Showing 2025Show all
2 papers · 1 filter
stat.ML2025
Efficient Best-of-Both-Worlds Algorithms for Contextual Combinatorial Semi-Bandits
Mengmeng Li, Philipp J. Schneider, Jelisaveta Aleksić +1
We introduce the first best-of-both-worlds algorithm for contextual combinatorial semi-bandits that simultaneously guarantees regret in the adve…
math.OC2025
Towards Optimal Offline Reinforcement Learning
Mengmeng Li, Daniel Kuhn, Tobias Sutter
We study offline reinforcement learning problems with a long-run average reward objective. The state-action pairs generated by any fixed behavioral policy thus follow a Markov chai…