Constrained Reinforcement Learning with Smoothed Log Barrier Function

arXiv:2403.14508v1 Announce Type: new
Abstract: Reinforcement Learning (RL) has been widely applied to many control tasks and substantially improved the performances compared to conventional control methods in many domains where the reward function is well defined. However, for many real-world problems, it is often more convenient to formulate optimization problems in terms of rewards and constraints simultaneously. Optimizing such constrained problems via reward shaping can be difficult as it requires tedious manual tuning of reward functions with several interacting terms. …

abstract arxiv control cs.ai cs.lg cs.sy domains eess.sy function however optimization performances reinforcement reinforcement learning tasks terms type world