{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8131337761878967, "min": 0.8131337761878967, "max": 2.8507213592529297, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7781.6904296875, "min": 7781.6904296875, "max": 29256.953125, "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": 13.00084114074707, "min": 0.3146093785762787, "max": 13.00084114074707, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2535.1640625, "min": 61.034217834472656, "max": 2624.9794921875, "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": 0.06354423108232189, "min": 0.061612873628773206, "max": 0.07781195699313756, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25417692432928757, "min": 0.24645149451509282, "max": 0.3636916453579747, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21714577473261776, "min": 0.12901567617960857, "max": 0.2716754124883343, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.868583098930471, "min": 0.5160627047184343, "max": 1.3529566219624352, "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": 25.681818181818183, "min": 3.6363636363636362, "max": 25.681818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1130.0, "min": 160.0, "max": 1393.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.681818181818183, "min": 3.6363636363636362, "max": 25.681818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1130.0, "min": 160.0, "max": 1393.0, "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": "1705891828", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/roboto/Software/.miniconda/envs/HFRL/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=/home/roboto/Software/ml-agents-custom-envs/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2", "numpy_version": "1.21.2", "end_time_seconds": "1705892052" }, "total": 223.11941895799828, "count": 1, "self": 0.218087208995712, "children": { "run_training.setup": { "total": 0.02777301400055876, "count": 1, "self": 0.02777301400055876 }, "TrainerController.start_learning": { "total": 222.873558735002, "count": 1, "self": 0.3119534327852307, "children": { "TrainerController._reset_env": { "total": 1.5715625770026236, "count": 1, "self": 1.5715625770026236 }, "TrainerController.advance": { "total": 220.93544689521514, "count": 18201, "self": 0.16038432313507656, "children": { "env_step": { "total": 220.77506257208006, "count": 18201, "self": 144.68942124030582, "children": { "SubprocessEnvManager._take_step": { "total": 75.91934540115471, "count": 18201, "self": 0.8019164445213391, "children": { "TorchPolicy.evaluate": { "total": 75.11742895663338, "count": 18201, "self": 75.11742895663338 } } }, "workers": { "total": 0.1662959306195262, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 222.49752348200855, "count": 18201, "is_parallel": true, "self": 122.34409181486262, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001291034001042135, "count": 1, "is_parallel": true, "self": 0.0003377350003574975, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009532990006846376, "count": 10, "is_parallel": true, "self": 0.0009532990006846376 } } }, "UnityEnvironment.step": { "total": 0.015823729998373892, "count": 1, "is_parallel": true, "self": 0.00022800499573349953, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000151368003571406, "count": 1, "is_parallel": true, "self": 0.000151368003571406 }, "communicator.exchange": { "total": 0.0146607779970509, "count": 1, "is_parallel": true, "self": 0.0146607779970509 }, "steps_from_proto": { "total": 0.0007835790020180866, "count": 1, "is_parallel": true, "self": 0.0001660799898672849, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006174990121508017, "count": 10, "is_parallel": true, "self": 0.0006174990121508017 } } } } } } }, "UnityEnvironment.step": { "total": 100.15343166714592, "count": 18200, "is_parallel": true, "self": 4.1765696630463935, "children": { "UnityEnvironment._generate_step_input": { "total": 2.2558485222034506, "count": 18200, "is_parallel": true, "self": 2.2558485222034506 }, "communicator.exchange": { "total": 79.640976661678, "count": 18200, "is_parallel": true, "self": 79.640976661678 }, "steps_from_proto": { "total": 14.080036820218083, "count": 18200, "is_parallel": true, "self": 2.8033314647327643, "children": { "_process_rank_one_or_two_observation": { "total": 11.27670535548532, "count": 182000, "is_parallel": true, "self": 11.27670535548532 } } } } } } } } } } } } }, "trainer_threads": { "total": 8.70709991431795e-05, "count": 1, "self": 8.70709991431795e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 220.39852485174197, "count": 233188, "is_parallel": true, "self": 2.0390649433102226, "children": { "process_trajectory": { "total": 117.768107806427, "count": 233188, "is_parallel": true, "self": 117.49019857042731, "children": { "RLTrainer._checkpoint": { "total": 0.27790923599968664, "count": 4, "is_parallel": true, "self": 0.27790923599968664 } } }, "_update_policy": { "total": 100.59135210200475, "count": 90, "is_parallel": true, "self": 29.993701711158792, "children": { "TorchPPOOptimizer.update": { "total": 70.59765039084596, "count": 4587, "is_parallel": true, "self": 70.59765039084596 } } } } } } } } }, "TrainerController._save_models": { "total": 0.05450875899987295, "count": 1, "self": 0.000590319003094919, "children": { "RLTrainer._checkpoint": { "total": 0.053918439996778034, "count": 1, "self": 0.053918439996778034 } } } } } } }