{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9669439792633057, "min": 0.9669439792633057, "max": 2.8651185035705566, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9243.017578125, "min": 9243.017578125, "max": 29341.6796875, "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": 1.3561557531356812, "min": 0.08919902890920639, "max": 1.3561557531356812, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 264.45037841796875, "min": 17.304611206054688, "max": 273.4912109375, "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": 0.06520253819561571, "min": 0.05958396135932109, "max": 0.07437491107225022, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26081015278246283, "min": 0.25227111931627744, "max": 0.3667486611024394, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.09636735989182604, "min": 0.04533774399269354, "max": 0.11031127293758533, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.3854694395673042, "min": 0.18135097597077415, "max": 0.5391862003826627, "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": 26.545454545454547, "min": 3.5681818181818183, "max": 26.545454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1168.0, "min": 157.0, "max": 1449.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.545454545454547, "min": 3.5681818181818183, "max": 26.545454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1168.0, "min": 157.0, "max": 1449.0, "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": "1677162829", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1677163310" }, "total": 480.40644559599997, "count": 1, "self": 0.3898341909998635, "children": { "run_training.setup": { "total": 0.19334343500003115, "count": 1, "self": 0.19334343500003115 }, "TrainerController.start_learning": { "total": 479.8232679700001, "count": 1, "self": 0.5241825370021616, "children": { "TrainerController._reset_env": { "total": 8.291881466999996, "count": 1, "self": 8.291881466999996 }, "TrainerController.advance": { "total": 470.8667146749979, "count": 18203, "self": 0.2895359659918313, "children": { "env_step": { "total": 470.5771787090061, "count": 18203, "self": 325.0597490870058, "children": { "SubprocessEnvManager._take_step": { "total": 145.22572952200528, "count": 18203, "self": 1.5452709950110375, "children": { "TorchPolicy.evaluate": { "total": 143.68045852699424, "count": 18203, "self": 31.794372578987748, "children": { "TorchPolicy.sample_actions": { "total": 111.8860859480065, "count": 18203, "self": 111.8860859480065 } } } } }, "workers": { "total": 0.2917000999950119, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 478.3077718539957, "count": 18203, "is_parallel": true, "self": 235.0820228230022, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0054812730000435295, "count": 1, "is_parallel": true, "self": 0.0026523980000092706, "children": { "_process_rank_one_or_two_observation": { "total": 0.002828875000034259, "count": 10, "is_parallel": true, "self": 0.002828875000034259 } } }, "UnityEnvironment.step": { "total": 0.03854398900000433, "count": 1, "is_parallel": true, "self": 0.000597132999985206, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004770489999827987, "count": 1, "is_parallel": true, "self": 0.0004770489999827987 }, "communicator.exchange": { "total": 0.03551114200001848, "count": 1, "is_parallel": true, "self": 0.03551114200001848 }, "steps_from_proto": { "total": 0.001958665000017845, "count": 1, "is_parallel": true, "self": 0.00046288600009347647, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014957789999243687, "count": 10, "is_parallel": true, "self": 0.0014957789999243687 } } } } } } }, "UnityEnvironment.step": { "total": 243.22574903099348, "count": 18202, "is_parallel": true, "self": 9.797748113001148, "children": { "UnityEnvironment._generate_step_input": { "total": 5.454286935995242, "count": 18202, "is_parallel": true, "self": 5.454286935995242 }, "communicator.exchange": { "total": 195.169809913993, "count": 18202, "is_parallel": true, "self": 195.169809913993 }, "steps_from_proto": { "total": 32.8039040680041, "count": 18202, "is_parallel": true, "self": 7.177130139992869, "children": { "_process_rank_one_or_two_observation": { "total": 25.626773928011232, "count": 182020, "is_parallel": true, "self": 25.626773928011232 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012030499999582389, "count": 1, "self": 0.00012030499999582389, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 467.31755065700514, "count": 423471, "is_parallel": true, "self": 10.524614990020837, "children": { "process_trajectory": { "total": 266.62745861198425, "count": 423471, "is_parallel": true, "self": 265.6900662039843, "children": { "RLTrainer._checkpoint": { "total": 0.937392407999937, "count": 4, "is_parallel": true, "self": 0.937392407999937 } } }, "_update_policy": { "total": 190.16547705500005, "count": 90, "is_parallel": true, "self": 64.6008750029988, "children": { "TorchPPOOptimizer.update": { "total": 125.56460205200125, "count": 4587, "is_parallel": true, "self": 125.56460205200125 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14036898599999859, "count": 1, "self": 0.001048912999976892, "children": { "RLTrainer._checkpoint": { "total": 0.1393200730000217, "count": 1, "self": 0.1393200730000217 } } } } } } }