{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4033211469650269, "min": 1.4033211469650269, "max": 1.4260895252227783, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69587.890625, "min": 68304.828125, "max": 76335.875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 78.68203497615262, "min": 76.72670807453416, "max": 395.375, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49491.0, "min": 48977.0, "max": 50608.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999973.0, "min": 49987.0, "max": 1999973.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999973.0, "min": 49987.0, "max": 1999973.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4854953289031982, "min": 0.09897430986166, "max": 2.4955966472625732, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1560.89111328125, "min": 12.569737434387207, "max": 1607.164306640625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.9615127383523685, "min": 1.7774303475702842, "max": 3.9615127383523685, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2487.8299996852875, "min": 225.7336541414261, "max": 2501.2240886688232, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.9615127383523685, "min": 1.7774303475702842, "max": 3.9615127383523685, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2487.8299996852875, "min": 225.7336541414261, "max": 2501.2240886688232, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015697793266735968, "min": 0.014368707828240682, "max": 0.02205368612485472, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.047093379800207905, "min": 0.028737415656481365, "max": 0.05815946893611301, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05203511777023475, "min": 0.02214452183494965, "max": 0.059683067186011206, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15610535331070424, "min": 0.0442890436698993, "max": 0.1790492015580336, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.5229988257000065e-06, "min": 3.5229988257000065e-06, "max": 0.0002953500765499749, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0568996477100019e-05, "min": 1.0568996477100019e-05, "max": 0.00084413836862055, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10117430000000001, "min": 0.10117430000000001, "max": 0.19845002500000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30352290000000004, "min": 0.20747694999999997, "max": 0.58137945, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.85975700000001e-05, "min": 6.85975700000001e-05, "max": 0.004922656247499998, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002057927100000003, "min": 0.0002057927100000003, "max": 0.014070834555000002, "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": "1705789399", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ml-agents/config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1705792042" }, "total": 2642.3328215590004, "count": 1, "self": 0.4967438650000986, "children": { "run_training.setup": { "total": 0.05645684199998868, "count": 1, "self": 0.05645684199998868 }, "TrainerController.start_learning": { "total": 2641.7796208520003, "count": 1, "self": 5.115104574078032, "children": { "TrainerController._reset_env": { "total": 3.458775797000044, "count": 1, "self": 3.458775797000044 }, "TrainerController.advance": { "total": 2633.0824843649216, "count": 232688, "self": 5.289147296750343, "children": { "env_step": { "total": 2087.4389536721683, "count": 232688, "self": 1741.5476866438355, "children": { "SubprocessEnvManager._take_step": { "total": 342.6891106861617, "count": 232688, "self": 18.204394166118618, "children": { "TorchPolicy.evaluate": { "total": 324.4847165200431, "count": 222891, "self": 324.4847165200431 } } }, "workers": { "total": 3.2021563421710653, "count": 232688, "self": 0.0, "children": { "worker_root": { "total": 2633.9968415680096, "count": 232688, "is_parallel": true, "self": 1213.9723888672427, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0006986739999774727, "count": 1, "is_parallel": true, "self": 0.00019582499976422696, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005028490002132457, "count": 2, "is_parallel": true, "self": 0.0005028490002132457 } } }, "UnityEnvironment.step": { "total": 0.030087356999956683, "count": 1, "is_parallel": true, "self": 0.00036709000028167793, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019478199988043343, "count": 1, "is_parallel": true, "self": 0.00019478199988043343 }, "communicator.exchange": { "total": 0.028754818999914278, "count": 1, "is_parallel": true, "self": 0.028754818999914278 }, "steps_from_proto": { "total": 0.0007706659998802934, "count": 1, "is_parallel": true, "self": 0.00019792399984908116, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005727420000312122, "count": 2, "is_parallel": true, "self": 0.0005727420000312122 } } } } } } }, "UnityEnvironment.step": { "total": 1420.024452700767, "count": 232687, "is_parallel": true, "self": 43.570789307038694, "children": { "UnityEnvironment._generate_step_input": { "total": 86.7793957308611, "count": 232687, "is_parallel": true, "self": 86.7793957308611 }, "communicator.exchange": { "total": 1191.2882936089195, "count": 232687, "is_parallel": true, "self": 1191.2882936089195 }, "steps_from_proto": { "total": 98.38597405394762, "count": 232687, "is_parallel": true, "self": 34.909734926912506, "children": { "_process_rank_one_or_two_observation": { "total": 63.476239127035115, "count": 465374, "is_parallel": true, "self": 63.476239127035115 } } } } } } } } } } }, "trainer_advance": { "total": 540.3543833960027, "count": 232688, "self": 7.600867555075183, "children": { "process_trajectory": { "total": 165.48935803492645, "count": 232688, "self": 164.13738695392726, "children": { "RLTrainer._checkpoint": { "total": 1.351971080999192, "count": 10, "self": 1.351971080999192 } } }, "_update_policy": { "total": 367.2641578060011, "count": 97, "self": 300.90669256200067, "children": { "TorchPPOOptimizer.update": { "total": 66.35746524400042, "count": 2910, "self": 66.35746524400042 } } } } } } }, "trainer_threads": { "total": 1.0350004231440835e-06, "count": 1, "self": 1.0350004231440835e-06 }, "TrainerController._save_models": { "total": 0.1232550810000248, "count": 1, "self": 0.00295050699969579, "children": { "RLTrainer._checkpoint": { "total": 0.12030457400032901, "count": 1, "self": 0.12030457400032901 } } } } } } }