English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We make significant progress toward the stochastic shortest path problem withadversarial costs and unknown transition. Specifically, we develop algorithmsthat achieve $\widetilde{O}(\sqrt{S^2ADT_\star K})$ regret for thefull-information setting and $\widetilde{O}(\sqrt{S^3A^2DT_\star K})$ regretfor the bandit feedback setting, where $D$ is the diameter, $T_\star$ is theexpected hitting time of the optimal policy, $S$ is the number of states, $A$is the number of actions, and $K$ is the number of episodes. Our work strictlyimproves (Rosenberg and Mansour, 2020) in the full information setting, extends(Chen et al., 2020) from known transition to unknown transition, and is alsothe first to consider the most challenging combination: bandit feedback withadversarial costs and unknown transition. To remedy the gap between our upperbounds and the current best lower bounds constructed via a stochasticallyoblivious adversary, we also propose algorithms with near-optimal regret forthis special case.

Finding the Stochastic Shortest Path with Low Regret: The Adversarial Cost and Unknown Transition Case