Skip to content

Opening book details…

Can I read Provably More Efficient Q-Learning in the One-Sided-Feedback/Full-Feedback Settings on EtoBox?

Provably More Efficient Q-Learning in the One-Sided-Feedback/Full-Feedback Settings by Gong, Xiao-Yue; Simchi-Levi, David is a scholarly article available to read on EtoBox.

What is Provably More Efficient Q-Learning in the One-Sided-Feedback/Full-Feedback Settings about?

Motivated by the episodic version of the classical inventory control problem, we propose a new Q-learning-based algorithm, Elimination-Based Half-Q-Learning (HQL), that enjoys improved efficiency over existing algorithms for a wide variety of problems in the one-sided-feedback setting. We also provide a simpler variant of the algorithm, Full-Q-Learning (FQL), for the full-feedback setting. We establish that HQL incurs $ \tilde{\mathcal{O}}(H^3\sqrt{ T})$ regret and FQL incurs $\tilde{\mathcal{O}}(H^2\sqrt{ T})$ regret, where $H$ is the length of each episode and $T$ is the total length of the horizon. The regret bounds are not affected by the possibly huge state and action space. Our numerical experiments demonstrate the superior efficiency of HQL and FQL, and the potential to combine reinforcement learning with richer feedback models.

Author
Gong, Xiao-Yue; Simchi-Levi, David
Published
2020
Language
EN

More by Gong, Xiao-Yue; Simchi-Levi, David

Browse all works by Gong, Xiao-Yue; Simchi-Levi, David