method · first seen 29 Oct 2026
UCBVI
Also: upper confidence bound value iteration
An optimism-based model-based reinforcement learning algorithm for episodic tabular MDPs.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Closing the Log Gap: Minimax-Optimal Regret for Episodic RLPapers · 29 Oct 2026 · Guy Zamir, Victor Boone, Matthew Zurek, Yudong Chen
- Exploration via Exploitation: The Blessing of Reward Diversity in Personalized Federated RLPapers · 7 Nov 2026 · Jiin Woo, Gauri Joshi, Yuejie Chi
Latest sources
- Exploration via Exploitation: The Blessing of Reward Diversity in Personalized Federated RLPapers · 7 Nov 2026 · Jiin Woo, Gauri Joshi, Yuejie Chi
- Closing the Log Gap: Minimax-Optimal Regret for Episodic RLPapers · 29 Oct 2026 · Guy Zamir, Victor Boone, Matthew Zurek, Yudong Chen