{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7528964281082153, "min": 0.7528964281082153, "max": 2.8509700298309326, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7155.52783203125, "min": 7155.52783203125, "max": 29102.703125, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.956405639648438, "min": 0.29787591099739075, "max": 12.956405639648438, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2526.4990234375, "min": 57.787925720214844, "max": 2640.55517578125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0706908948757736, "min": 0.06312227231603317, "max": 0.07285380519162715, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2827635795030944, "min": 0.2557500552445394, "max": 0.3531862621089471, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1779409669266612, "min": 0.12655679031512607, "max": 0.28504161676939793, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7117638677066448, "min": 0.5062271612605043, "max": 1.4252080838469896, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.613636363636363, "min": 3.590909090909091, "max": 25.89090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1127.0, "min": 158.0, "max": 1424.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.613636363636363, "min": 3.590909090909091, "max": 25.89090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1127.0, "min": 158.0, "max": 1424.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1756042176", "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", "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": "1756042919" }, "total": 743.43093095, "count": 1, "self": 0.692404420999992, "children": { "run_training.setup": { "total": 0.05675258299993402, "count": 1, "self": 0.05675258299993402 }, "TrainerController.start_learning": { "total": 742.681773946, "count": 1, "self": 0.908091301991135, "children": { "TrainerController._reset_env": { "total": 5.091291355000067, "count": 1, "self": 5.091291355000067 }, "TrainerController.advance": { "total": 736.5825437700089, "count": 18192, "self": 0.9466520380024122, "children": { "env_step": { "total": 522.316609806976, "count": 18192, "self": 443.059950774983, "children": { "SubprocessEnvManager._take_step": { "total": 78.70692454199889, "count": 18192, "self": 3.5555905599931066, "children": { "TorchPolicy.evaluate": { "total": 75.15133398200578, "count": 18192, "self": 75.15133398200578 } } }, "workers": { "total": 0.5497344899940799, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 739.5420104680068, "count": 18192, "is_parallel": true, "self": 361.1152129420086, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008963831999835747, "count": 1, "is_parallel": true, "self": 0.005890254999940225, "children": { "_process_rank_one_or_two_observation": { "total": 0.003073576999895522, "count": 10, "is_parallel": true, "self": 0.003073576999895522 } } }, "UnityEnvironment.step": { "total": 0.1300518049999937, "count": 1, "is_parallel": true, "self": 0.0008425529999840364, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005747320001319167, "count": 1, "is_parallel": true, "self": 0.0005747320001319167 }, "communicator.exchange": { "total": 0.12612553600001775, "count": 1, "is_parallel": true, "self": 0.12612553600001775 }, "steps_from_proto": { "total": 0.0025089839998599928, "count": 1, "is_parallel": true, "self": 0.00048591900008432276, "children": { "_process_rank_one_or_two_observation": { "total": 0.00202306499977567, "count": 10, "is_parallel": true, "self": 0.00202306499977567 } } } } } } }, "UnityEnvironment.step": { "total": 378.42679752599815, "count": 18191, "is_parallel": true, "self": 17.365708915024925, "children": { "UnityEnvironment._generate_step_input": { "total": 9.253897432972508, "count": 18191, "is_parallel": true, "self": 9.253897432972508 }, "communicator.exchange": { "total": 300.10134320500265, "count": 18191, "is_parallel": true, "self": 300.10134320500265 }, "steps_from_proto": { "total": 51.70584797299807, "count": 18191, "is_parallel": true, "self": 10.591154011963454, "children": { "_process_rank_one_or_two_observation": { "total": 41.11469396103462, "count": 181910, "is_parallel": true, "self": 41.11469396103462 } } } } } } } } } } }, "trainer_advance": { "total": 213.3192819250305, "count": 18192, "self": 1.2155570840138807, "children": { "process_trajectory": { "total": 43.26120213201739, "count": 18192, "self": 42.60721722101766, "children": { "RLTrainer._checkpoint": { "total": 0.6539849109997249, "count": 4, "self": 0.6539849109997249 } } }, "_update_policy": { "total": 168.84252270899924, "count": 90, "self": 57.879228728990256, "children": { "TorchPPOOptimizer.update": { "total": 110.96329398000898, "count": 4587, "self": 110.96329398000898 } } } } } } }, "trainer_threads": { "total": 1.651000275160186e-06, "count": 1, "self": 1.651000275160186e-06 }, "TrainerController._save_models": { "total": 0.09984586799964745, "count": 1, "self": 0.001943943999322073, "children": { "RLTrainer._checkpoint": { "total": 0.09790192400032538, "count": 1, "self": 0.09790192400032538 } } } } } } }