{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8597385287284851, "min": 0.8597385287284851, "max": 2.8618063926696777, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8208.783203125, "min": 8208.783203125, "max": 29307.759765625, "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": 12.852070808410645, "min": 0.5164111256599426, "max": 12.852070808410645, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2506.15380859375, "min": 100.18376159667969, "max": 2607.283203125, "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": 0.06876063435814941, "min": 0.062206382332963175, "max": 0.07603328409145345, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27504253743259766, "min": 0.2574286869009181, "max": 0.35579460488595804, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1975904208626233, "min": 0.15396977624828545, "max": 0.30251789017050873, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7903616834504932, "min": 0.6158791049931418, "max": 1.5125894508525437, "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": 25.431818181818183, "min": 4.0227272727272725, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1119.0, "min": 177.0, "max": 1399.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.431818181818183, "min": 4.0227272727272725, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1119.0, "min": 177.0, "max": 1399.0, "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": "1678516630", "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 ./content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget134 --no-graphics", "mlagents_version": "0.29.0", "mlagents_envs_version": "0.29.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1678517132" }, "total": 501.9885006480008, "count": 1, "self": 0.4417172790008408, "children": { "run_training.setup": { "total": 0.2039826529999118, "count": 1, "self": 0.2039826529999118 }, "TrainerController.start_learning": { "total": 501.34280071600006, "count": 1, "self": 0.5759518069799014, "children": { "TrainerController._reset_env": { "total": 11.60341346000041, "count": 1, "self": 11.60341346000041 }, "TrainerController.advance": { "total": 489.04800855402027, "count": 18202, "self": 0.2924938019878027, "children": { "env_step": { "total": 488.75551475203247, "count": 18202, "self": 345.62828219105086, "children": { "SubprocessEnvManager._take_step": { "total": 142.85064818503997, "count": 18202, "self": 1.5497314450740305, "children": { "TorchPolicy.evaluate": { "total": 141.30091673996594, "count": 18202, "self": 30.70963395198305, "children": { "TorchPolicy.sample_actions": { "total": 110.59128278798289, "count": 18202, "self": 110.59128278798289 } } } } }, "workers": { "total": 0.2765843759416384, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 499.6037741860546, "count": 18202, "is_parallel": true, "self": 247.41171643097823, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0031769340002938407, "count": 1, "is_parallel": true, "self": 0.0010422980003568227, "children": { "_process_rank_one_or_two_observation": { "total": 0.002134635999937018, "count": 10, "is_parallel": true, "self": 0.002134635999937018 } } }, "UnityEnvironment.step": { "total": 0.05643437500020809, "count": 1, "is_parallel": true, "self": 0.00040273700051329797, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003730079997694702, "count": 1, "is_parallel": true, "self": 0.0003730079997694702 }, "communicator.exchange": { "total": 0.05365626799994061, "count": 1, "is_parallel": true, "self": 0.05365626799994061 }, "steps_from_proto": { "total": 0.002002361999984714, "count": 1, "is_parallel": true, "self": 0.0004220929995426559, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015802690004420583, "count": 10, "is_parallel": true, "self": 0.0015802690004420583 } } } } } } }, "UnityEnvironment.step": { "total": 252.19205775507635, "count": 18201, "is_parallel": true, "self": 9.715321236031741, "children": { "UnityEnvironment._generate_step_input": { "total": 5.122485087015775, "count": 18201, "is_parallel": true, "self": 5.122485087015775 }, "communicator.exchange": { "total": 204.32853786103988, "count": 18201, "is_parallel": true, "self": 204.32853786103988 }, "steps_from_proto": { "total": 33.025713570988955, "count": 18201, "is_parallel": true, "self": 7.266439383838588, "children": { "_process_rank_one_or_two_observation": { "total": 25.759274187150368, "count": 182010, "is_parallel": true, "self": 25.759274187150368 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011712600007740548, "count": 1, "self": 0.00011712600007740548, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 485.0185345252612, "count": 467185, "is_parallel": true, "self": 12.0565652301093, "children": { "process_trajectory": { "total": 274.9691860331486, "count": 467185, "is_parallel": true, "self": 273.35013480314865, "children": { "RLTrainer._checkpoint": { "total": 1.6190512299999682, "count": 4, "is_parallel": true, "self": 1.6190512299999682 } } }, "_update_policy": { "total": 197.9927832620033, "count": 90, "is_parallel": true, "self": 85.20350026495544, "children": { "TorchPPOOptimizer.update": { "total": 112.78928299704785, "count": 4584, "is_parallel": true, "self": 112.78928299704785 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1153097689993956, "count": 1, "self": 0.0008599729990237392, "children": { "RLTrainer._checkpoint": { "total": 0.11444979600037186, "count": 1, "self": 0.11444979600037186 } } } } } } }