{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8611301183700562, "min": 0.8611301183700562, "max": 2.8657422065734863, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8222.0703125, "min": 8222.0703125, "max": 29411.111328125, "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": 12.964935302734375, "min": 0.2805672883987427, "max": 12.964935302734375, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2528.162353515625, "min": 54.4300537109375, "max": 2617.423095703125, "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": 0.07358072317462452, "min": 0.059199218854308705, "max": 0.07714252447773357, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2943228926984981, "min": 0.23679687541723482, "max": 0.3857126223886678, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19207708479142654, "min": 0.1256192287649302, "max": 0.28288584357383206, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7683083391657062, "min": 0.5024769150597208, "max": 1.4144292178691604, "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": 25.818181818181817, "min": 3.6363636363636362, "max": 25.818181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1136.0, "min": 160.0, "max": 1391.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.818181818181817, "min": 3.6363636363636362, "max": 25.818181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1136.0, "min": 160.0, "max": 1391.0, "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": "1700231706", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700232195" }, "total": 489.0650146920001, "count": 1, "self": 0.4301758650000238, "children": { "run_training.setup": { "total": 0.04184989600003064, "count": 1, "self": 0.04184989600003064 }, "TrainerController.start_learning": { "total": 488.59298893100004, "count": 1, "self": 0.6178613840039588, "children": { "TrainerController._reset_env": { "total": 8.219567095000002, "count": 1, "self": 8.219567095000002 }, "TrainerController.advance": { "total": 479.6680367959963, "count": 18199, "self": 0.292514478997532, "children": { "env_step": { "total": 479.37552231699874, "count": 18199, "self": 331.6446580650032, "children": { "SubprocessEnvManager._take_step": { "total": 147.43638202900638, "count": 18199, "self": 1.5118916080066356, "children": { "TorchPolicy.evaluate": { "total": 145.92449042099975, "count": 18199, "self": 145.92449042099975 } } }, "workers": { "total": 0.2944822229891315, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 487.0837858950157, "count": 18199, "is_parallel": true, "self": 234.55342411300717, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0054981229999384595, "count": 1, "is_parallel": true, "self": 0.003989320000073349, "children": { "_process_rank_one_or_two_observation": { "total": 0.001508802999865111, "count": 10, "is_parallel": true, "self": 0.001508802999865111 } } }, "UnityEnvironment.step": { "total": 0.03484560000003967, "count": 1, "is_parallel": true, "self": 0.0006377680000468899, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003853929999877437, "count": 1, "is_parallel": true, "self": 0.0003853929999877437 }, "communicator.exchange": { "total": 0.031897883999931764, "count": 1, "is_parallel": true, "self": 0.031897883999931764 }, "steps_from_proto": { "total": 0.0019245550000732692, "count": 1, "is_parallel": true, "self": 0.0003896760000543509, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015348790000189183, "count": 10, "is_parallel": true, "self": 0.0015348790000189183 } } } } } } }, "UnityEnvironment.step": { "total": 252.53036178200853, "count": 18198, "is_parallel": true, "self": 10.890032941028835, "children": { "UnityEnvironment._generate_step_input": { "total": 5.643882936981754, "count": 18198, "is_parallel": true, "self": 5.643882936981754 }, "communicator.exchange": { "total": 200.43077331299878, "count": 18198, "is_parallel": true, "self": 200.43077331299878 }, "steps_from_proto": { "total": 35.56567259099916, "count": 18198, "is_parallel": true, "self": 6.923681450996696, "children": { "_process_rank_one_or_two_observation": { "total": 28.64199114000246, "count": 181980, "is_parallel": true, "self": 28.64199114000246 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014302199997473508, "count": 1, "self": 0.00014302199997473508, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 475.5370926920847, "count": 520354, "is_parallel": true, "self": 10.760590513034686, "children": { "process_trajectory": { "total": 269.7422711870504, "count": 520354, "is_parallel": true, "self": 269.17178609905034, "children": { "RLTrainer._checkpoint": { "total": 0.5704850880000549, "count": 4, "is_parallel": true, "self": 0.5704850880000549 } } }, "_update_policy": { "total": 195.0342309919996, "count": 90, "is_parallel": true, "self": 60.956998150999425, "children": { "TorchPPOOptimizer.update": { "total": 134.07723284100018, "count": 4587, "is_parallel": true, "self": 134.07723284100018 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0873806339998282, "count": 1, "self": 0.001052768999898035, "children": { "RLTrainer._checkpoint": { "total": 0.08632786499993017, "count": 1, "self": 0.08632786499993017 } } } } } } }