{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7348459959030151, "min": 0.7348459959030151, "max": 2.865286350250244, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7048.64306640625, "min": 7048.64306640625, "max": 29437.953125, "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": 12.883021354675293, "min": 0.396801620721817, "max": 12.883021354675293, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2512.189208984375, "min": 76.9795150756836, "max": 2608.241943359375, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06970750582495741, "min": 0.0634444485605676, "max": 0.07180017014262359, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27883002329982964, "min": 0.257203988702945, "max": 0.35900085071311794, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22227553241685327, "min": 0.13914987840461454, "max": 0.2973207308965571, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8891021296674131, "min": 0.5565995136184582, "max": 1.4866036544827854, "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": 25.272727272727273, "min": 3.8863636363636362, "max": 25.4, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1112.0, "min": 171.0, "max": 1397.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.272727272727273, "min": 3.8863636363636362, "max": 25.4, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1112.0, "min": 171.0, "max": 1397.0, "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": "1703355053", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703355244" }, "total": 190.66512508000233, "count": 1, "self": 0.21861784999782685, "children": { "run_training.setup": { "total": 0.03512233000219567, "count": 1, "self": 0.03512233000219567 }, "TrainerController.start_learning": { "total": 190.4113849000023, "count": 1, "self": 0.27285283554374473, "children": { "TrainerController._reset_env": { "total": 1.6260928140000033, "count": 1, "self": 1.6260928140000033 }, "TrainerController.advance": { "total": 188.46283069545825, "count": 18204, "self": 0.1334940063425165, "children": { "env_step": { "total": 188.32933668911573, "count": 18204, "self": 122.32277728152621, "children": { "SubprocessEnvManager._take_step": { "total": 65.86555651080562, "count": 18204, "self": 0.6742835178374662, "children": { "TorchPolicy.evaluate": { "total": 65.19127299296815, "count": 18204, "self": 65.19127299296815 } } }, "workers": { "total": 0.14100289678390254, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 190.12331954228648, "count": 18204, "is_parallel": true, "self": 106.02259637352836, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001002428001811495, "count": 1, "is_parallel": true, "self": 0.00030572399919037707, "children": { "_process_rank_one_or_two_observation": { "total": 0.000696704002621118, "count": 10, "is_parallel": true, "self": 0.000696704002621118 } } }, "UnityEnvironment.step": { "total": 0.01436938600090798, "count": 1, "is_parallel": true, "self": 0.00020444900292204693, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00014785999883315526, "count": 1, "is_parallel": true, "self": 0.00014785999883315526 }, "communicator.exchange": { "total": 0.013358883999899263, "count": 1, "is_parallel": true, "self": 0.013358883999899263 }, "steps_from_proto": { "total": 0.0006581929992535152, "count": 1, "is_parallel": true, "self": 0.00014898199879098684, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005092110004625283, "count": 10, "is_parallel": true, "self": 0.0005092110004625283 } } } } } } }, "UnityEnvironment.step": { "total": 84.10072316875812, "count": 18203, "is_parallel": true, "self": 3.6891173070798686, "children": { "UnityEnvironment._generate_step_input": { "total": 2.1030777683481574, "count": 18203, "is_parallel": true, "self": 2.1030777683481574 }, "communicator.exchange": { "total": 66.46717382049246, "count": 18203, "is_parallel": true, "self": 66.46717382049246 }, "steps_from_proto": { "total": 11.841354272837634, "count": 18203, "is_parallel": true, "self": 2.520660168331233, "children": { "_process_rank_one_or_two_observation": { "total": 9.320694104506401, "count": 182030, "is_parallel": true, "self": 9.320694104506401 } } } } } } } } } } } } }, "trainer_threads": { "total": 6.571500125573948e-05, "count": 1, "self": 6.571500125573948e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 188.33426644726205, "count": 135668, "is_parallel": true, "self": 0.9353842000418808, "children": { "process_trajectory": { "total": 103.981528868233, "count": 135668, "is_parallel": true, "self": 103.67325237323894, "children": { "RLTrainer._checkpoint": { "total": 0.30827649499406107, "count": 4, "is_parallel": true, "self": 0.30827649499406107 } } }, "_update_policy": { "total": 83.41735337898717, "count": 90, "is_parallel": true, "self": 21.51815268601058, "children": { "TorchPPOOptimizer.update": { "total": 61.89920069297659, "count": 4587, "is_parallel": true, "self": 61.89920069297659 } } } } } } } } }, "TrainerController._save_models": { "total": 0.04954283999904874, "count": 1, "self": 0.00040619699939270504, "children": { "RLTrainer._checkpoint": { "total": 0.04913664299965603, "count": 1, "self": 0.04913664299965603 } } } } } } }