{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9069250822067261, "min": 0.9069250822067261, "max": 2.8706092834472656, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8669.296875, "min": 8669.296875, "max": 29461.0625, "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": 12.94612979888916, "min": 0.28005075454711914, "max": 12.957053184509277, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2524.495361328125, "min": 54.32984924316406, "max": 2643.23876953125, "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": 0.07751411882282791, "min": 0.06343679293229298, "max": 0.07751411882282791, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.31005647529131164, "min": 0.25792493867501276, "max": 0.3759135350714239, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20289182586266716, "min": 0.11332497593156957, "max": 0.28935924654497824, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8115673034506686, "min": 0.45329990372627826, "max": 1.3306983735631492, "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": 25.318181818181817, "min": 3.2045454545454546, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1114.0, "min": 141.0, "max": 1410.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.318181818181817, "min": 3.2045454545454546, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1114.0, "min": 141.0, "max": 1410.0, "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": "1708747704", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1708748151" }, "total": 446.447679464, "count": 1, "self": 0.43497157699994204, "children": { "run_training.setup": { "total": 0.05030990699992799, "count": 1, "self": 0.05030990699992799 }, "TrainerController.start_learning": { "total": 445.9623979800001, "count": 1, "self": 0.5682120950023091, "children": { "TrainerController._reset_env": { "total": 3.249984110000014, "count": 1, "self": 3.249984110000014 }, "TrainerController.advance": { "total": 442.045104750998, "count": 18200, "self": 0.26652247398942563, "children": { "env_step": { "total": 441.7785822770086, "count": 18200, "self": 284.78522696800337, "children": { "SubprocessEnvManager._take_step": { "total": 156.70781002398758, "count": 18200, "self": 1.5048749829913959, "children": { "TorchPolicy.evaluate": { "total": 155.20293504099618, "count": 18200, "self": 155.20293504099618 } } }, "workers": { "total": 0.28554528501763343, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 444.8618613250055, "count": 18200, "is_parallel": true, "self": 221.51422660001117, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005658488999870315, "count": 1, "is_parallel": true, "self": 0.004136007999704816, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015224810001654987, "count": 10, "is_parallel": true, "self": 0.0015224810001654987 } } }, "UnityEnvironment.step": { "total": 0.03907590599987998, "count": 1, "is_parallel": true, "self": 0.0007275269999809097, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004284369999822957, "count": 1, "is_parallel": true, "self": 0.0004284369999822957 }, "communicator.exchange": { "total": 0.03551913899991632, "count": 1, "is_parallel": true, "self": 0.03551913899991632 }, "steps_from_proto": { "total": 0.002400803000000451, "count": 1, "is_parallel": true, "self": 0.00041851499963740935, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019822880003630416, "count": 10, "is_parallel": true, "self": 0.0019822880003630416 } } } } } } }, "UnityEnvironment.step": { "total": 223.34763472499435, "count": 18199, "is_parallel": true, "self": 10.616457504032951, "children": { "UnityEnvironment._generate_step_input": { "total": 5.509817621999673, "count": 18199, "is_parallel": true, "self": 5.509817621999673 }, "communicator.exchange": { "total": 172.2111414999929, "count": 18199, "is_parallel": true, "self": 172.2111414999929 }, "steps_from_proto": { "total": 35.010218098968835, "count": 18199, "is_parallel": true, "self": 6.454513635020248, "children": { "_process_rank_one_or_two_observation": { "total": 28.555704463948587, "count": 181990, "is_parallel": true, "self": 28.555704463948587 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.838699990410532e-05, "count": 1, "self": 3.838699990410532e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 436.246459377993, "count": 669495, "is_parallel": true, "self": 14.556455712956904, "children": { "process_trajectory": { "total": 240.55062389203545, "count": 669495, "is_parallel": true, "self": 239.7823043780354, "children": { "RLTrainer._checkpoint": { "total": 0.7683195140000407, "count": 4, "is_parallel": true, "self": 0.7683195140000407 } } }, "_update_policy": { "total": 181.13937977300066, "count": 90, "is_parallel": true, "self": 51.7445487159946, "children": { "TorchPPOOptimizer.update": { "total": 129.39483105700606, "count": 4587, "is_parallel": true, "self": 129.39483105700606 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09905863699987094, "count": 1, "self": 0.0009261850000257255, "children": { "RLTrainer._checkpoint": { "total": 0.09813245199984522, "count": 1, "self": 0.09813245199984522 } } } } } } }