{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1118569374084473, "min": 1.0751315355300903, "max": 2.8644354343414307, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10616.009765625, "min": 10616.009765625, "max": 29366.19140625, "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": 10.01583194732666, "min": 0.40802836418151855, "max": 10.01583194732666, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1953.087158203125, "min": 79.15750122070312, "max": 2042.1552734375, "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": 0.03199521463830024, "min": 0.02304690623132046, "max": 0.03328513243832276, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.12798085855320096, "min": 0.09563968744381175, "max": 0.1662858861576145, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.26506936084479094, "min": 0.1418232012850543, "max": 0.31913476039965943, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.0602774433791637, "min": 0.5672928051402172, "max": 1.5956738019982972, "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": 0.0013851600382799997, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.102694, "min": 0.102694, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.410776, "min": 0.410776, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00014443060000000012, "min": 0.00014443060000000012, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000005, "min": 0.0005777224000000005, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 19.363636363636363, "min": 3.522727272727273, "max": 20.09090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 852.0, "min": 155.0, "max": 1088.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 19.363636363636363, "min": 3.522727272727273, "max": 20.09090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 852.0, "min": 155.0, "max": 1088.0, "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": "1708883288", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1708883784" }, "total": 495.73705442999994, "count": 1, "self": 0.4861209929998722, "children": { "run_training.setup": { "total": 0.05494973299994399, "count": 1, "self": 0.05494973299994399 }, "TrainerController.start_learning": { "total": 495.1959837040001, "count": 1, "self": 0.7385380239958295, "children": { "TrainerController._reset_env": { "total": 3.346589631000029, "count": 1, "self": 3.346589631000029 }, "TrainerController.advance": { "total": 491.0043738520044, "count": 18199, "self": 0.35096168799236693, "children": { "env_step": { "total": 490.653412164012, "count": 18199, "self": 313.8691904999988, "children": { "SubprocessEnvManager._take_step": { "total": 176.4268859039979, "count": 18199, "self": 1.7823161359993946, "children": { "TorchPolicy.evaluate": { "total": 174.64456976799852, "count": 18199, "self": 174.64456976799852 } } }, "workers": { "total": 0.3573357600153031, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 493.74471048800615, "count": 18199, "is_parallel": true, "self": 231.52256468302835, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005530367000005754, "count": 1, "is_parallel": true, "self": 0.003764856000202599, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017655109998031548, "count": 10, "is_parallel": true, "self": 0.0017655109998031548 } } }, "UnityEnvironment.step": { "total": 0.041075525999985985, "count": 1, "is_parallel": true, "self": 0.00068971399991824, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004986400000461799, "count": 1, "is_parallel": true, "self": 0.0004986400000461799 }, "communicator.exchange": { "total": 0.037563213999987966, "count": 1, "is_parallel": true, "self": 0.037563213999987966 }, "steps_from_proto": { "total": 0.002323958000033599, "count": 1, "is_parallel": true, "self": 0.0004236809998019453, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019002770002316538, "count": 10, "is_parallel": true, "self": 0.0019002770002316538 } } } } } } }, "UnityEnvironment.step": { "total": 262.2221458049778, "count": 18198, "is_parallel": true, "self": 12.173885420947613, "children": { "UnityEnvironment._generate_step_input": { "total": 6.398751289006896, "count": 18198, "is_parallel": true, "self": 6.398751289006896 }, "communicator.exchange": { "total": 203.4526937330089, "count": 18198, "is_parallel": true, "self": 203.4526937330089 }, "steps_from_proto": { "total": 40.19681536201438, "count": 18198, "is_parallel": true, "self": 7.600361414982103, "children": { "_process_rank_one_or_two_observation": { "total": 32.59645394703227, "count": 181980, "is_parallel": true, "self": 32.59645394703227 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00021728000001530745, "count": 1, "self": 0.00021728000001530745, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 481.4182021960521, "count": 1008610, "is_parallel": true, "self": 23.40665227399984, "children": { "process_trajectory": { "total": 341.6719421350525, "count": 1008610, "is_parallel": true, "self": 341.07137430105286, "children": { "RLTrainer._checkpoint": { "total": 0.6005678339996621, "count": 4, "is_parallel": true, "self": 0.6005678339996621 } } }, "_update_policy": { "total": 116.33960778699975, "count": 90, "is_parallel": true, "self": 57.7406572780003, "children": { "TorchPPOOptimizer.update": { "total": 58.59895050899945, "count": 1080, "is_parallel": true, "self": 58.59895050899945 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10626491699986218, "count": 1, "self": 0.0010275269999056036, "children": { "RLTrainer._checkpoint": { "total": 0.10523738999995658, "count": 1, "self": 0.10523738999995658 } } } } } } }