{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0013301372528076, "min": 1.0000104904174805, "max": 2.8484127521514893, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9560.7001953125, "min": 9560.7001953125, "max": 29170.595703125, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 11.854952812194824, "min": 0.40804263949394226, "max": 11.854952812194824, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2311.7158203125, "min": 79.16027069091797, "max": 2378.58251953125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06824096118939718, "min": 0.062746003022196, "max": 0.0726130405181034, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2729638447575887, "min": 0.250984012088784, "max": 0.363065202590517, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20688702560522976, "min": 0.13482619513182298, "max": 0.2938480947349294, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.827548102420919, "min": 0.5393047805272919, "max": 1.469240473674647, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 23.5, "min": 3.9318181818181817, "max": 23.5, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1034.0, "min": 173.0, "max": 1273.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.5, "min": 3.9318181818181817, "max": 23.5, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1034.0, "min": 173.0, "max": 1273.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1681672179", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1681672649" }, "total": 470.47056432400007, "count": 1, "self": 0.4338300510002, "children": { "run_training.setup": { "total": 0.17529905099991083, "count": 1, "self": 0.17529905099991083 }, "TrainerController.start_learning": { "total": 469.86143522199995, "count": 1, "self": 0.6505260919997227, "children": { "TrainerController._reset_env": { "total": 4.662438586999997, "count": 1, "self": 4.662438586999997 }, "TrainerController.advance": { "total": 464.4154935890002, "count": 18201, "self": 0.3139860860022736, "children": { "env_step": { "total": 464.10150750299795, "count": 18201, "self": 340.0618134180196, "children": { "SubprocessEnvManager._take_step": { "total": 123.74149258799832, "count": 18201, "self": 1.8181634610019728, "children": { "TorchPolicy.evaluate": { "total": 121.92332912699635, "count": 18201, "self": 121.92332912699635 } } }, "workers": { "total": 0.2982014969800275, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 468.2744856629886, "count": 18201, "is_parallel": true, "self": 212.9953454349885, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006576634999987618, "count": 1, "is_parallel": true, "self": 0.004319499000189353, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022571359997982654, "count": 10, "is_parallel": true, "self": 0.0022571359997982654 } } }, "UnityEnvironment.step": { "total": 0.03732977100003154, "count": 1, "is_parallel": true, "self": 0.0005722170002400162, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00035591999994721846, "count": 1, "is_parallel": true, "self": 0.00035591999994721846 }, "communicator.exchange": { "total": 0.034513871999934054, "count": 1, "is_parallel": true, "self": 0.034513871999934054 }, "steps_from_proto": { "total": 0.0018877619999102535, "count": 1, "is_parallel": true, "self": 0.0003704769998194024, "children": { "_process_rank_one_or_two_observation": { "total": 0.001517285000090851, "count": 10, "is_parallel": true, "self": 0.001517285000090851 } } } } } } }, "UnityEnvironment.step": { "total": 255.27914022800007, "count": 18200, "is_parallel": true, "self": 10.405149999021546, "children": { "UnityEnvironment._generate_step_input": { "total": 5.544085766992907, "count": 18200, "is_parallel": true, "self": 5.544085766992907 }, "communicator.exchange": { "total": 206.6918934729864, "count": 18200, "is_parallel": true, "self": 206.6918934729864 }, "steps_from_proto": { "total": 32.63801098899921, "count": 18200, "is_parallel": true, "self": 6.730043133996219, "children": { "_process_rank_one_or_two_observation": { "total": 25.907967855002994, "count": 182000, "is_parallel": true, "self": 25.907967855002994 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016665199996168667, "count": 1, "self": 0.00016665199996168667, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 460.9471030199304, "count": 418700, "is_parallel": true, "self": 10.390655498012165, "children": { "process_trajectory": { "total": 254.37236197191748, "count": 418700, "is_parallel": true, "self": 253.1180108489176, "children": { "RLTrainer._checkpoint": { "total": 1.2543511229998785, "count": 4, "is_parallel": true, "self": 1.2543511229998785 } } }, "_update_policy": { "total": 196.18408555000076, "count": 90, "is_parallel": true, "self": 70.73319325001012, "children": { "TorchPPOOptimizer.update": { "total": 125.45089229999064, "count": 4584, "is_parallel": true, "self": 125.45089229999064 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13281030200005262, "count": 1, "self": 0.0009389180002017383, "children": { "RLTrainer._checkpoint": { "total": 0.13187138399985088, "count": 1, "self": 0.13187138399985088 } } } } } } }