{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.405710220336914, "min": 1.405710220336914, "max": 1.4263275861740112, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69966.4140625, "min": 68330.421875, "max": 75426.0859375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 107.18736383442265, "min": 85.67764298093587, "max": 424.16101694915255, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49199.0, "min": 48882.0, "max": 50051.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999933.0, "min": 49808.0, "max": 1999933.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999933.0, "min": 49808.0, "max": 1999933.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.367574691772461, "min": 0.16920553147792816, "max": 2.4795570373535156, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1086.716796875, "min": 19.797046661376953, "max": 1411.1474609375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5041888471782077, "min": 2.0079374512036643, "max": 3.9464882178357126, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1608.4226808547974, "min": 234.9286817908287, "max": 2261.588827729225, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5041888471782077, "min": 2.0079374512036643, "max": 3.9464882178357126, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1608.4226808547974, "min": 234.9286817908287, "max": 2261.588827729225, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016173494507650807, "min": 0.014006655630914288, "max": 0.01952426765023524, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04852048352295242, "min": 0.02835403488716111, "max": 0.058572802950705716, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.047835040175252495, "min": 0.022441325864444174, "max": 0.06231017721196015, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14350512052575748, "min": 0.04488265172888835, "max": 0.18176486181716123, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.180798939766669e-06, "min": 3.180798939766669e-06, "max": 0.00029532202655932493, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.542396819300007e-06, "min": 9.542396819300007e-06, "max": 0.0008440644186451998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10106023333333335, "min": 0.10106023333333335, "max": 0.19844067500000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3031807, "min": 0.20736899999999997, "max": 0.5813548000000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.29056433333334e-05, "min": 6.29056433333334e-05, "max": 0.004922189682499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001887169300000002, "min": 0.0001887169300000002, "max": 0.01406960452, "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": "1673210237", "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": "1673212729" }, "total": 2491.95964455, "count": 1, "self": 0.39238108300014574, "children": { "run_training.setup": { "total": 0.130513034000046, "count": 1, "self": 0.130513034000046 }, "TrainerController.start_learning": { "total": 2491.436750433, "count": 1, "self": 4.364100948987925, "children": { "TrainerController._reset_env": { "total": 8.115697790000013, "count": 1, "self": 8.115697790000013 }, "TrainerController.advance": { "total": 2478.8290878030116, "count": 231891, "self": 4.58859900414609, "children": { "env_step": { "total": 1963.8838011999296, "count": 231891, "self": 1652.0529995459365, "children": { "SubprocessEnvManager._take_step": { "total": 308.9170775301185, "count": 231891, "self": 15.775765976265916, "children": { "TorchPolicy.evaluate": { "total": 293.1413115538526, "count": 223014, "self": 72.7815757858408, "children": { "TorchPolicy.sample_actions": { "total": 220.35973576801177, "count": 223014, "self": 220.35973576801177 } } } } }, "workers": { "total": 2.9137241238746583, "count": 231891, "self": 0.0, "children": { "worker_root": { "total": 2482.779344342949, "count": 231891, "is_parallel": true, "self": 1122.6038354740158, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021262930000602864, "count": 1, "is_parallel": true, "self": 0.0003792629998997654, "children": { "_process_rank_one_or_two_observation": { "total": 0.001747030000160521, "count": 2, "is_parallel": true, "self": 0.001747030000160521 } } }, "UnityEnvironment.step": { "total": 0.03093041700003596, "count": 1, "is_parallel": true, "self": 0.000323539000078199, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020755999992161378, "count": 1, "is_parallel": true, "self": 0.00020755999992161378 }, "communicator.exchange": { "total": 0.029629567000029056, "count": 1, "is_parallel": true, "self": 0.029629567000029056 }, "steps_from_proto": { "total": 0.0007697510000070906, "count": 1, "is_parallel": true, "self": 0.00025738299996191927, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005123680000451714, "count": 2, "is_parallel": true, "self": 0.0005123680000451714 } } } } } } }, "UnityEnvironment.step": { "total": 1360.1755088689333, "count": 231890, "is_parallel": true, "self": 37.54601666491635, "children": { "UnityEnvironment._generate_step_input": { "total": 89.19720956403364, "count": 231890, "is_parallel": true, "self": 89.19720956403364 }, "communicator.exchange": { "total": 1129.4379577269895, "count": 231890, "is_parallel": true, "self": 1129.4379577269895 }, "steps_from_proto": { "total": 103.99432491299387, "count": 231890, "is_parallel": true, "self": 45.44910446217705, "children": { "_process_rank_one_or_two_observation": { "total": 58.54522045081683, "count": 463780, "is_parallel": true, "self": 58.54522045081683 } } } } } } } } } } }, "trainer_advance": { "total": 510.35668759893576, "count": 231891, "self": 6.799810051886425, "children": { "process_trajectory": { "total": 165.40853974704999, "count": 231891, "self": 164.14229242905026, "children": { "RLTrainer._checkpoint": { "total": 1.2662473179997278, "count": 10, "self": 1.2662473179997278 } } }, "_update_policy": { "total": 338.14833779999935, "count": 97, "self": 283.2754373900018, "children": { "TorchPPOOptimizer.update": { "total": 54.872900409997555, "count": 2910, "self": 54.872900409997555 } } } } } } }, "trainer_threads": { "total": 9.180002962239087e-07, "count": 1, "self": 9.180002962239087e-07 }, "TrainerController._save_models": { "total": 0.12786297299999205, "count": 1, "self": 0.0022603980000894808, "children": { "RLTrainer._checkpoint": { "total": 0.12560257499990257, "count": 1, "self": 0.12560257499990257 } } } } } } }