{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7899582386016846, "min": 0.7675452828407288, "max": 2.8903439044952393, "count": 200 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8133.41015625, "min": 7294.75048828125, "max": 29570.138671875, "count": 200 }, "SnowballTarget.Step.mean": { "value": 1999992.0, "min": 9952.0, "max": 1999992.0, "count": 200 }, "SnowballTarget.Step.sum": { "value": 1999992.0, "min": 9952.0, "max": 1999992.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.199864387512207, "min": -0.09513217210769653, "max": 14.263813972473145, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2910.97216796875, "min": -18.45564079284668, "max": 2924.081787109375, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.90909090909091, "min": 2.6363636363636362, "max": 28.386363636363637, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1535.0, "min": 116.0, "max": 1545.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.90909090909091, "min": 2.6363636363636362, "max": 28.386363636363637, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1535.0, "min": 116.0, "max": 1545.0, "count": 200 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.023605609668884427, "min": 0.015988392693398055, "max": 0.029666174179874362, "count": 191 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.023605609668884427, "min": 0.015988392693398055, "max": 0.029666174179874362, "count": 191 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.15311876356601714, "min": 0.0945033897459507, "max": 0.3203707575798035, "count": 191 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.15311876356601714, "min": 0.0945033897459507, "max": 0.3203707575798035, "count": 191 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 5.844998051999849e-07, "min": 5.844998051999849e-07, "max": 0.0002983632005456, "count": 191 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 5.844998051999849e-07, "min": 5.844998051999849e-07, "max": 0.0002983632005456, "count": 191 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.1001948, "min": 0.1001948, "max": 0.1994544, "count": 191 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.1001948, "min": 0.1001948, "max": 0.1994544, "count": 191 }, "SnowballTarget.Policy.Beta.mean": { "value": 2.94605199999995e-05, "min": 2.94605199999995e-05, "max": 0.00994549456, "count": 191 }, "SnowballTarget.Policy.Beta.sum": { "value": 2.94605199999995e-05, "min": 2.94605199999995e-05, "max": 0.00994549456, "count": 191 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1756744182", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/hungchan/miniconda3/envs/rl_31012/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1756746217" }, "total": 2034.945576685, "count": 1, "self": 0.22280772400017668, "children": { "run_training.setup": { "total": 0.014937456999859933, "count": 1, "self": 0.014937456999859933 }, "TrainerController.start_learning": { "total": 2034.707831504, "count": 1, "self": 2.090146202893038, "children": { "TrainerController._reset_env": { "total": 1.483924055999978, "count": 1, "self": 1.483924055999978 }, "TrainerController.advance": { "total": 2031.0903070571067, "count": 181864, "self": 1.9976428490458602, "children": { "env_step": { "total": 1407.2546968289648, "count": 181864, "self": 1074.0869557420808, "children": { "SubprocessEnvManager._take_step": { "total": 331.8149656088565, "count": 181864, "self": 6.398366203912019, "children": { "TorchPolicy.evaluate": { "total": 325.41659940494446, "count": 181864, "self": 325.41659940494446 } } }, "workers": { "total": 1.3527754780275245, "count": 181864, "self": 0.0, "children": { "worker_root": { "total": 2031.6684058839683, "count": 181864, "is_parallel": true, "self": 1096.1810742638997, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009950090000074852, "count": 1, "is_parallel": true, "self": 0.0002717519998896023, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007232570001178829, "count": 10, "is_parallel": true, "self": 0.0007232570001178829 } } }, "UnityEnvironment.step": { "total": 0.015677181000000928, "count": 1, "is_parallel": true, "self": 0.00022112700025900267, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00016523799990864063, "count": 1, "is_parallel": true, "self": 0.00016523799990864063 }, "communicator.exchange": { "total": 0.01464410699986729, "count": 1, "is_parallel": true, "self": 0.01464410699986729 }, "steps_from_proto": { "total": 0.0006467089999659947, "count": 1, "is_parallel": true, "self": 0.0001443310000013298, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005023779999646649, "count": 10, "is_parallel": true, "self": 0.0005023779999646649 } } } } } } }, "UnityEnvironment.step": { "total": 935.4873316200685, "count": 181863, "is_parallel": true, "self": 35.60573260907904, "children": { "UnityEnvironment._generate_step_input": { "total": 20.04231953900762, "count": 181863, "is_parallel": true, "self": 20.04231953900762 }, "communicator.exchange": { "total": 769.2791198750026, "count": 181863, "is_parallel": true, "self": 769.2791198750026 }, "steps_from_proto": { "total": 110.56015959697925, "count": 181863, "is_parallel": true, "self": 22.2171321491287, "children": { "_process_rank_one_or_two_observation": { "total": 88.34302744785055, "count": 1818630, "is_parallel": true, "self": 88.34302744785055 } } } } } } } } } } }, "trainer_advance": { "total": 621.837967379096, "count": 181864, "self": 2.5286666780179985, "children": { "process_trajectory": { "total": 135.94426321507808, "count": 181864, "self": 133.73425045007662, "children": { "RLTrainer._checkpoint": { "total": 2.2100127650014656, "count": 40, "self": 2.2100127650014656 } } }, "_update_policy": { "total": 483.3650374859999, "count": 191, "self": 388.68595532199015, "children": { "TorchPPOOptimizer.update": { "total": 94.67908216400974, "count": 9550, "self": 94.67908216400974 } } } } } } }, "trainer_threads": { "total": 6.63000264466973e-07, "count": 1, "self": 6.63000264466973e-07 }, "TrainerController._save_models": { "total": 0.043453525000131776, "count": 1, "self": 0.00045814800023435964, "children": { "RLTrainer._checkpoint": { "total": 0.04299537699989742, "count": 1, "self": 0.04299537699989742 } } } } } } }