{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8024705648422241, "min": 0.7927044034004211, "max": 2.8715708255767822, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7626.68017578125, "min": 7626.68017578125, "max": 29312.99609375, "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": 13.134885787963867, "min": 0.36808502674102783, "max": 13.134885787963867, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2561.302734375, "min": 71.40849304199219, "max": 2667.78759765625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06297214812487559, "min": 0.061769234232747744, "max": 0.07346908968996585, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25188859249950235, "min": 0.24707693693099098, "max": 0.3643654756802682, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17930980738909805, "min": 0.12426529690741982, "max": 0.28639841452240944, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7172392295563922, "min": 0.49706118762967927, "max": 1.3513686992958482, "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.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": 25.772727272727273, "min": 3.272727272727273, "max": 26.045454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1134.0, "min": 144.0, "max": 1407.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.772727272727273, "min": 3.272727272727273, "max": 26.045454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1134.0, "min": 144.0, "max": 1407.0, "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": "1738556176", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1738556613" }, "total": 436.99709046399994, "count": 1, "self": 0.486197231999995, "children": { "run_training.setup": { "total": 0.021219816999973773, "count": 1, "self": 0.021219816999973773 }, "TrainerController.start_learning": { "total": 436.48967341499997, "count": 1, "self": 0.4003564170109257, "children": { "TrainerController._reset_env": { "total": 2.112275834000002, "count": 1, "self": 2.112275834000002 }, "TrainerController.advance": { "total": 433.8870258569889, "count": 18192, "self": 0.3703260089930609, "children": { "env_step": { "total": 306.1356830560005, "count": 18192, "self": 232.67486720400757, "children": { "SubprocessEnvManager._take_step": { "total": 73.23477412098941, "count": 18192, "self": 1.2972446959947774, "children": { "TorchPolicy.evaluate": { "total": 71.93752942499464, "count": 18192, "self": 71.93752942499464 } } }, "workers": { "total": 0.22604173100353364, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 434.82218574100716, "count": 18192, "is_parallel": true, "self": 231.2313866400068, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003064812000047823, "count": 1, "is_parallel": true, "self": 0.0008624459999282408, "children": { "_process_rank_one_or_two_observation": { "total": 0.002202366000119582, "count": 10, "is_parallel": true, "self": 0.002202366000119582 } } }, "UnityEnvironment.step": { "total": 0.03552457000000686, "count": 1, "is_parallel": true, "self": 0.0005742539999573637, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041981499998655636, "count": 1, "is_parallel": true, "self": 0.00041981499998655636 }, "communicator.exchange": { "total": 0.03252814400002535, "count": 1, "is_parallel": true, "self": 0.03252814400002535 }, "steps_from_proto": { "total": 0.002002357000037591, "count": 1, "is_parallel": true, "self": 0.0003522280001106992, "children": { "_process_rank_one_or_two_observation": { "total": 0.001650128999926892, "count": 10, "is_parallel": true, "self": 0.001650128999926892 } } } } } } }, "UnityEnvironment.step": { "total": 203.59079910100036, "count": 18191, "is_parallel": true, "self": 9.580058947025464, "children": { "UnityEnvironment._generate_step_input": { "total": 5.448285991981493, "count": 18191, "is_parallel": true, "self": 5.448285991981493 }, "communicator.exchange": { "total": 157.47318739600723, "count": 18191, "is_parallel": true, "self": 157.47318739600723 }, "steps_from_proto": { "total": 31.089266765986167, "count": 18191, "is_parallel": true, "self": 5.538819233036293, "children": { "_process_rank_one_or_two_observation": { "total": 25.550447532949875, "count": 181910, "is_parallel": true, "self": 25.550447532949875 } } } } } } } } } } }, "trainer_advance": { "total": 127.38101679199531, "count": 18192, "self": 0.47278789700408197, "children": { "process_trajectory": { "total": 27.36454938599104, "count": 18192, "self": 26.813021801991, "children": { "RLTrainer._checkpoint": { "total": 0.5515275840000413, "count": 4, "self": 0.5515275840000413 } } }, "_update_policy": { "total": 99.54367950900019, "count": 90, "self": 40.12375789299176, "children": { "TorchPPOOptimizer.update": { "total": 59.41992161600842, "count": 4587, "self": 59.41992161600842 } } } } } } }, "trainer_threads": { "total": 8.800000159681076e-07, "count": 1, "self": 8.800000159681076e-07 }, "TrainerController._save_models": { "total": 0.09001442700014195, "count": 1, "self": 0.0009488680002505134, "children": { "RLTrainer._checkpoint": { "total": 0.08906555899989144, "count": 1, "self": 0.08906555899989144 } } } } } } }