{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0398240089416504, "min": 1.0398240089416504, "max": 2.866269826889038, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10683.15234375, "min": 10683.15234375, "max": 29353.46875, "count": 10 }, "SnowballTarget.Step.mean": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3127219676971436, "min": 0.2507854402065277, "max": 2.3127219676971436, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 471.7952880859375, "min": 48.652374267578125, "max": 471.7952880859375, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06389200429628403, "min": 0.062248186127844204, "max": 0.07397499721789477, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3194600214814201, "min": 0.24899274451137682, "max": 0.36987498608947383, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.15586212218976486, "min": 0.07571165587504247, "max": 0.15882034897804262, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7793106109488244, "min": 0.3028466235001699, "max": 0.7941017448902131, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 0.00015823204725600002, "min": 0.00015823204725600002, "max": 0.000291882002706, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0007911602362800001, "min": 0.0006923281692239998, "max": 0.00138516003828, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.15274400000000002, "min": 0.15274400000000002, "max": 0.19729400000000002, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.7637200000000001, "min": 0.630776, "max": 0.96172, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0026419256000000005, "min": 0.0026419256000000005, "max": 0.0048649706, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.013209628000000003, "min": 0.0115557224, "max": 0.023089828, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 22.618181818181817, "min": 4.0227272727272725, "max": 22.618181818181817, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1244.0, "min": 177.0, "max": 1244.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 22.618181818181817, "min": 4.0227272727272725, "max": 22.618181818181817, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1244.0, "min": 177.0, "max": 1244.0, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677691188", "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 --force", "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": "1677691448" }, "total": 260.20794596199994, "count": 1, "self": 0.006016890999944735, "children": { "run_training.setup": { "total": 0.10764882199998738, "count": 1, "self": 0.10764882199998738 }, "TrainerController.start_learning": { "total": 260.094280249, "count": 1, "self": 0.8553450709955541, "children": { "TrainerController._reset_env": { "total": 7.026263712999935, "count": 1, "self": 7.026263712999935 }, "TrainerController.advance": { "total": 252.09290672800478, "count": 10049, "self": 0.16911708899385758, "children": { "env_step": { "total": 251.92378963901092, "count": 10049, "self": 172.526267241009, "children": { "SubprocessEnvManager._take_step": { "total": 79.24467633799225, "count": 10049, "self": 0.9792645899973422, "children": { "TorchPolicy.evaluate": { "total": 78.2654117479949, "count": 10049, "self": 17.849673215000962, "children": { "TorchPolicy.sample_actions": { "total": 60.41573853299394, "count": 10049, "self": 60.41573853299394 } } } } }, "workers": { "total": 0.15284606000966505, "count": 10048, "self": 0.0, "children": { "worker_root": { "total": 258.6776240289953, "count": 10048, "is_parallel": true, "self": 128.7869458539932, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00216344599994045, "count": 1, "is_parallel": true, "self": 0.0007475899999462854, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014158559999941644, "count": 10, "is_parallel": true, "self": 0.0014158559999941644 } } }, "UnityEnvironment.step": { "total": 0.07644220099996346, "count": 1, "is_parallel": true, "self": 0.0005894959999750427, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004214379999893936, "count": 1, "is_parallel": true, "self": 0.0004214379999893936 }, "communicator.exchange": { "total": 0.07340030000000297, "count": 1, "is_parallel": true, "self": 0.07340030000000297 }, "steps_from_proto": { "total": 0.0020309669999960533, "count": 1, "is_parallel": true, "self": 0.00046088700003110716, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015700799999649462, "count": 10, "is_parallel": true, "self": 0.0015700799999649462 } } } } } } }, "UnityEnvironment.step": { "total": 129.8906781750021, "count": 10047, "is_parallel": true, "self": 5.248739870997497, "children": { "UnityEnvironment._generate_step_input": { "total": 2.8828429830062987, "count": 10047, "is_parallel": true, "self": 2.8828429830062987 }, "communicator.exchange": { "total": 104.55522575800114, "count": 10047, "is_parallel": true, "self": 104.55522575800114 }, "steps_from_proto": { "total": 17.20386956299717, "count": 10047, "is_parallel": true, "self": 3.7718461520039455, "children": { "_process_rank_one_or_two_observation": { "total": 13.432023410993224, "count": 100470, "is_parallel": true, "self": 13.432023410993224 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0009472699998696044, "count": 1, "self": 0.0009472699998696044, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 250.73056016997555, "count": 220460, "is_parallel": true, "self": 5.610790782031017, "children": { "process_trajectory": { "total": 142.3387238549443, "count": 220460, "is_parallel": true, "self": 139.62837210494422, "children": { "RLTrainer._checkpoint": { "total": 2.710351750000086, "count": 10, "is_parallel": true, "self": 2.710351750000086 } } }, "_update_policy": { "total": 102.78104553300022, "count": 50, "is_parallel": true, "self": 36.61635267699944, "children": { "TorchPPOOptimizer.update": { "total": 66.16469285600078, "count": 2547, "is_parallel": true, "self": 66.16469285600078 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11881746699987161, "count": 1, "self": 0.0014952389997233695, "children": { "RLTrainer._checkpoint": { "total": 0.11732222800014824, "count": 1, "self": 0.11732222800014824 } } } } } } }