{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.938618540763855, "min": 0.938618540763855, "max": 2.87599515914917, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8972.2548828125, "min": 8972.2548828125, "max": 29484.701171875, "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": 12.54054069519043, "min": 0.18026265501976013, "max": 12.54054069519043, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2445.405517578125, "min": 34.97095489501953, "max": 2505.1455078125, "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": 0.06648631611503386, "min": 0.06215271084935617, "max": 0.07396830529706125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26594526446013544, "min": 0.24861084339742467, "max": 0.3698415264853062, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17673435690356235, "min": 0.09940047554018924, "max": 0.27343076771380853, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7069374276142494, "min": 0.39760190216075697, "max": 1.3671538385690427, "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": 25.227272727272727, "min": 2.75, "max": 25.227272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1110.0, "min": 121.0, "max": 1366.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.227272727272727, "min": 2.75, "max": 25.227272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1110.0, "min": 121.0, "max": 1366.0, "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": "1689292044", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1689292543" }, "total": 499.474360219, "count": 1, "self": 0.43075143999999455, "children": { "run_training.setup": { "total": 0.05000792399999909, "count": 1, "self": 0.05000792399999909 }, "TrainerController.start_learning": { "total": 498.993600855, "count": 1, "self": 0.5880310720008879, "children": { "TrainerController._reset_env": { "total": 4.089379120000046, "count": 1, "self": 4.089379120000046 }, "TrainerController.advance": { "total": 494.1759352909991, "count": 18201, "self": 0.30424915599905944, "children": { "env_step": { "total": 493.87168613500006, "count": 18201, "self": 357.77386607400064, "children": { "SubprocessEnvManager._take_step": { "total": 135.80767412800066, "count": 18201, "self": 1.9485818090045086, "children": { "TorchPolicy.evaluate": { "total": 133.85909231899615, "count": 18201, "self": 133.85909231899615 } } }, "workers": { "total": 0.2901459329987688, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 497.3372399060041, "count": 18201, "is_parallel": true, "self": 235.14856411101022, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005649292000043715, "count": 1, "is_parallel": true, "self": 0.004162787999973716, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014865040000699992, "count": 10, "is_parallel": true, "self": 0.0014865040000699992 } } }, "UnityEnvironment.step": { "total": 0.037675933000002715, "count": 1, "is_parallel": true, "self": 0.0005611850000377672, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041024000000788874, "count": 1, "is_parallel": true, "self": 0.00041024000000788874 }, "communicator.exchange": { "total": 0.033788329000003614, "count": 1, "is_parallel": true, "self": 0.033788329000003614 }, "steps_from_proto": { "total": 0.002916178999953445, "count": 1, "is_parallel": true, "self": 0.0005920839998907468, "children": { "_process_rank_one_or_two_observation": { "total": 0.002324095000062698, "count": 10, "is_parallel": true, "self": 0.002324095000062698 } } } } } } }, "UnityEnvironment.step": { "total": 262.18867579499386, "count": 18200, "is_parallel": true, "self": 10.927727862001404, "children": { "UnityEnvironment._generate_step_input": { "total": 5.817867067995621, "count": 18200, "is_parallel": true, "self": 5.817867067995621 }, "communicator.exchange": { "total": 205.85649500000227, "count": 18200, "is_parallel": true, "self": 205.85649500000227 }, "steps_from_proto": { "total": 39.58658586499456, "count": 18200, "is_parallel": true, "self": 7.211965547014302, "children": { "_process_rank_one_or_two_observation": { "total": 32.37462031798026, "count": 182000, "is_parallel": true, "self": 32.37462031798026 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015286299992567365, "count": 1, "self": 0.00015286299992567365, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 490.16979860498725, "count": 468330, "is_parallel": true, "self": 10.74216311396816, "children": { "process_trajectory": { "total": 270.2515906570193, "count": 468330, "is_parallel": true, "self": 269.3796941320192, "children": { "RLTrainer._checkpoint": { "total": 0.8718965250000679, "count": 4, "is_parallel": true, "self": 0.8718965250000679 } } }, "_update_policy": { "total": 209.1760448339998, "count": 90, "is_parallel": true, "self": 80.83944234499802, "children": { "TorchPPOOptimizer.update": { "total": 128.3366024890018, "count": 4587, "is_parallel": true, "self": 128.3366024890018 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1401025090000303, "count": 1, "self": 0.000930520000110846, "children": { "RLTrainer._checkpoint": { "total": 0.13917198899991945, "count": 1, "self": 0.13917198899991945 } } } } } } }