Tighter Regret Bounds for Contextual Action-Set Reinforcement Learning

Abstract:We study episodic reinforcement learning with fixed reward and transition functions, but with episode-dependent admissible action sets that are observed at the start of each episode. Performance is measured by cumulative regret against the episode-wise optimal value, $\sum_{k=1}^K [V^{*,M^k} - V^{\pi^k,M^k}]$, where $M^k$ represents the action context in the $k$-th episode. We show that the MVP algorithm naturally extends to this framework and enjoys strong theoretical guarantees. In particular, we establish a minimax regret bound of $\widetilde{O}(\sqrt{SAH^3K\log L})$ for adversarial contexts, where $L$ denotes the number of possible contexts. This result implies a regret bound of $\widetilde{O}(\sqrt{SAH^3K})$ for stochastic contexts. We further translate the stochastic regret guarantee into a sample complexity bound of $\widetilde{O}(SAH^3/\epsilon^2)$ for a fixed context distribution. In addition, we derive a gap-dependent regret bound of \[ \widetilde O\left( \inf_{p\in [0,1)} \left( \frac{1}{\Delta_{\min}^{p}} + pK\Delta_{\min}^{p} \right)\log K \cdot \mathrm{poly}(S,A,H) \right), \] where $\Delta_{\min}^{p}$ is the global $p$-trimmed positive-gap floor over suboptimal $(h,s,a)$ triples. This bound can substantially improve upon the minimax rate when the relevant suboptimality gaps are large.

This manuscript is superseded by Optimal Multi-Reward Reinforcement Learning (https://arxiv.org/abs/2609.36486), whose results subsume our action-context RL results. Substantial differences in scope and content required a separate arXiv submission rather than a replacement. We withdraw this manuscript and refer readers to the new paper

Machine Learning (cs.LG); Machine Learning (stat.ML)

arXiv:2605.15692 [cs.LG]

(or arXiv:2605.15692v2 [cs.LG] for this version)