The Most Overestimated Q Value Regularization in High-Dimensional Discrete Action Spaces for Offline Reinforcement Learning

Summary

Researchers propose most overestimated Q value regularization (MQR), an offline reinforcement learning algorithm for high-dimensional discrete action spaces. MQR penalizes the action with the most overestimated Q value rather than applying uniform penalties across the whole action space. On a robotic pushing and grasping task, it reached a 96.94% clearance rate in simulation and 99.04% in real-world dense configurations, and the code is publicly available.