2 papers
cs.LG2025
Best Arm Identification with Possibly Biased Offline Data
Le Yang, Vincent Y. F. Tan, Wang Chi Cheung
We study the best arm identification (BAI) problem with potentially biased offline data in the fixed confidence setting, which commonly arises in real-world scenarios such as clini…
cs.LG2025
Efficiently Solving Discounted MDPs with Predictions on Transition Matrices
Lixing Lyu, Jiashuo Jiang, Wang Chi Cheung
We study infinite-horizon Discounted Markov Decision Processes (DMDPs) under a generative model. Motivated by the Algorithm with Advice framework Mitzenmacher and Vassilvitskii 202…