{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6866129040718079, "min": 0.6866129040718079, "max": 2.853877544403076, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6525.56884765625, "min": 6525.56884765625, "max": 29132.3828125, "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": 12.990679740905762, "min": 0.45783981680870056, "max": 12.990679740905762, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2533.1826171875, "min": 88.8209228515625, "max": 2618.18359375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06691247674048188, "min": 0.06000601548847614, "max": 0.07770210306854079, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26764990696192753, "min": 0.2575401519470866, "max": 0.37759528810948173, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2146731256416031, "min": 0.12147532986915288, "max": 0.29513194321417335, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8586925025664124, "min": 0.4859013194766115, "max": 1.4756597160708669, "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": 26.068181818181817, "min": 3.772727272727273, "max": 26.068181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1147.0, "min": 166.0, "max": 1397.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.068181818181817, "min": 3.772727272727273, "max": 26.068181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1147.0, "min": 166.0, "max": 1397.0, "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": "1754317021", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1754317441" }, "total": 420.0381634790001, "count": 1, "self": 0.6130719580000914, "children": { "run_training.setup": { "total": 0.02762943599987011, "count": 1, "self": 0.02762943599987011 }, "TrainerController.start_learning": { "total": 419.39746208500014, "count": 1, "self": 0.3455291270101952, "children": { "TrainerController._reset_env": { "total": 3.275865850999935, "count": 1, "self": 3.275865850999935 }, "TrainerController.advance": { "total": 415.69602424998993, "count": 18192, "self": 0.3706213749503604, "children": { "env_step": { "total": 298.37872758000253, "count": 18192, "self": 229.96664159703482, "children": { "SubprocessEnvManager._take_step": { "total": 68.21523186696027, "count": 18192, "self": 1.2070050829729553, "children": { "TorchPolicy.evaluate": { "total": 67.00822678398731, "count": 18192, "self": 67.00822678398731 } } }, "workers": { "total": 0.19685411600744374, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 418.0379529290112, "count": 18192, "is_parallel": true, "self": 215.6557529030115, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005650754000043889, "count": 1, "is_parallel": true, "self": 0.0036516600000595645, "children": { "_process_rank_one_or_two_observation": { "total": 0.001999093999984325, "count": 10, "is_parallel": true, "self": 0.001999093999984325 } } }, "UnityEnvironment.step": { "total": 0.03480870099997446, "count": 1, "is_parallel": true, "self": 0.000566767999998774, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003896989999248035, "count": 1, "is_parallel": true, "self": 0.0003896989999248035 }, "communicator.exchange": { "total": 0.0317558189999545, "count": 1, "is_parallel": true, "self": 0.0317558189999545 }, "steps_from_proto": { "total": 0.0020964150000963855, "count": 1, "is_parallel": true, "self": 0.00040056600005300425, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016958490000433812, "count": 10, "is_parallel": true, "self": 0.0016958490000433812 } } } } } } }, "UnityEnvironment.step": { "total": 202.38220002599974, "count": 18191, "is_parallel": true, "self": 9.712377696067279, "children": { "UnityEnvironment._generate_step_input": { "total": 5.4473396909688745, "count": 18191, "is_parallel": true, "self": 5.4473396909688745 }, "communicator.exchange": { "total": 155.65307796797333, "count": 18191, "is_parallel": true, "self": 155.65307796797333 }, "steps_from_proto": { "total": 31.569404670990252, "count": 18191, "is_parallel": true, "self": 5.523973820992296, "children": { "_process_rank_one_or_two_observation": { "total": 26.045430849997956, "count": 181910, "is_parallel": true, "self": 26.045430849997956 } } } } } } } } } } }, "trainer_advance": { "total": 116.94667529503704, "count": 18192, "self": 0.4045793480172506, "children": { "process_trajectory": { "total": 26.011600184020608, "count": 18192, "self": 25.604205475020308, "children": { "RLTrainer._checkpoint": { "total": 0.4073947090003003, "count": 4, "self": 0.4073947090003003 } } }, "_update_policy": { "total": 90.53049576299918, "count": 90, "self": 38.09753823799383, "children": { "TorchPPOOptimizer.update": { "total": 52.43295752500535, "count": 4587, "self": 52.43295752500535 } } } } } } }, "trainer_threads": { "total": 1.0160001693293452e-06, "count": 1, "self": 1.0160001693293452e-06 }, "TrainerController._save_models": { "total": 0.08004184099991107, "count": 1, "self": 0.0008365480002794357, "children": { "RLTrainer._checkpoint": { "total": 0.07920529299963164, "count": 1, "self": 0.07920529299963164 } } } } } } }