Constrained Reinforcement Learning with Smoothed Log Barrier Function

no code implementations • 21 Mar 2024 • Baohe Zhang, Yuan Zhang, Lilli Frison, Thomas Brox, Joschka Bödecker

However, for many real-world problems, it is often more convenient to formulate optimization problems in terms of rewards and constraints simultaneously.

reinforcement-learning Reinforcement Learning (RL)