{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0984749794006348, "min": 1.0984749794006348, "max": 2.8583476543426514, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10548.6552734375, "min": 10548.6552734375, "max": 29335.22265625, "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": 12.810503005981445, "min": 0.32797971367836, "max": 12.810503005981445, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2498.048095703125, "min": 63.6280632019043, "max": 2571.763427734375, "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": 0.06990396818989264, "min": 0.06361322305390643, "max": 0.07742398521251173, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27961587275957056, "min": 0.2544528922156257, "max": 0.3871199260625587, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19075208365478938, "min": 0.1098086138611988, "max": 0.2837318495208142, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7630083346191575, "min": 0.4392344554447952, "max": 1.418659247604071, "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": 25.40909090909091, "min": 3.1363636363636362, "max": 25.40909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1118.0, "min": 138.0, "max": 1364.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.40909090909091, "min": 3.1363636363636362, "max": 25.40909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1118.0, "min": 138.0, "max": 1364.0, "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": "1685668327", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1685668961" }, "total": 633.91708657, "count": 1, "self": 0.9030138069999794, "children": { "run_training.setup": { "total": 0.05853729800014662, "count": 1, "self": 0.05853729800014662 }, "TrainerController.start_learning": { "total": 632.9555354649999, "count": 1, "self": 0.8938488269900517, "children": { "TrainerController._reset_env": { "total": 1.0310933759999443, "count": 1, "self": 1.0310933759999443 }, "TrainerController.advance": { "total": 630.7620596650095, "count": 18222, "self": 0.4435611890269229, "children": { "env_step": { "total": 630.3184984759826, "count": 18222, "self": 515.6682469159175, "children": { "SubprocessEnvManager._take_step": { "total": 114.22731459302486, "count": 18222, "self": 2.838448351033776, "children": { "TorchPolicy.evaluate": { "total": 111.38886624199108, "count": 18222, "self": 111.38886624199108 } } }, "workers": { "total": 0.4229369670401866, "count": 18222, "self": 0.0, "children": { "worker_root": { "total": 630.2347865580196, "count": 18222, "is_parallel": true, "self": 271.5086637310096, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007881406000024072, "count": 1, "is_parallel": true, "self": 0.005650622999382904, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022307830006411677, "count": 10, "is_parallel": true, "self": 0.0022307830006411677 } } }, "UnityEnvironment.step": { "total": 0.0559965719999127, "count": 1, "is_parallel": true, "self": 0.0009161839998341748, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005188090001411183, "count": 1, "is_parallel": true, "self": 0.0005188090001411183 }, "communicator.exchange": { "total": 0.04966108400003577, "count": 1, "is_parallel": true, "self": 0.04966108400003577 }, "steps_from_proto": { "total": 0.004900494999901639, "count": 1, "is_parallel": true, "self": 0.00254598399965289, "children": { "_process_rank_one_or_two_observation": { "total": 0.002354511000248749, "count": 10, "is_parallel": true, "self": 0.002354511000248749 } } } } } } }, "UnityEnvironment.step": { "total": 358.72612282700993, "count": 18221, "is_parallel": true, "self": 14.775975457039749, "children": { "UnityEnvironment._generate_step_input": { "total": 7.728707697992377, "count": 18221, "is_parallel": true, "self": 7.728707697992377 }, "communicator.exchange": { "total": 286.34155356997803, "count": 18221, "is_parallel": true, "self": 286.34155356997803 }, "steps_from_proto": { "total": 49.87988610199977, "count": 18221, "is_parallel": true, "self": 9.948039363080397, "children": { "_process_rank_one_or_two_observation": { "total": 39.931846738919376, "count": 182210, "is_parallel": true, "self": 39.931846738919376 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00025471700018897536, "count": 1, "self": 0.00025471700018897536, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 624.9611883390492, "count": 634427, "is_parallel": true, "self": 15.7321097420147, "children": { "process_trajectory": { "total": 331.1813396090349, "count": 634427, "is_parallel": true, "self": 329.04240113403466, "children": { "RLTrainer._checkpoint": { "total": 2.138938475000259, "count": 4, "is_parallel": true, "self": 2.138938475000259 } } }, "_update_policy": { "total": 278.04773898799954, "count": 90, "is_parallel": true, "self": 101.93982396699425, "children": { "TorchPPOOptimizer.update": { "total": 176.10791502100528, "count": 4584, "is_parallel": true, "self": 176.10791502100528 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2682788800002527, "count": 1, "self": 0.0015655420002076426, "children": { "RLTrainer._checkpoint": { "total": 0.26671333800004504, "count": 1, "self": 0.26671333800004504 } } } } } } }