2 citations · 8 across the 12 of their papers we have counts for
3 papers · 1 filter
Learning Bellman Complete Representations for Offline Policy Evaluation
Jonathan D. Chang, Kaiwen Wang, Nathan Kallus +1
We study representation learning for Offline Reinforcement Learning (RL), focusing on the important task of Offline Policy Evaluation (OPE). Recent work shows that, in contrast to…
Provable Benefits of Representational Transfer in Reinforcement Learning
Alekh Agarwal, Yuda Song, Wen Sun +3
We study the problem of representational transfer in RL, where an agent first pretrains in a number of source tasks to discover a shared representation, which is subsequently used…
Doubly Robust Distributionally Robust Off-Policy Evaluation and Learning
Nathan Kallus, Xiaojie Mao, Kaiwen Wang +1
Off-policy evaluation and learning (OPE/L) use offline observational data to make better decisions, which is crucial in applications where online experimentation is limited. Howeve…