{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9198587536811829, "min": 0.9198587536811829, "max": 2.871812105178833, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8782.8115234375, "min": 8782.8115234375, "max": 29410.228515625, "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": 12.793374061584473, "min": 0.41380077600479126, "max": 12.793374061584473, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2494.7080078125, "min": 80.27735137939453, "max": 2621.959228515625, "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": 0.06668174611495845, "min": 0.061519490821713894, "max": 0.07293217401020229, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2667269844598338, "min": 0.2514018374466675, "max": 0.36466087005101144, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2147723681056032, "min": 0.1432864532312926, "max": 0.31729634128072687, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8590894724224128, "min": 0.5731458129251704, "max": 1.4845566784634312, "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": 25.113636363636363, "min": 3.409090909090909, "max": 25.490909090909092, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1105.0, "min": 150.0, "max": 1402.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.113636363636363, "min": 3.409090909090909, "max": 25.490909090909092, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1105.0, "min": 150.0, "max": 1402.0, "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": "1673634834", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1673635290" }, "total": 456.50101982700005, "count": 1, "self": 0.3919911030001231, "children": { "run_training.setup": { "total": 0.10930709299998398, "count": 1, "self": 0.10930709299998398 }, "TrainerController.start_learning": { "total": 455.99972163099994, "count": 1, "self": 0.5313269280039776, "children": { "TrainerController._reset_env": { "total": 8.875506201999997, "count": 1, "self": 8.875506201999997 }, "TrainerController.advance": { "total": 446.4693224539959, "count": 18200, "self": 0.2839772559926814, "children": { "env_step": { "total": 446.18534519800323, "count": 18200, "self": 292.00064610501863, "children": { "SubprocessEnvManager._take_step": { "total": 153.89066350799965, "count": 18200, "self": 1.4789820569872063, "children": { "TorchPolicy.evaluate": { "total": 152.41168145101244, "count": 18200, "self": 35.505972822017156, "children": { "TorchPolicy.sample_actions": { "total": 116.90570862899528, "count": 18200, "self": 116.90570862899528 } } } } }, "workers": { "total": 0.29403558498495386, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 454.6899664539933, "count": 18200, "is_parallel": true, "self": 221.37485349599353, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.010467222999977821, "count": 1, "is_parallel": true, "self": 0.006687911999847529, "children": { "_process_rank_one_or_two_observation": { "total": 0.003779311000130292, "count": 10, "is_parallel": true, "self": 0.003779311000130292 } } }, "UnityEnvironment.step": { "total": 0.04703521400006139, "count": 1, "is_parallel": true, "self": 0.0004382130000522011, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00031624899997950706, "count": 1, "is_parallel": true, "self": 0.00031624899997950706 }, "communicator.exchange": { "total": 0.04419738100000359, "count": 1, "is_parallel": true, "self": 0.04419738100000359 }, "steps_from_proto": { "total": 0.0020833710000260908, "count": 1, "is_parallel": true, "self": 0.0005071880002560647, "children": { "_process_rank_one_or_two_observation": { "total": 0.001576182999770026, "count": 10, "is_parallel": true, "self": 0.001576182999770026 } } } } } } }, "UnityEnvironment.step": { "total": 233.31511295799976, "count": 18199, "is_parallel": true, "self": 8.763693477013135, "children": { "UnityEnvironment._generate_step_input": { "total": 5.703208457006781, "count": 18199, "is_parallel": true, "self": 5.703208457006781 }, "communicator.exchange": { "total": 185.95023191699238, "count": 18199, "is_parallel": true, "self": 185.95023191699238 }, "steps_from_proto": { "total": 32.897979106987464, "count": 18199, "is_parallel": true, "self": 7.084942155975455, "children": { "_process_rank_one_or_two_observation": { "total": 25.81303695101201, "count": 181990, "is_parallel": true, "self": 25.81303695101201 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.7545000029458606e-05, "count": 1, "self": 4.7545000029458606e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 443.04978315398, "count": 348523, "is_parallel": true, "self": 9.887929237984508, "children": { "process_trajectory": { "total": 253.3712930449957, "count": 348523, "is_parallel": true, "self": 252.55201198399584, "children": { "RLTrainer._checkpoint": { "total": 0.819281060999856, "count": 4, "is_parallel": true, "self": 0.819281060999856 } } }, "_update_policy": { "total": 179.7905608709998, "count": 90, "is_parallel": true, "self": 46.36150516699479, "children": { "TorchPPOOptimizer.update": { "total": 133.429055704005, "count": 4587, "is_parallel": true, "self": 133.429055704005 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12351850200002445, "count": 1, "self": 0.0010903130000770034, "children": { "RLTrainer._checkpoint": { "total": 0.12242818899994745, "count": 1, "self": 0.12242818899994745 } } } } } } }