{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7683492302894592, "min": 0.7600694894790649, "max": 2.8741514682769775, "count": 30 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7885.568359375, "min": 7340.7509765625, "max": 29402.568359375, "count": 30 }, "SnowballTarget.Step.mean": { "value": 299968.0, "min": 9952.0, "max": 299968.0, "count": 30 }, "SnowballTarget.Step.sum": { "value": 299968.0, "min": 9952.0, "max": 299968.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.998841285705566, "min": 0.19241949915885925, "max": 12.998841285705566, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2651.763671875, "min": 37.329383850097656, "max": 2654.54150390625, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06713153425964764, "min": 0.06284714500076255, "max": 0.07652197535313177, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3356576712982382, "min": 0.2513885800030502, "max": 0.3736244197375616, "count": 30 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2094671048370062, "min": 0.10411210189683034, "max": 0.30990612353472147, "count": 30 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.047335524185031, "min": 0.4164484075873214, "max": 1.4703391290762844, "count": 30 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 5.288098237333331e-06, "min": 5.288098237333331e-06, "max": 0.00029458800180399996, "count": 30 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.6440491186666655e-05, "min": 2.6440491186666655e-05, "max": 0.0014234400255199997, "count": 30 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10176266666666667, "min": 0.10176266666666667, "max": 0.198196, "count": 30 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5088133333333333, "min": 0.42025066666666666, "max": 0.97448, "count": 30 }, "SnowballTarget.Policy.Beta.mean": { "value": 9.795706666666662e-05, "min": 9.795706666666662e-05, "max": 0.0049099804000000006, "count": 30 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0004897853333333331, "min": 0.0004897853333333331, "max": 0.023726551999999998, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.581818181818182, "min": 2.5454545454545454, "max": 25.886363636363637, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1407.0, "min": 112.0, "max": 1407.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.581818181818182, "min": 2.5454545454545454, "max": 25.886363636363637, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1407.0, "min": 112.0, "max": 1407.0, "count": 30 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678244734", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1678245418" }, "total": 684.2784943450001, "count": 1, "self": 0.4438370200002737, "children": { "run_training.setup": { "total": 0.11171971699991445, "count": 1, "self": 0.11171971699991445 }, "TrainerController.start_learning": { "total": 683.7229376079999, "count": 1, "self": 0.8522606479788237, "children": { "TrainerController._reset_env": { "total": 9.05685581199998, "count": 1, "self": 9.05685581199998 }, "TrainerController.advance": { "total": 673.6957560500209, "count": 27342, "self": 0.42919146802682917, "children": { "env_step": { "total": 673.2665645819941, "count": 27342, "self": 465.44963245902227, "children": { "SubprocessEnvManager._take_step": { "total": 207.42095395898878, "count": 27342, "self": 2.2939976459615536, "children": { "TorchPolicy.evaluate": { "total": 205.12695631302722, "count": 27342, "self": 46.24493992701673, "children": { "TorchPolicy.sample_actions": { "total": 158.8820163860105, "count": 27342, "self": 158.8820163860105 } } } } }, "workers": { "total": 0.3959781639830453, "count": 27342, "self": 0.0, "children": { "worker_root": { "total": 681.435375669992, "count": 27342, "is_parallel": true, "self": 327.8167077269936, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005358617999945636, "count": 1, "is_parallel": true, "self": 0.003958468000064386, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014001499998812506, "count": 10, "is_parallel": true, "self": 0.0014001499998812506 } } }, "UnityEnvironment.step": { "total": 0.08134832899986577, "count": 1, "is_parallel": true, "self": 0.000558968999712306, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00035829400007969525, "count": 1, "is_parallel": true, "self": 0.00035829400007969525 }, "communicator.exchange": { "total": 0.07860995700002604, "count": 1, "is_parallel": true, "self": 0.07860995700002604 }, "steps_from_proto": { "total": 0.001821109000047727, "count": 1, "is_parallel": true, "self": 0.0003753129999495286, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014457960000981984, "count": 10, "is_parallel": true, "self": 0.0014457960000981984 } } } } } } }, "UnityEnvironment.step": { "total": 353.6186679429984, "count": 27341, "is_parallel": true, "self": 14.410563015999742, "children": { "UnityEnvironment._generate_step_input": { "total": 7.738144318989953, "count": 27341, "is_parallel": true, "self": 7.738144318989953 }, "communicator.exchange": { "total": 285.91918032102194, "count": 27341, "is_parallel": true, "self": 285.91918032102194 }, "steps_from_proto": { "total": 45.550780286986765, "count": 27341, "is_parallel": true, "self": 9.85456692895491, "children": { "_process_rank_one_or_two_observation": { "total": 35.696213358031855, "count": 273410, "is_parallel": true, "self": 35.696213358031855 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00039866600013738207, "count": 1, "self": 0.00039866600013738207, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 668.8792041659781, "count": 593637, "is_parallel": true, "self": 15.004068415982147, "children": { "process_trajectory": { "total": 380.84772338199673, "count": 593637, "is_parallel": true, "self": 378.36171301299646, "children": { "RLTrainer._checkpoint": { "total": 2.486010369000269, "count": 6, "is_parallel": true, "self": 2.486010369000269 } } }, "_update_policy": { "total": 273.0274123679992, "count": 136, "is_parallel": true, "self": 95.3609779240087, "children": { "TorchPPOOptimizer.update": { "total": 177.6664344439905, "count": 6933, "is_parallel": true, "self": 177.6664344439905 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1176664320000782, "count": 1, "self": 0.0008412150000367546, "children": { "RLTrainer._checkpoint": { "total": 0.11682521700004145, "count": 1, "self": 0.11682521700004145 } } } } } } }