{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4082659482955933, "min": 1.4082659482955933, "max": 1.4286198616027832, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68790.9765625, "min": 68046.1484375, "max": 78018.671875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 104.34033613445378, "min": 79.82552504038772, "max": 411.0409836065574, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49666.0, "min": 48733.0, "max": 50147.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999442.0, "min": 49519.0, "max": 1999442.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999442.0, "min": 49519.0, "max": 1999442.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4404830932617188, "min": -0.07957151532173157, "max": 2.488839864730835, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1161.669921875, "min": -9.628153800964355, "max": 1490.2061767578125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.761812964782995, "min": 1.713225462343082, "max": 3.98396397028363, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1790.6229712367058, "min": 207.30028094351292, "max": 2382.199718415737, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.761812964782995, "min": 1.713225462343082, "max": 3.98396397028363, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1790.6229712367058, "min": 207.30028094351292, "max": 2382.199718415737, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015988687483089355, "min": 0.012179698971400891, "max": 0.01997013816661719, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.047966062449268064, "min": 0.024359397942801782, "max": 0.05991041449985157, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04921055059466097, "min": 0.022554339623699585, "max": 0.062001516669988634, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1476316517839829, "min": 0.04510867924739917, "max": 0.1823618557304144, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4498488500833395e-06, "min": 3.4498488500833395e-06, "max": 0.00029536530154489996, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0349546550250018e-05, "min": 1.0349546550250018e-05, "max": 0.00084426856857715, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10114991666666667, "min": 0.10114991666666667, "max": 0.1984551, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30344975, "min": 0.20749280000000006, "max": 0.58142285, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.738084166666679e-05, "min": 6.738084166666679e-05, "max": 0.00492290949, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020214252500000039, "min": 0.00020214252500000039, "max": 0.014073000215000001, "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": "1696630660", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.21.2", "end_time_seconds": "1696633284" }, "total": 2623.8919580330003, "count": 1, "self": 0.9357613470006072, "children": { "run_training.setup": { "total": 0.08676078500002404, "count": 1, "self": 0.08676078500002404 }, "TrainerController.start_learning": { "total": 2622.8694359009996, "count": 1, "self": 4.934856435017991, "children": { "TrainerController._reset_env": { "total": 8.022407643999998, "count": 1, "self": 8.022407643999998 }, "TrainerController.advance": { "total": 2609.726708569982, "count": 232185, "self": 4.983412869010408, "children": { "env_step": { "total": 1991.945817038982, "count": 232185, "self": 1644.6028970218845, "children": { "SubprocessEnvManager._take_step": { "total": 344.2406456560653, "count": 232185, "self": 18.012264579082967, "children": { "TorchPolicy.evaluate": { "total": 326.2283810769823, "count": 222970, "self": 326.2283810769823 } } }, "workers": { "total": 3.1022743610323005, "count": 232185, "self": 0.0, "children": { "worker_root": { "total": 2615.082253548951, "count": 232185, "is_parallel": true, "self": 1280.6472498139688, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0007758549999721254, "count": 1, "is_parallel": true, "self": 0.0002270839999596319, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005487710000124935, "count": 2, "is_parallel": true, "self": 0.0005487710000124935 } } }, "UnityEnvironment.step": { "total": 0.04501029299996162, "count": 1, "is_parallel": true, "self": 0.0002873959999192266, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022462000003997673, "count": 1, "is_parallel": true, "self": 0.00022462000003997673 }, "communicator.exchange": { "total": 0.0437748479999982, "count": 1, "is_parallel": true, "self": 0.0437748479999982 }, "steps_from_proto": { "total": 0.0007234290000042165, "count": 1, "is_parallel": true, "self": 0.00020007799997756592, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005233510000266506, "count": 2, "is_parallel": true, "self": 0.0005233510000266506 } } } } } } }, "UnityEnvironment.step": { "total": 1334.4350037349823, "count": 232184, "is_parallel": true, "self": 41.77302129006716, "children": { "UnityEnvironment._generate_step_input": { "total": 85.54666952894655, "count": 232184, "is_parallel": true, "self": 85.54666952894655 }, "communicator.exchange": { "total": 1103.7879635400059, "count": 232184, "is_parallel": true, "self": 1103.7879635400059 }, "steps_from_proto": { "total": 103.32734937596268, "count": 232184, "is_parallel": true, "self": 37.300535805920106, "children": { "_process_rank_one_or_two_observation": { "total": 66.02681357004258, "count": 464368, "is_parallel": true, "self": 66.02681357004258 } } } } } } } } } } }, "trainer_advance": { "total": 612.7974786619892, "count": 232185, "self": 7.182525530887347, "children": { "process_trajectory": { "total": 158.72473594910298, "count": 232185, "self": 157.435204829103, "children": { "RLTrainer._checkpoint": { "total": 1.2895311199999924, "count": 10, "self": 1.2895311199999924 } } }, "_update_policy": { "total": 446.89021718199893, "count": 97, "self": 381.7328099260105, "children": { "TorchPPOOptimizer.update": { "total": 65.15740725598846, "count": 2910, "self": 65.15740725598846 } } } } } } }, "trainer_threads": { "total": 1.475999852118548e-06, "count": 1, "self": 1.475999852118548e-06 }, "TrainerController._save_models": { "total": 0.185461776000011, "count": 1, "self": 0.003744202999769186, "children": { "RLTrainer._checkpoint": { "total": 0.18171757300024183, "count": 1, "self": 0.18171757300024183 } } } } } } }