004, "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": "1729557529", "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": "1729560006" }, "total": 2476.723205529, "count": 1, "self": 0.43452742199997374, "children": { "run_training.setup": { "total": 0.05357508899999175, "count": 1, "self": 0.05357508899999175 }, "TrainerController.start_learning": { "total": 2476.2351030180002, "count": 1, "self": 4.504778304953561, "children": { "TrainerController._reset_env": { "total": 4.273036767000008, "count": 1, "self": 4.273036767000008 }, "TrainerController.advance": { "total": 2467.3439893540462, "count": 231145, "self": 4.759334315016531, "children": { "env_step": { "total": 1969.1490365490145, "count": 231145, "self": 1550.510840965011, "children": { "SubprocessEnvManager._take_step": { "total": 415.8515582450194, "count": 231145, "self": 15.949002304971486, "children": { "TorchPolicy.evaluate": { "total": 399.90255594004793, "count": 222880, "self": 399.90255594004793 } } }, "workers": { "total": 2.7866373389838373, "count": 231145, "self": 0.0, "children": { "worker_root": { "total": 2468.8261943360135, "count": 231145, "is_parallel": true, "self": 1210.8047910869907, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008571589999064599, "count": 1, "is_parallel": true, "self": 0.00028148199987754197, "children": { "_process_rank_one_or_two_observation": { "total": 0.000575677000028918, "count": 2, "is_parallel": true, "self": 0.000575677000028918 } } }, "UnityEnvironment.step": { "total": 0.03035821700007091, "count": 1, "is_parallel": true, "self": 0.00042210399999476067, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019977199997356365, "count": 1, "is_parallel": true, "self": 0.00019977199997356365 }, "communicator.exchange": { "total": 0.02890101200000572, "count": 1, "is_parallel": true, "self": 0.02890101200000572 }, "steps_from_proto": { "total": 0.0008353290000968627, "count": 1, "is_parallel": true, "self": 0.00023172100020474318, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006036079998921196, "count": 2, "is_parallel": true, "self": 0.0006036079998921196 } } } } } } }, "UnityEnvironment.step": { "total": 1258.0214032490228, "count": 231144, "is_parallel": true, "self": 38.03838082390416, "children": { "UnityEnvironment._generate_step_input": { "total": 83.91775226412051, "count": 231144, "is_parallel": true, "self": 83.91775226412051 }, "communicator.exchange": { "total": 1045.924581263001, "count": 231144, "is_parallel": true, "self": 1045.924581263001 }, "steps_from_proto": { "total": 90.14068889799705, "count": 231144, "is_parallel": true, "self": 34.44988782184373, "children": { "_process_rank_one_or_two_observation": { "total": 55.69080107615332, "count": 462288, "is_parallel": true, "self": 55.69080107615332 } } } } } } } } } } }, "trainer_advance": { "total": 493.43561849001526, "count": 231145, "self": 6.628024622992598, "children": { "process_trajectory": { "total": 158.7054522210217, "count": 231145, "self": 157.28535698602195, "children": { "RLTrainer._checkpoint": { "total": 1.4200952349997351, "count": 10, "self": 1.4200952349997351 } } }, "_update_policy": { "total": 328.102141646001, "count": 96, "self": 264.24220569302076, "children": { "TorchPPOOptimizer.update": { "total": 63.85993595298021, "count": 2880, "self": 63.85993595298021 } } } } } } }, "trainer_threads": { "total": 1.1209999684069771e-06, "count": 1, "self": 1.1209999684069771e-06 }, "TrainerController._save_models": { "total": 0.11329747100035092, "count": 1, "self": 0.0017993520000345598, "children": { "RLTrainer._checkpoint": { "total": 0.11149811900031636, "count": 1, "self": 0.11149811900031636 } } } } } } }