{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.817284107208252, "min": 0.817284107208252, "max": 2.880920886993408, "count": 40 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8342.8359375, "min": 7850.9345703125, "max": 29408.44140625, "count": 40 }, "SnowballTarget.Step.mean": { "value": 399992.0, "min": 9952.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Step.sum": { "value": 399992.0, "min": 9952.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.455543518066406, "min": 0.16437116265296936, "max": 12.516606330871582, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2428.8310546875, "min": 31.888004302978516, "max": 2565.245849609375, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.40909090909091, "min": 3.0681818181818183, "max": 24.62962962962963, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1074.0, "min": 135.0, "max": 1352.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.40909090909091, "min": 3.0681818181818183, "max": 24.62962962962963, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1074.0, "min": 135.0, "max": 1352.0, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.048369509726077974, "min": 0.04168043035429482, "max": 0.05462529299856054, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.09673901945215595, "min": 0.08336086070858964, "max": 0.16050351717864283, "count": 40 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2216655766847087, "min": 0.11104704931323581, "max": 0.3173592958380195, "count": 40 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.4433311533694174, "min": 0.22209409862647161, "max": 0.9511543643825195, "count": 40 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 4.716098428000004e-06, "min": 4.716098428000004e-06, "max": 0.000295116001628, "count": 40 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 9.432196856000007e-06, "min": 9.432196856000007e-06, "max": 0.000820998026334, "count": 40 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10235799999999999, "min": 0.10235799999999999, "max": 0.24755800000000003, "count": 40 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.20471599999999998, "min": 0.20471599999999998, "max": 0.710499, "count": 40 }, "SnowballTarget.Policy.Beta.mean": { "value": 8.844280000000006e-05, "min": 8.844280000000006e-05, "max": 0.004918762799999999, "count": 40 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00017688560000000012, "min": 0.00017688560000000012, "max": 0.013685933400000001, "count": 40 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1741165153", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1741165931" }, "total": 777.5172890659999, "count": 1, "self": 0.4440142489995651, "children": { "run_training.setup": { "total": 0.027918905000205996, "count": 1, "self": 0.027918905000205996 }, "TrainerController.start_learning": { "total": 777.0453559120001, "count": 1, "self": 0.6197974060189608, "children": { "TrainerController._reset_env": { "total": 2.5239070659999925, "count": 1, "self": 2.5239070659999925 }, "TrainerController.advance": { "total": 773.8131043129817, "count": 36392, "self": 0.65870621302156, "children": { "env_step": { "total": 583.1726520469663, "count": 36392, "self": 441.2143017209564, "children": { "SubprocessEnvManager._take_step": { "total": 141.5693021510324, "count": 36392, "self": 2.454410039082859, "children": { "TorchPolicy.evaluate": { "total": 139.11489211194953, "count": 36392, "self": 139.11489211194953 } } }, "workers": { "total": 0.3890481749774608, "count": 36392, "self": 0.0, "children": { "worker_root": { "total": 774.5863322520372, "count": 36392, "is_parallel": true, "self": 387.2644585690505, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026819419999810634, "count": 1, "is_parallel": true, "self": 0.0007616200002757978, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019203219997052656, "count": 10, "is_parallel": true, "self": 0.0019203219997052656 } } }, "UnityEnvironment.step": { "total": 0.03990929000019605, "count": 1, "is_parallel": true, "self": 0.0005508150002242473, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040232800006378966, "count": 1, "is_parallel": true, "self": 0.00040232800006378966 }, "communicator.exchange": { "total": 0.037069298999995226, "count": 1, "is_parallel": true, "self": 0.037069298999995226 }, "steps_from_proto": { "total": 0.0018868479999127885, "count": 1, "is_parallel": true, "self": 0.0003569929999684973, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015298549999442912, "count": 10, "is_parallel": true, "self": 0.0015298549999442912 } } } } } } }, "UnityEnvironment.step": { "total": 387.32187368298673, "count": 36391, "is_parallel": true, "self": 18.683283434951363, "children": { "UnityEnvironment._generate_step_input": { "total": 10.469411926015937, "count": 36391, "is_parallel": true, "self": 10.469411926015937 }, "communicator.exchange": { "total": 297.7430077330332, "count": 36391, "is_parallel": true, "self": 297.7430077330332 }, "steps_from_proto": { "total": 60.426170588986224, "count": 36391, "is_parallel": true, "self": 10.488236471951268, "children": { "_process_rank_one_or_two_observation": { "total": 49.937934117034956, "count": 363910, "is_parallel": true, "self": 49.937934117034956 } } } } } } } } } } }, "trainer_advance": { "total": 189.9817460529939, "count": 36392, "self": 0.7933764399979282, "children": { "process_trajectory": { "total": 53.413764952994825, "count": 36392, "self": 52.541130710995276, "children": { "RLTrainer._checkpoint": { "total": 0.872634241999549, "count": 8, "self": 0.872634241999549 } } }, "_update_policy": { "total": 135.77460466000116, "count": 90, "self": 74.23403170601136, "children": { "TorchPPOOptimizer.update": { "total": 61.540572953989795, "count": 4587, "self": 61.540572953989795 } } } } } } }, "trainer_threads": { "total": 8.929996511142235e-07, "count": 1, "self": 8.929996511142235e-07 }, "TrainerController._save_models": { "total": 0.08854623399975026, "count": 1, "self": 0.0012196369998491718, "children": { "RLTrainer._checkpoint": { "total": 0.08732659699990108, "count": 1, "self": 0.08732659699990108 } } } } } } }