{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0801036357879639, "min": 1.0801036357879639, "max": 2.8812692165374756, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10265.3046875, "min": 10265.3046875, "max": 29411.99609375, "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": 12.756884574890137, "min": 0.4580287039279938, "max": 12.762374877929688, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2487.592529296875, "min": 88.8575668334961, "max": 2603.5244140625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06556609462113913, "min": 0.06171148405995279, "max": 0.07288568455146115, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2622643784845565, "min": 0.25903957016199974, "max": 0.36442842275730575, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.24433831556462773, "min": 0.18846201607455298, "max": 0.45081162145909137, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9773532622585109, "min": 0.7538480642982119, "max": 1.8032464858363655, "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": 0.09999999999999998, "min": 0.09999999999999998, "max": 0.09999999999999998, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.3999999999999999, "min": 0.3999999999999999, "max": 0.4999999999999999, "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.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.Environment.CumulativeReward.mean": { "value": 24.795454545454547, "min": 3.590909090909091, "max": 25.113636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1091.0, "min": 158.0, "max": 1379.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.795454545454547, "min": 3.590909090909091, "max": 25.113636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1091.0, "min": 158.0, "max": 1379.0, "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": "1791214261", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1791214701" }, "total": 440.26331568700016, "count": 1, "self": 0.4323882539999886, "children": { "run_training.setup": { "total": 0.0260864300000776, "count": 1, "self": 0.0260864300000776 }, "TrainerController.start_learning": { "total": 439.8048410030001, "count": 1, "self": 0.3263966920180792, "children": { "TrainerController._reset_env": { "total": 2.7965584549999676, "count": 1, "self": 2.7965584549999676 }, "TrainerController.advance": { "total": 436.578178303982, "count": 18192, "self": 0.35695121694243426, "children": { "env_step": { "total": 314.4382021010208, "count": 18192, "self": 245.10798705101, "children": { "SubprocessEnvManager._take_step": { "total": 69.12921915800962, "count": 18192, "self": 1.2073633200234326, "children": { "TorchPolicy.evaluate": { "total": 67.92185583798619, "count": 18192, "self": 67.92185583798619 } } }, "workers": { "total": 0.20099589200117407, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 437.99593489301697, "count": 18192, "is_parallel": true, "self": 222.2195748230256, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0050989220001156355, "count": 1, "is_parallel": true, "self": 0.0036067260007257573, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014921959993898781, "count": 10, "is_parallel": true, "self": 0.0014921959993898781 } } }, "UnityEnvironment.step": { "total": 0.03415105800013407, "count": 1, "is_parallel": true, "self": 0.000575809000110894, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000409778999937771, "count": 1, "is_parallel": true, "self": 0.000409778999937771 }, "communicator.exchange": { "total": 0.03131287800010796, "count": 1, "is_parallel": true, "self": 0.03131287800010796 }, "steps_from_proto": { "total": 0.0018525919999774487, "count": 1, "is_parallel": true, "self": 0.00034826300020540657, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015043289997720422, "count": 10, "is_parallel": true, "self": 0.0015043289997720422 } } } } } } }, "UnityEnvironment.step": { "total": 215.77636006999137, "count": 18191, "is_parallel": true, "self": 10.12305796499777, "children": { "UnityEnvironment._generate_step_input": { "total": 5.2462575240047045, "count": 18191, "is_parallel": true, "self": 5.2462575240047045 }, "communicator.exchange": { "total": 164.49264586299705, "count": 18191, "is_parallel": true, "self": 164.49264586299705 }, "steps_from_proto": { "total": 35.914398717991844, "count": 18191, "is_parallel": true, "self": 6.683779233959285, "children": { "_process_rank_one_or_two_observation": { "total": 29.23061948403256, "count": 181910, "is_parallel": true, "self": 29.23061948403256 } } } } } } } } } } }, "trainer_advance": { "total": 121.78302498601875, "count": 18192, "self": 0.4061828930489355, "children": { "process_trajectory": { "total": 24.48577697896917, "count": 18192, "self": 23.985689610969075, "children": { "RLTrainer._checkpoint": { "total": 0.500087368000095, "count": 4, "self": 0.500087368000095 } } }, "_update_policy": { "total": 96.89106511400064, "count": 90, "self": 37.05839402299375, "children": { "TorchPPOOptimizer.update": { "total": 59.83267109100689, "count": 4587, "self": 59.83267109100689 } } } } } } }, "trainer_threads": { "total": 9.719999525259482e-07, "count": 1, "self": 9.719999525259482e-07 }, "TrainerController._save_models": { "total": 0.10370658000010735, "count": 1, "self": 0.0010684750000109489, "children": { "RLTrainer._checkpoint": { "total": 0.1026381050000964, "count": 1, "self": 0.1026381050000964 } } } } } } }