LGAIMar 1, 2024

Scale-free Adversarial Reinforcement Learning

arXiv:2403.00930v12 citationsh-index: 3COLT
Originality Highly original
AI Analysis

This addresses a fundamental challenge in reinforcement learning for scenarios with unknown reward scales, offering theoretical advancements rather than incremental improvements.

The paper tackles the problem of scale-free learning in Markov Decision Processes where reward scales are unknown, achieving the first minimax optimal expected regret bound and high-probability regret guarantees in adversarial settings.

This paper initiates the study of scale-free learning in Markov Decision Processes (MDPs), where the scale of rewards/losses is unknown to the learner. We design a generic algorithmic framework, \underline{S}cale \underline{C}lipping \underline{B}ound (\texttt{SCB}), and instantiate this framework in both the adversarial Multi-armed Bandit (MAB) setting and the adversarial MDP setting. Through this framework, we achieve the first minimax optimal expected regret bound and the first high-probability regret bound in scale-free adversarial MABs, resolving an open problem raised in \cite{hadiji2023adaptation}. On adversarial MDPs, our framework also give birth to the first scale-free RL algorithm with a $\tilde{\mathcal{O}}(\sqrt{T})$ high-probability regret guarantee.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes