{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.7313357591629028, "min": 1.7127974033355713, "max": 2.8897507190704346, "count": 33 }, "SnowballTarget.Policy.Entropy.sum": { "value": 5789.5869140625, "min": 3986.89013671875, "max": 9949.412109375, "count": 33 }, "SnowballTarget.Step.mean": { "value": 98992.0, "min": 2968.0, "max": 98992.0, "count": 33 }, "SnowballTarget.Step.sum": { "value": 98992.0, "min": 2968.0, "max": 98992.0, "count": 33 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 8.963665008544922, "min": 0.10108505934476852, "max": 8.963665008544922, "count": 33 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 457.14691162109375, "min": 4.144487380981445, "max": 457.14691162109375, "count": 33 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 33 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 4378.0, "min": 2189.0, "max": 4378.0, "count": 33 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06821459705037448, "min": 0.056161290620437676, "max": 0.08300557076090984, "count": 33 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.13642919410074897, "min": 0.056161290620437676, "max": 0.16539050954138385, "count": 33 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.24401900318323397, "min": 0.09071497918636191, "max": 0.3442269283182481, "count": 33 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.48803800636646794, "min": 0.09071497918636191, "max": 0.6462239623069763, "count": 33 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 6.564097812000004e-06, "min": 6.564097812000004e-06, "max": 0.000293664002112, "count": 33 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.3128195624000008e-05, "min": 1.3128195624000008e-05, "max": 0.000554328015224, "count": 33 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10218800000000001, "min": 0.10218800000000001, "max": 0.19788800000000004, "count": 33 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.20437600000000003, "min": 0.10548800000000003, "max": 0.38477600000000006, "count": 33 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00011918120000000008, "min": 0.00011918120000000008, "max": 0.0048946112, "count": 33 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00023836240000000016, "min": 0.00023836240000000016, "max": 0.0092403224, "count": 33 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 18.714285714285715, "min": 2.727272727272727, "max": 19.09090909090909, "count": 33 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 393.0, "min": 30.0, "max": 406.0, "count": 33 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 18.714285714285715, "min": 2.727272727272727, "max": 19.09090909090909, "count": 33 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 393.0, "min": 30.0, "max": 406.0, "count": 33 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1694866240", "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 --force", "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": "1694866533" }, "total": 292.990521747, "count": 1, "self": 0.5265611539998645, "children": { "run_training.setup": { "total": 0.05236504100003003, "count": 1, "self": 0.05236504100003003 }, "TrainerController.start_learning": { "total": 292.4115955520001, "count": 1, "self": 0.44906356599926767, "children": { "TrainerController._reset_env": { "total": 1.0040535400000863, "count": 1, "self": 1.0040535400000863 }, "TrainerController.advance": { "total": 290.8054328090011, "count": 9117, "self": 0.2306598060079068, "children": { "env_step": { "total": 290.5747730029932, "count": 9117, "self": 232.47457808300373, "children": { "SubprocessEnvManager._take_step": { "total": 57.89622661499152, "count": 9117, "self": 1.3152518990029876, "children": { "TorchPolicy.evaluate": { "total": 56.58097471598853, "count": 9117, "self": 56.58097471598853 } } }, "workers": { "total": 0.20396830499794305, "count": 9117, "self": 0.0, "children": { "worker_root": { "total": 291.25662964599746, "count": 9117, "is_parallel": true, "self": 123.46436249100248, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002140725000117527, "count": 1, "is_parallel": true, "self": 0.0006109940006808756, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015297309994366515, "count": 10, "is_parallel": true, "self": 0.0015297309994366515 } } }, "UnityEnvironment.step": { "total": 0.05819984600020689, "count": 1, "is_parallel": true, "self": 0.0005269930002214096, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045711899997513683, "count": 1, "is_parallel": true, "self": 0.00045711899997513683 }, "communicator.exchange": { "total": 0.05370774099992559, "count": 1, "is_parallel": true, "self": 0.05370774099992559 }, "steps_from_proto": { "total": 0.0035079930000847526, "count": 1, "is_parallel": true, "self": 0.0015020980004010198, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020058949996837327, "count": 10, "is_parallel": true, "self": 0.0020058949996837327 } } } } } } }, "UnityEnvironment.step": { "total": 167.792267154995, "count": 9116, "is_parallel": true, "self": 6.9609572139977445, "children": { "UnityEnvironment._generate_step_input": { "total": 3.7738556229912774, "count": 9116, "is_parallel": true, "self": 3.7738556229912774 }, "communicator.exchange": { "total": 132.94538953800497, "count": 9116, "is_parallel": true, "self": 132.94538953800497 }, "steps_from_proto": { "total": 24.112064780000992, "count": 9116, "is_parallel": true, "self": 4.669569226967724, "children": { "_process_rank_one_or_two_observation": { "total": 19.442495553033268, "count": 91160, "is_parallel": true, "self": 19.442495553033268 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.913099974146462e-05, "count": 1, "self": 4.913099974146462e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 288.7915713470172, "count": 225280, "is_parallel": true, "self": 5.8745017050594015, "children": { "process_trajectory": { "total": 129.6866089769578, "count": 225280, "is_parallel": true, "self": 129.12433366295772, "children": { "RLTrainer._checkpoint": { "total": 0.5622753140000896, "count": 2, "is_parallel": true, "self": 0.5622753140000896 } } }, "_update_policy": { "total": 153.230460665, "count": 45, "is_parallel": true, "self": 50.57828893099645, "children": { "TorchPPOOptimizer.update": { "total": 102.65217173400356, "count": 2292, "is_parallel": true, "self": 102.65217173400356 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15299650599990855, "count": 1, "self": 0.0013579679998656502, "children": { "RLTrainer._checkpoint": { "total": 0.1516385380000429, "count": 1, "self": 0.1516385380000429 } } } } } } }