{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4007923603057861, "min": 1.4007923603057861, "max": 1.4268736839294434, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68948.3984375, "min": 68355.7265625, "max": 76920.6015625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 80.39087947882736, "min": 78.16640253565768, "max": 391.515625, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49360.0, "min": 48844.0, "max": 50114.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999958.0, "min": 49845.0, "max": 1999958.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999958.0, "min": 49845.0, "max": 1999958.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.394939661026001, "min": 0.00452062813565135, "max": 2.4571375846862793, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1470.492919921875, "min": 0.5741197466850281, "max": 1532.2919921875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6738363549064736, "min": 1.8986369155523346, "max": 3.9346096283350236, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2255.7355219125748, "min": 241.12688827514648, "max": 2390.5631998181343, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6738363549064736, "min": 1.8986369155523346, "max": 3.9346096283350236, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2255.7355219125748, "min": 241.12688827514648, "max": 2390.5631998181343, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.014083502792426669, "min": 0.014083502792426669, "max": 0.020321885131609936, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.042250508377280005, "min": 0.029693088269171615, "max": 0.055273245718368946, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.059423663839697834, "min": 0.022659232933074237, "max": 0.06161989147464435, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1782709915190935, "min": 0.045318465866148475, "max": 0.1782709915190935, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4801488399833343e-06, "min": 3.4801488399833343e-06, "max": 0.00029524035158654997, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0440446519950002e-05, "min": 1.0440446519950002e-05, "max": 0.0008436064687978498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10116001666666669, "min": 0.10116001666666669, "max": 0.1984134500000001, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30348005000000006, "min": 0.2074488, "max": 0.58120215, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.788483166666669e-05, "min": 6.788483166666669e-05, "max": 0.0049208311549999995, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020365449500000005, "min": 0.00020365449500000005, "max": 0.014061987285, "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": "1671073546", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1671075878" }, "total": 2332.1954697, "count": 1, "self": 0.3900981619999584, "children": { "run_training.setup": { "total": 0.10867736499994862, "count": 1, "self": 0.10867736499994862 }, "TrainerController.start_learning": { "total": 2331.696694173, "count": 1, "self": 4.025367542953973, "children": { "TrainerController._reset_env": { "total": 9.200852647000033, "count": 1, "self": 9.200852647000033 }, "TrainerController.advance": { "total": 2318.350162554046, "count": 232707, "self": 4.267579872028364, "children": { "env_step": { "total": 1835.343304222988, "count": 232707, "self": 1539.1861108720154, "children": { "SubprocessEnvManager._take_step": { "total": 293.4514078939701, "count": 232707, "self": 15.044724277893579, "children": { "TorchPolicy.evaluate": { "total": 278.4066836160765, "count": 222901, "self": 68.47432931601952, "children": { "TorchPolicy.sample_actions": { "total": 209.932354300057, "count": 222901, "self": 209.932354300057 } } } } }, "workers": { "total": 2.7057854570024347, "count": 232707, "self": 0.0, "children": { "worker_root": { "total": 2323.717643377024, "count": 232707, "is_parallel": true, "self": 1058.689054605071, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018297139999958745, "count": 1, "is_parallel": true, "self": 0.00032910800007357466, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015006059999222998, "count": 2, "is_parallel": true, "self": 0.0015006059999222998 } } }, "UnityEnvironment.step": { "total": 0.0286146750000853, "count": 1, "is_parallel": true, "self": 0.0002581600000439721, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002035869999872375, "count": 1, "is_parallel": true, "self": 0.0002035869999872375 }, "communicator.exchange": { "total": 0.02734713200004535, "count": 1, "is_parallel": true, "self": 0.02734713200004535 }, "steps_from_proto": { "total": 0.0008057960000087405, "count": 1, "is_parallel": true, "self": 0.00030924500003948197, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004965509999692586, "count": 2, "is_parallel": true, "self": 0.0004965509999692586 } } } } } } }, "UnityEnvironment.step": { "total": 1265.028588771953, "count": 232706, "is_parallel": true, "self": 35.45462302300166, "children": { "UnityEnvironment._generate_step_input": { "total": 82.87760505698361, "count": 232706, "is_parallel": true, "self": 82.87760505698361 }, "communicator.exchange": { "total": 1049.3597882579436, "count": 232706, "is_parallel": true, "self": 1049.3597882579436 }, "steps_from_proto": { "total": 97.33657243402422, "count": 232706, "is_parallel": true, "self": 42.5675959019469, "children": { "_process_rank_one_or_two_observation": { "total": 54.76897653207732, "count": 465412, "is_parallel": true, "self": 54.76897653207732 } } } } } } } } } } }, "trainer_advance": { "total": 478.7392784590296, "count": 232707, "self": 6.085267702987153, "children": { "process_trajectory": { "total": 158.4219921390427, "count": 232707, "self": 157.93367619804235, "children": { "RLTrainer._checkpoint": { "total": 0.48831594100033726, "count": 4, "self": 0.48831594100033726 } } }, "_update_policy": { "total": 314.23201861699977, "count": 97, "self": 260.9788152019844, "children": { "TorchPPOOptimizer.update": { "total": 53.25320341501538, "count": 2910, "self": 53.25320341501538 } } } } } } }, "trainer_threads": { "total": 9.4600000011269e-07, "count": 1, "self": 9.4600000011269e-07 }, "TrainerController._save_models": { "total": 0.12031048300013936, "count": 1, "self": 0.0019651229999908537, "children": { "RLTrainer._checkpoint": { "total": 0.1183453600001485, "count": 1, "self": 0.1183453600001485 } } } } } } }