{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6387420296669006, "min": 0.6327793002128601, "max": 1.0834821462631226, "count": 81 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6084.65673828125, "min": 6062.658203125, "max": 10170.32421875, "count": 81 }, "SnowballTarget.Step.mean": { "value": 999968.0, "min": 199992.0, "max": 999968.0, "count": 81 }, "SnowballTarget.Step.sum": { "value": 999968.0, "min": 199992.0, "max": 999968.0, "count": 81 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.081706047058105, "min": 12.850728988647461, "max": 14.137797355651855, "count": 81 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2745.9326171875, "min": 1659.88916015625, "max": 2893.48779296875, "count": 81 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 81 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 6567.0, "max": 10945.0, "count": 81 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0703826310534222, "min": 0.06245207467901648, "max": 0.07407977656146292, "count": 81 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2815305242136888, "min": 0.2182903964227686, "max": 0.3703988828073146, "count": 81 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.15891914109827257, "min": 0.15105286941808813, "max": 0.213871904374922, "count": 81 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6356765643930903, "min": 0.5644757202552522, "max": 1.0519777287714882, "count": 81 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.4292995235999971e-06, "min": 1.4292995235999971e-06, "max": 0.0002406792197736, "count": 81 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 5.717198094399989e-06, "min": 5.717198094399989e-06, "max": 0.001176996107668, "count": 81 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.1004764, "min": 0.1004764, "max": 0.1802264, "count": 81 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4019056, "min": 0.4019056, "max": 0.8923320000000001, "count": 81 }, "SnowballTarget.Policy.Beta.mean": { "value": 3.377235999999996e-05, "min": 3.377235999999996e-05, "max": 0.00401329736, "count": 81 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00013508943999999983, "min": 0.00013508943999999983, "max": 0.0196273668, "count": 81 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.818181818181817, "min": 25.6, "max": 28.163636363636364, "count": 81 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1224.0, "min": 752.0, "max": 1549.0, "count": 81 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.818181818181817, "min": 25.6, "max": 28.163636363636364, "count": 81 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1224.0, "min": 752.0, "max": 1549.0, "count": 81 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 81 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 81 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1696787465", "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 --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.21.2", "end_time_seconds": "1696789911" }, "total": 2445.7466050200005, "count": 1, "self": 0.5262043780007843, "children": { "run_training.setup": { "total": 0.1078088299996125, "count": 1, "self": 0.1078088299996125 }, "TrainerController.start_learning": { "total": 2445.112591812, "count": 1, "self": 3.538825564038234, "children": { "TrainerController._reset_env": { "total": 1.6163898869999684, "count": 1, "self": 1.6163898869999684 }, "TrainerController.advance": { "total": 2439.866838730962, "count": 73338, "self": 1.6385281669158758, "children": { "env_step": { "total": 2438.2283105640463, "count": 73338, "self": 1928.7964934030601, "children": { "SubprocessEnvManager._take_step": { "total": 507.7968274750001, "count": 73338, "self": 9.076216953976655, "children": { "TorchPolicy.evaluate": { "total": 498.72061052102345, "count": 73338, "self": 498.72061052102345 } } }, "workers": { "total": 1.6349896859860564, "count": 73338, "self": 0.0, "children": { "worker_root": { "total": 2436.716611641107, "count": 73338, "is_parallel": true, "self": 1136.0442708630117, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0032841679999364715, "count": 1, "is_parallel": true, "self": 0.0008225539991144615, "children": { "_process_rank_one_or_two_observation": { "total": 0.00246161400082201, "count": 10, "is_parallel": true, "self": 0.00246161400082201 } } }, "UnityEnvironment.step": { "total": 0.13225638999983858, "count": 1, "is_parallel": true, "self": 0.0007449060003636987, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005100240000501799, "count": 1, "is_parallel": true, "self": 0.0005100240000501799 }, "communicator.exchange": { "total": 0.1286362329997246, "count": 1, "is_parallel": true, "self": 0.1286362329997246 }, "steps_from_proto": { "total": 0.0023652269997000985, "count": 1, "is_parallel": true, "self": 0.0004277669991097355, "children": { "_process_rank_one_or_two_observation": { "total": 0.001937460000590363, "count": 10, "is_parallel": true, "self": 0.001937460000590363 } } } } } } }, "UnityEnvironment.step": { "total": 1300.6723407780955, "count": 73337, "is_parallel": true, "self": 57.34887038916622, "children": { "UnityEnvironment._generate_step_input": { "total": 31.22861080296161, "count": 73337, "is_parallel": true, "self": 31.22861080296161 }, "communicator.exchange": { "total": 1015.1126084040106, "count": 73337, "is_parallel": true, "self": 1015.1126084040106 }, "steps_from_proto": { "total": 196.98225118195705, "count": 73337, "is_parallel": true, "self": 38.846725553930355, "children": { "_process_rank_one_or_two_observation": { "total": 158.1355256280267, "count": 733370, "is_parallel": true, "self": 158.1355256280267 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016458899972349172, "count": 1, "self": 0.00016458899972349172, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 2418.7039180392794, "count": 2444408, "is_parallel": true, "self": 58.017053019495506, "children": { "process_trajectory": { "total": 1285.300306515785, "count": 2444408, "is_parallel": true, "self": 1281.1163833047872, "children": { "RLTrainer._checkpoint": { "total": 4.183923210997818, "count": 21, "is_parallel": true, "self": 4.183923210997818 } } }, "_update_policy": { "total": 1075.386558503999, "count": 366, "is_parallel": true, "self": 376.61259414306323, "children": { "TorchPPOOptimizer.update": { "total": 698.7739643609357, "count": 18660, "is_parallel": true, "self": 698.7739643609357 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09037304100002075, "count": 1, "self": 0.0014845739997326746, "children": { "RLTrainer._checkpoint": { "total": 0.08888846700028807, "count": 1, "self": 0.08888846700028807 } } } } } } }