{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9280178546905518, "min": 0.9280178546905518, "max": 2.8585011959075928, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8881.130859375, "min": 8881.130859375, "max": 29273.91015625, "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": 12.439998626708984, "min": 0.25527888536453247, "max": 12.439998626708984, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2425.7998046875, "min": 49.52410125732422, "max": 2532.25732421875, "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": 0.06525879453664518, "min": 0.05874856612846248, "max": 0.07555479375033766, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2610351781465807, "min": 0.23499426451384992, "max": 0.37777396875168834, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.206851647144147, "min": 0.11409294613016148, "max": 0.29194492189323196, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.827406588576588, "min": 0.4563717845206459, "max": 1.4597246094661598, "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": 24.386363636363637, "min": 3.1136363636363638, "max": 25.045454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1073.0, "min": 137.0, "max": 1353.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.386363636363637, "min": 3.1136363636363638, "max": 25.045454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1073.0, "min": 137.0, "max": 1353.0, "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": "1721151204", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1721151667" }, "total": 462.62322497900004, "count": 1, "self": 0.48519518000011885, "children": { "run_training.setup": { "total": 0.06220941900005528, "count": 1, "self": 0.06220941900005528 }, "TrainerController.start_learning": { "total": 462.07582037999987, "count": 1, "self": 0.6078157530155295, "children": { "TrainerController._reset_env": { "total": 3.6234574799998427, "count": 1, "self": 3.6234574799998427 }, "TrainerController.advance": { "total": 457.7110165629847, "count": 18208, "self": 0.2962914629781608, "children": { "env_step": { "total": 457.41472510000654, "count": 18208, "self": 296.60760436300393, "children": { "SubprocessEnvManager._take_step": { "total": 160.5246787269955, "count": 18208, "self": 1.5433213559788328, "children": { "TorchPolicy.evaluate": { "total": 158.98135737101666, "count": 18208, "self": 158.98135737101666 } } }, "workers": { "total": 0.28244201000711655, "count": 18208, "self": 0.0, "children": { "worker_root": { "total": 460.706033219981, "count": 18208, "is_parallel": true, "self": 236.51051711997707, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006595984000114186, "count": 1, "is_parallel": true, "self": 0.004220856999836542, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023751270002776437, "count": 10, "is_parallel": true, "self": 0.0023751270002776437 } } }, "UnityEnvironment.step": { "total": 0.08522650899999462, "count": 1, "is_parallel": true, "self": 0.0006879550001031021, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046916099995542027, "count": 1, "is_parallel": true, "self": 0.00046916099995542027 }, "communicator.exchange": { "total": 0.0819510060000539, "count": 1, "is_parallel": true, "self": 0.0819510060000539 }, "steps_from_proto": { "total": 0.0021183869998822047, "count": 1, "is_parallel": true, "self": 0.0004059209998104052, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017124660000717995, "count": 10, "is_parallel": true, "self": 0.0017124660000717995 } } } } } } }, "UnityEnvironment.step": { "total": 224.19551610000394, "count": 18207, "is_parallel": true, "self": 10.431676463017766, "children": { "UnityEnvironment._generate_step_input": { "total": 5.377607168994928, "count": 18207, "is_parallel": true, "self": 5.377607168994928 }, "communicator.exchange": { "total": 175.35693456999365, "count": 18207, "is_parallel": true, "self": 175.35693456999365 }, "steps_from_proto": { "total": 33.029297897997594, "count": 18207, "is_parallel": true, "self": 6.2687565579631155, "children": { "_process_rank_one_or_two_observation": { "total": 26.76054134003448, "count": 182070, "is_parallel": true, "self": 26.76054134003448 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017873499996312603, "count": 1, "self": 0.00017873499996312603, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 452.1157860799817, "count": 684061, "is_parallel": true, "self": 14.491803350894997, "children": { "process_trajectory": { "total": 250.2868147560855, "count": 684061, "is_parallel": true, "self": 249.37154058208557, "children": { "RLTrainer._checkpoint": { "total": 0.9152741739999328, "count": 4, "is_parallel": true, "self": 0.9152741739999328 } } }, "_update_policy": { "total": 187.33716797300121, "count": 90, "is_parallel": true, "self": 60.29775219899943, "children": { "TorchPPOOptimizer.update": { "total": 127.03941577400178, "count": 4587, "is_parallel": true, "self": 127.03941577400178 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13335184899983688, "count": 1, "self": 0.0009831889999531995, "children": { "RLTrainer._checkpoint": { "total": 0.13236865999988368, "count": 1, "self": 0.13236865999988368 } } } } } } }