{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8439730405807495, "min": 0.8439730405807495, "max": 2.8562042713165283, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8123.240234375, "min": 8123.240234375, "max": 29250.388671875, "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": 12.926410675048828, "min": 0.2630747854709625, "max": 12.926410675048828, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2520.650146484375, "min": 51.03650665283203, "max": 2628.05859375, "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": 0.07300874599016371, "min": 0.06324982391136776, "max": 0.07709351943790978, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29203498396065486, "min": 0.252999295645471, "max": 0.3645771658192126, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18521281992833988, "min": 0.13071461608199694, "max": 0.2934536890071981, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7408512797133595, "min": 0.5228584643279878, "max": 1.4672684450359905, "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": 25.363636363636363, "min": 3.727272727272727, "max": 25.436363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1116.0, "min": 164.0, "max": 1399.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.363636363636363, "min": 3.727272727272727, "max": 25.436363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1116.0, "min": 164.0, "max": 1399.0, "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": "1719056586", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719057059" }, "total": 472.644242731, "count": 1, "self": 0.6801512939999839, "children": { "run_training.setup": { "total": 0.054298135999999886, "count": 1, "self": 0.054298135999999886 }, "TrainerController.start_learning": { "total": 471.90979330100004, "count": 1, "self": 0.6139594400037822, "children": { "TrainerController._reset_env": { "total": 2.817882102999988, "count": 1, "self": 2.817882102999988 }, "TrainerController.advance": { "total": 468.3441757319962, "count": 18223, "self": 0.29542985298832036, "children": { "env_step": { "total": 468.04874587900787, "count": 18223, "self": 306.38436550300605, "children": { "SubprocessEnvManager._take_step": { "total": 161.35823612500457, "count": 18223, "self": 1.565594845009457, "children": { "TorchPolicy.evaluate": { "total": 159.7926412799951, "count": 18223, "self": 159.7926412799951 } } }, "workers": { "total": 0.3061442509972494, "count": 18223, "self": 0.0, "children": { "worker_root": { "total": 470.65199625300005, "count": 18223, "is_parallel": true, "self": 237.3308344790131, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005156426999974428, "count": 1, "is_parallel": true, "self": 0.003428408999923249, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017280180000511791, "count": 10, "is_parallel": true, "self": 0.0017280180000511791 } } }, "UnityEnvironment.step": { "total": 0.03603282199998148, "count": 1, "is_parallel": true, "self": 0.0006745669999190795, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040223100000957857, "count": 1, "is_parallel": true, "self": 0.00040223100000957857 }, "communicator.exchange": { "total": 0.032807765000029576, "count": 1, "is_parallel": true, "self": 0.032807765000029576 }, "steps_from_proto": { "total": 0.002148259000023245, "count": 1, "is_parallel": true, "self": 0.0004193660000737509, "children": { "_process_rank_one_or_two_observation": { "total": 0.001728892999949494, "count": 10, "is_parallel": true, "self": 0.001728892999949494 } } } } } } }, "UnityEnvironment.step": { "total": 233.32116177398694, "count": 18222, "is_parallel": true, "self": 10.534953338990306, "children": { "UnityEnvironment._generate_step_input": { "total": 5.577158020001946, "count": 18222, "is_parallel": true, "self": 5.577158020001946 }, "communicator.exchange": { "total": 182.11915364699502, "count": 18222, "is_parallel": true, "self": 182.11915364699502 }, "steps_from_proto": { "total": 35.089896767999676, "count": 18222, "is_parallel": true, "self": 6.677338799017093, "children": { "_process_rank_one_or_two_observation": { "total": 28.412557968982583, "count": 182220, "is_parallel": true, "self": 28.412557968982583 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014439900007801043, "count": 1, "self": 0.00014439900007801043, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 462.81615744999687, "count": 697604, "is_parallel": true, "self": 14.76791120298725, "children": { "process_trajectory": { "total": 256.4912259430092, "count": 697604, "is_parallel": true, "self": 255.2226398460091, "children": { "RLTrainer._checkpoint": { "total": 1.2685860970001386, "count": 4, "is_parallel": true, "self": 1.2685860970001386 } } }, "_update_policy": { "total": 191.5570203040004, "count": 90, "is_parallel": true, "self": 61.661839387002885, "children": { "TorchPPOOptimizer.update": { "total": 129.8951809169975, "count": 4587, "is_parallel": true, "self": 129.8951809169975 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13363162699999975, "count": 1, "self": 0.0013093470000740126, "children": { "RLTrainer._checkpoint": { "total": 0.13232227999992574, "count": 1, "self": 0.13232227999992574 } } } } } } }