{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4059127569198608, "min": 1.4059127569198608, "max": 1.4265698194503784, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71208.078125, "min": 69291.375, "max": 77628.0234375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 83.08789386401327, "min": 80.70424836601308, "max": 418.14166666666665, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 50102.0, "min": 48746.0, "max": 50177.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999980.0, "min": 49996.0, "max": 1999980.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999980.0, "min": 49996.0, "max": 1999980.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4206883907318115, "min": 0.19703511893749237, "max": 2.465147018432617, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1459.675048828125, "min": 23.447179794311523, "max": 1504.367431640625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7410275871876264, "min": 1.7669623769631906, "max": 3.954944784900799, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2255.8396350741386, "min": 210.2685228586197, "max": 2339.7205330729485, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7410275871876264, "min": 1.7669623769631906, "max": 3.954944784900799, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2255.8396350741386, "min": 210.2685228586197, "max": 2339.7205330729485, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017349197867992595, "min": 0.014020363801682834, "max": 0.021458208475572366, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05204759360397778, "min": 0.028040727603365668, "max": 0.06048764553415822, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.057220331662231026, "min": 0.02146807440246145, "max": 0.06889855327705544, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17166099498669307, "min": 0.0429361488049229, "max": 0.19367487753431, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.7859987380333427e-06, "min": 3.7859987380333427e-06, "max": 0.00029537070154309997, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1357996214100028e-05, "min": 1.1357996214100028e-05, "max": 0.0008444064185312001, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10126196666666666, "min": 0.10126196666666666, "max": 0.1984569, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3037859, "min": 0.20765305000000006, "max": 0.5814688, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.297213666666684e-05, "min": 7.297213666666684e-05, "max": 0.00492299931, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021891641000000052, "min": 0.00021891641000000052, "max": 0.014075293120000002, "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": "1718627647", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718629971" }, "total": 2323.916052843, "count": 1, "self": 0.4420061640003041, "children": { "run_training.setup": { "total": 0.05517907800003741, "count": 1, "self": 0.05517907800003741 }, "TrainerController.start_learning": { "total": 2323.418867601, "count": 1, "self": 4.276852102005705, "children": { "TrainerController._reset_env": { "total": 3.192371488000049, "count": 1, "self": 3.192371488000049 }, "TrainerController.advance": { "total": 2315.8386164909944, "count": 232494, "self": 4.534188375933354, "children": { "env_step": { "total": 1829.5800792740388, "count": 232494, "self": 1509.199628304835, "children": { "SubprocessEnvManager._take_step": { "total": 317.56383276110046, "count": 232494, "self": 16.10188001116171, "children": { "TorchPolicy.evaluate": { "total": 301.46195274993875, "count": 222940, "self": 301.46195274993875 } } }, "workers": { "total": 2.816618208103364, "count": 232494, "self": 0.0, "children": { "worker_root": { "total": 2316.644089353994, "count": 232494, "is_parallel": true, "self": 1103.273342411941, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009723309999571939, "count": 1, "is_parallel": true, "self": 0.0002983929999800239, "children": { "_process_rank_one_or_two_observation": { "total": 0.00067393799997717, "count": 2, "is_parallel": true, "self": 0.00067393799997717 } } }, "UnityEnvironment.step": { "total": 0.02868501600005402, "count": 1, "is_parallel": true, "self": 0.0003971000001001812, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002129350000359409, "count": 1, "is_parallel": true, "self": 0.0002129350000359409 }, "communicator.exchange": { "total": 0.027313201999959347, "count": 1, "is_parallel": true, "self": 0.027313201999959347 }, "steps_from_proto": { "total": 0.0007617789999585511, "count": 1, "is_parallel": true, "self": 0.00021047799987172766, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005513010000868235, "count": 2, "is_parallel": true, "self": 0.0005513010000868235 } } } } } } }, "UnityEnvironment.step": { "total": 1213.3707469420528, "count": 232493, "is_parallel": true, "self": 38.452023927118034, "children": { "UnityEnvironment._generate_step_input": { "total": 78.51457622994451, "count": 232493, "is_parallel": true, "self": 78.51457622994451 }, "communicator.exchange": { "total": 1009.0096239120028, "count": 232493, "is_parallel": true, "self": 1009.0096239120028 }, "steps_from_proto": { "total": 87.39452287298741, "count": 232493, "is_parallel": true, "self": 30.97238426584761, "children": { "_process_rank_one_or_two_observation": { "total": 56.4221386071398, "count": 464986, "is_parallel": true, "self": 56.4221386071398 } } } } } } } } } } }, "trainer_advance": { "total": 481.72434884102233, "count": 232494, "self": 6.5836712729806095, "children": { "process_trajectory": { "total": 150.53974167404158, "count": 232494, "self": 149.27302203204135, "children": { "RLTrainer._checkpoint": { "total": 1.2667196420002256, "count": 10, "self": 1.2667196420002256 } } }, "_update_policy": { "total": 324.60093589400014, "count": 97, "self": 261.49979013500695, "children": { "TorchPPOOptimizer.update": { "total": 63.1011457589932, "count": 2910, "self": 63.1011457589932 } } } } } } }, "trainer_threads": { "total": 1.0279995876771864e-06, "count": 1, "self": 1.0279995876771864e-06 }, "TrainerController._save_models": { "total": 0.11102649200029191, "count": 1, "self": 0.0020135670006311557, "children": { "RLTrainer._checkpoint": { "total": 0.10901292499966075, "count": 1, "self": 0.10901292499966075 } } } } } } }