{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4041850566864014, "min": 1.4041850566864014, "max": 1.4263774156570435, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70433.921875, "min": 68262.90625, "max": 78333.0859375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 115.08237986270022, "min": 85.35578583765113, "max": 409.6016260162602, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 50291.0, "min": 48936.0, "max": 50381.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999885.0, "min": 49754.0, "max": 1999885.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999885.0, "min": 49754.0, "max": 1999885.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.356548547744751, "min": -0.1317654848098755, "max": 2.425985336303711, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1027.4552001953125, "min": -16.075389862060547, "max": 1401.306884765625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5911074261599722, "min": 1.6521751582622528, "max": 3.8972521906753754, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1565.722837805748, "min": 201.56536930799484, "max": 2157.6767545342445, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5911074261599722, "min": 1.6521751582622528, "max": 3.8972521906753754, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1565.722837805748, "min": 201.56536930799484, "max": 2157.6767545342445, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017151922674869032, "min": 0.013156727639701177, "max": 0.018993364321795523, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05145576802460709, "min": 0.026313455279402355, "max": 0.05698009296538657, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04726677491433091, "min": 0.026521084581812224, "max": 0.06353914917757114, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14180032474299273, "min": 0.05304216916362445, "max": 0.19023049411674342, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.620248793283333e-06, "min": 3.620248793283333e-06, "max": 0.0002953488015504, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0860746379849999e-05, "min": 1.0860746379849999e-05, "max": 0.0008443321685559497, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10120671666666668, "min": 0.10120671666666668, "max": 0.1984496, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30362015000000003, "min": 0.20760759999999995, "max": 0.5814440499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.021516166666668e-05, "min": 7.021516166666668e-05, "max": 0.00492263504, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021064548500000004, "min": 0.00021064548500000004, "max": 0.014074058095000001, "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": "1697658515", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697660894" }, "total": 2378.920878909, "count": 1, "self": 0.4254350860001068, "children": { "run_training.setup": { "total": 0.04767173400000502, "count": 1, "self": 0.04767173400000502 }, "TrainerController.start_learning": { "total": 2378.447772089, "count": 1, "self": 4.564236611078741, "children": { "TrainerController._reset_env": { "total": 8.574699548000126, "count": 1, "self": 8.574699548000126 }, "TrainerController.advance": { "total": 2365.2048211299207, "count": 232145, "self": 4.616773090023344, "children": { "env_step": { "total": 1865.876793948958, "count": 232145, "self": 1546.0447853369017, "children": { "SubprocessEnvManager._take_step": { "total": 317.02159183802155, "count": 232145, "self": 16.57028305506151, "children": { "TorchPolicy.evaluate": { "total": 300.45130878296004, "count": 222992, "self": 300.45130878296004 } } }, "workers": { "total": 2.8104167740348203, "count": 232145, "self": 0.0, "children": { "worker_root": { "total": 2370.957903649847, "count": 232145, "is_parallel": true, "self": 1112.2474597139512, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008139730000493728, "count": 1, "is_parallel": true, "self": 0.00022846000024401292, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005855129998053599, "count": 2, "is_parallel": true, "self": 0.0005855129998053599 } } }, "UnityEnvironment.step": { "total": 0.029699166999989757, "count": 1, "is_parallel": true, "self": 0.00027426400015428953, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00024157299981197866, "count": 1, "is_parallel": true, "self": 0.00024157299981197866 }, "communicator.exchange": { "total": 0.028487662000088676, "count": 1, "is_parallel": true, "self": 0.028487662000088676 }, "steps_from_proto": { "total": 0.0006956679999348125, "count": 1, "is_parallel": true, "self": 0.00020483599996623525, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004908319999685773, "count": 2, "is_parallel": true, "self": 0.0004908319999685773 } } } } } } }, "UnityEnvironment.step": { "total": 1258.710443935896, "count": 232144, "is_parallel": true, "self": 40.48539313088895, "children": { "UnityEnvironment._generate_step_input": { "total": 83.45028855097917, "count": 232144, "is_parallel": true, "self": 83.45028855097917 }, "communicator.exchange": { "total": 1044.8837435270498, "count": 232144, "is_parallel": true, "self": 1044.8837435270498 }, "steps_from_proto": { "total": 89.89101872697802, "count": 232144, "is_parallel": true, "self": 31.655300202912485, "children": { "_process_rank_one_or_two_observation": { "total": 58.23571852406553, "count": 464288, "is_parallel": true, "self": 58.23571852406553 } } } } } } } } } } }, "trainer_advance": { "total": 494.7112540909395, "count": 232145, "self": 6.532686016939124, "children": { "process_trajectory": { "total": 146.67724356199733, "count": 232145, "self": 145.35350178399767, "children": { "RLTrainer._checkpoint": { "total": 1.3237417779996576, "count": 10, "self": 1.3237417779996576 } } }, "_update_policy": { "total": 341.50132451200307, "count": 97, "self": 280.0482820399891, "children": { "TorchPPOOptimizer.update": { "total": 61.453042472013976, "count": 2910, "self": 61.453042472013976 } } } } } } }, "trainer_threads": { "total": 1.1669999366858974e-06, "count": 1, "self": 1.1669999366858974e-06 }, "TrainerController._save_models": { "total": 0.10401363300024968, "count": 1, "self": 0.0018651979999049217, "children": { "RLTrainer._checkpoint": { "total": 0.10214843500034476, "count": 1, "self": 0.10214843500034476 } } } } } } }