2 papers
cs.LG2024
How Does Variance Shape the Regret in Contextual Bandits?
Zeyu Jia, Jian Qian, Alexander Rakhlin +1
We consider realizable contextual bandits with general function approximation, investigating how small reward variance can lead to better-than-minimax regret bounds. Unlike in mini…
cs.LG2024
Offline Reinforcement Learning: Role of State Aggregation and Trajectory Data
Zeyu Jia, Alexander Rakhlin, Ayush Sekhari +1
We revisit the problem of offline reinforcement learning with value function realizability but without Bellman completeness. Previous work by Xie and Jiang (2021) and Foster et al.…