← Search

Han-Dong Lim

2 accepted papers

2024

Regularized Q-Learning

NeurIPS 2024poster

Q-learning is widely used algorithm in reinforcement learning (RL) community. Under the lookup table setting, its convergence is well established. However, its behavior is known to be unstable with the linear function approximation case. This paper develops a new Q-learning algorithm, called RegQ, t…

Cited by 8SourcePDFScholar