{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4017291069030762, "min": 1.4017291069030762, "max": 1.4279954433441162, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70480.34375, "min": 68621.796875, "max": 79297.203125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 90.86422018348624, "min": 76.87227414330218, "max": 424.07563025210084, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49521.0, "min": 48838.0, "max": 50465.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999980.0, "min": 49882.0, "max": 1999980.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999980.0, "min": 49882.0, "max": 1999980.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.384267568588257, "min": 0.1394490748643875, "max": 2.51043963432312, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1299.42578125, "min": 16.45499038696289, "max": 1549.7298583984375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.693581321370711, "min": 1.7648601640584105, "max": 4.020862778299091, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2013.0018201470375, "min": 208.25349935889244, "max": 2511.7404150366783, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.693581321370711, "min": 1.7648601640584105, "max": 4.020862778299091, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2013.0018201470375, "min": 208.25349935889244, "max": 2511.7404150366783, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017305854346422067, "min": 0.01200464268986252, "max": 0.020445871089274682, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0519175630392662, "min": 0.02400928537972504, "max": 0.05982724530428338, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04971095170411799, "min": 0.020960237737745045, "max": 0.058459342022736865, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14913285511235397, "min": 0.04192047547549009, "max": 0.1719858255237341, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.7166987611333255e-06, "min": 3.7166987611333255e-06, "max": 0.0002953323015559, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1150096283399976e-05, "min": 1.1150096283399976e-05, "max": 0.0008441851686049499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10123886666666666, "min": 0.10123886666666666, "max": 0.1984441, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3037166, "min": 0.20763674999999998, "max": 0.5813950499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.181944666666654e-05, "min": 7.181944666666654e-05, "max": 0.004922360590000002, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002154583399999996, "min": 0.0002154583399999996, "max": 0.014071612995000003, "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": "1732841655", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1732844105" }, "total": 2450.532879736, "count": 1, "self": 0.425428990999535, "children": { "run_training.setup": { "total": 0.06520918999990499, "count": 1, "self": 0.06520918999990499 }, "TrainerController.start_learning": { "total": 2450.042241555, "count": 1, "self": 4.435105071075668, "children": { "TrainerController._reset_env": { "total": 5.874804714999982, "count": 1, "self": 5.874804714999982 }, "TrainerController.advance": { "total": 2439.619846098925, "count": 233023, "self": 4.399567758111061, "children": { "env_step": { "total": 1931.1304258448854, "count": 233023, "self": 1519.827187854797, "children": { "SubprocessEnvManager._take_step": { "total": 408.54584604399406, "count": 233023, "self": 16.138722769032256, "children": { "TorchPolicy.evaluate": { "total": 392.4071232749618, "count": 223047, "self": 392.4071232749618 } } }, "workers": { "total": 2.7573919460942307, "count": 233023, "self": 0.0, "children": { "worker_root": { "total": 2442.945824437035, "count": 233023, "is_parallel": true, "self": 1207.5819176900159, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001040595999938887, "count": 1, "is_parallel": true, "self": 0.00036509899996417516, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006754969999747118, "count": 2, "is_parallel": true, "self": 0.0006754969999747118 } } }, "UnityEnvironment.step": { "total": 0.029327486000056524, "count": 1, "is_parallel": true, "self": 0.00037977599981786625, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021315000003596651, "count": 1, "is_parallel": true, "self": 0.00021315000003596651 }, "communicator.exchange": { "total": 0.027996097000141162, "count": 1, "is_parallel": true, "self": 0.027996097000141162 }, "steps_from_proto": { "total": 0.0007384630000615289, "count": 1, "is_parallel": true, "self": 0.0002025850001245999, "children": { "_process_rank_one_or_two_observation": { "total": 0.000535877999936929, "count": 2, "is_parallel": true, "self": 0.000535877999936929 } } } } } } }, "UnityEnvironment.step": { "total": 1235.363906747019, "count": 233022, "is_parallel": true, "self": 36.70073567186387, "children": { "UnityEnvironment._generate_step_input": { "total": 82.5013313890031, "count": 233022, "is_parallel": true, "self": 82.5013313890031 }, "communicator.exchange": { "total": 1027.0980464490647, "count": 233022, "is_parallel": true, "self": 1027.0980464490647 }, "steps_from_proto": { "total": 89.06379323708734, "count": 233022, "is_parallel": true, "self": 33.20201881400385, "children": { "_process_rank_one_or_two_observation": { "total": 55.86177442308349, "count": 466044, "is_parallel": true, "self": 55.86177442308349 } } } } } } } } } } }, "trainer_advance": { "total": 504.08985249592865, "count": 233023, "self": 6.179979476959716, "children": { "process_trajectory": { "total": 169.80151184896772, "count": 233023, "self": 168.43772958996715, "children": { "RLTrainer._checkpoint": { "total": 1.3637822590005726, "count": 10, "self": 1.3637822590005726 } } }, "_update_policy": { "total": 328.1083611700012, "count": 97, "self": 262.6838246069847, "children": { "TorchPPOOptimizer.update": { "total": 65.42453656301655, "count": 2910, "self": 65.42453656301655 } } } } } } }, "trainer_threads": { "total": 1.5069999790284783e-06, "count": 1, "self": 1.5069999790284783e-06 }, "TrainerController._save_models": { "total": 0.11248416299986275, "count": 1, "self": 0.0022318709998216946, "children": { "RLTrainer._checkpoint": { "total": 0.11025229200004105, "count": 1, "self": 0.11025229200004105 } } } } } } }