2 papers
cs.LG2025
Maximum Total Correlation Reinforcement Learning
Bang You, Puze Liu, Huaping Liu +2
Simplicity is a powerful inductive bias. In reinforcement learning, regularization is used for simpler policies, data augmentation for simpler representations, and sparse reward fu…
cs.LG2025
Trajectory Entropy Reinforcement Learning for Predictable and Robust Control
Bang You, Chenxu Wang, Huaping Liu
Simplicity is a critical inductive bias for designing data-driven controllers, especially when robustness is important. Despite the impressive results of deep reinforcement learnin…