{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.406399130821228, "min": 1.4063981771469116, "max": 1.4304447174072266, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69055.6015625, "min": 68958.5078125, "max": 76321.8671875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 92.42429906542056, "min": 77.13458528951487, "max": 366.3382352941176, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49447.0, "min": 49076.0, "max": 50220.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999944.0, "min": 49836.0, "max": 1999944.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999944.0, "min": 49836.0, "max": 1999944.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.407731294631958, "min": 0.07655195891857147, "max": 2.4783289432525635, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1288.13623046875, "min": 11.1000337600708, "max": 1553.9453125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.779746847174992, "min": 1.8453407063566405, "max": 4.064257586774556, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2022.1645632386208, "min": 267.5744024217129, "max": 2496.527106165886, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.779746847174992, "min": 1.8453407063566405, "max": 4.064257586774556, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2022.1645632386208, "min": 267.5744024217129, "max": 2496.527106165886, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015024761387353971, "min": 0.013726897861003333, "max": 0.02169678861812119, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04507428416206191, "min": 0.027453795722006666, "max": 0.06509036585436358, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05226574966477023, "min": 0.02326111951842904, "max": 0.06229026907434067, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1567972489943107, "min": 0.04652223903685808, "max": 0.1736502488454183, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.835498721533333e-06, "min": 3.835498721533333e-06, "max": 0.0002953425015525, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.15064961646e-05, "min": 1.15064961646e-05, "max": 0.0008443024685658498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10127846666666668, "min": 0.10127846666666668, "max": 0.19844750000000008, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30383540000000003, "min": 0.20768275000000003, "max": 0.5814341500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.379548666666668e-05, "min": 7.379548666666668e-05, "max": 0.0049225302499999995, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022138646000000002, "min": 0.00022138646000000002, "max": 0.014073564085000004, "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": "1726762658", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1726767661" }, "total": 5003.287052381001, "count": 1, "self": 1.0090026010002475, "children": { "run_training.setup": { "total": 0.11413920100005726, "count": 1, "self": 0.11413920100005726 }, "TrainerController.start_learning": { "total": 5002.163910579, "count": 1, "self": 8.729700881978715, "children": { "TrainerController._reset_env": { "total": 4.35992919399996, "count": 1, "self": 4.35992919399996 }, "TrainerController.advance": { "total": 4988.936352369021, "count": 232633, "self": 8.784878164658949, "children": { "env_step": { "total": 3172.0158442031293, "count": 232633, "self": 2647.0147949511293, "children": { "SubprocessEnvManager._take_step": { "total": 519.3098999540337, "count": 232633, "self": 33.99731664505873, "children": { "TorchPolicy.evaluate": { "total": 485.3125833089749, "count": 222906, "self": 485.3125833089749 } } }, "workers": { "total": 5.691149297966604, "count": 232633, "self": 0.0, "children": { "worker_root": { "total": 4987.656985771987, "count": 232633, "is_parallel": true, "self": 2881.353652962102, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0013159569999743326, "count": 1, "is_parallel": true, "self": 0.0003472460000466526, "children": { "_process_rank_one_or_two_observation": { "total": 0.00096871099992768, "count": 2, "is_parallel": true, "self": 0.00096871099992768 } } }, "UnityEnvironment.step": { "total": 0.04341522499998973, "count": 1, "is_parallel": true, "self": 0.0005253919999859136, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023049599997193582, "count": 1, "is_parallel": true, "self": 0.00023049599997193582 }, "communicator.exchange": { "total": 0.04156923100003951, "count": 1, "is_parallel": true, "self": 0.04156923100003951 }, "steps_from_proto": { "total": 0.0010901059999923746, "count": 1, "is_parallel": true, "self": 0.0002834509999729562, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008066550000194184, "count": 2, "is_parallel": true, "self": 0.0008066550000194184 } } } } } } }, "UnityEnvironment.step": { "total": 2106.303332809885, "count": 232632, "is_parallel": true, "self": 66.3073202852654, "children": { "UnityEnvironment._generate_step_input": { "total": 116.14553314201908, "count": 232632, "is_parallel": true, "self": 116.14553314201908 }, "communicator.exchange": { "total": 1780.3862751816955, "count": 232632, "is_parallel": true, "self": 1780.3862751816955 }, "steps_from_proto": { "total": 143.464204200905, "count": 232632, "is_parallel": true, "self": 46.75187388854306, "children": { "_process_rank_one_or_two_observation": { "total": 96.71233031236193, "count": 465264, "is_parallel": true, "self": 96.71233031236193 } } } } } } } } } } }, "trainer_advance": { "total": 1808.1356300012321, "count": 232633, "self": 13.438877998338285, "children": { "process_trajectory": { "total": 270.161843717896, "count": 232633, "self": 268.658173279896, "children": { "RLTrainer._checkpoint": { "total": 1.503670437999972, "count": 10, "self": 1.503670437999972 } } }, "_update_policy": { "total": 1524.534908284998, "count": 97, "self": 360.56407436797485, "children": { "TorchPPOOptimizer.update": { "total": 1163.9708339170231, "count": 2910, "self": 1163.9708339170231 } } } } } } }, "trainer_threads": { "total": 1.1350002750987187e-06, "count": 1, "self": 1.1350002750987187e-06 }, "TrainerController._save_models": { "total": 0.13792699900022853, "count": 1, "self": 0.0045016450003458885, "children": { "RLTrainer._checkpoint": { "total": 0.13342535399988265, "count": 1, "self": 0.13342535399988265 } } } } } } }