Exploit Reward Shifting in Value-Based Deep-RL: Optimistic Curiosity-Based Exploration and Conservative Exploitation via Linear Reward Shaping Hao Sun 1 Lei Han 2 Rui Y ang

Aug-19-2025, 20:20:01 GMT–Neural Information Processing Systems 

In this work, we study the simple yet universally applicable case of reward shaping in value-based Deep Reinforcement Learning (DRL).