15 citations · 80 across the 14 of their papers we have counts for
5 papers · 1 filter
Optimal policy evaluation using kernel-based temporal difference methods
Yaqi Duan, Mengdi Wang, Martin J. Wainwright
We study methods based on reproducing kernel Hilbert spaces for estimating the value function of an infinite-horizon discounted Markov reward process (MRP). We study a regularized…
PU-Flow: a Point Cloud Upsampling Network with Normalizing Flows
Aihua Mao, Zihui Du, Junhui Hou +3
Point cloud upsampling aims to generate dense point clouds from given sparse ones, which is a challenging task due to the irregular and unordered nature of point sets. To address t…
Learning Good State and Action Representations via Tensor Decomposition
Chengzhuo Ni, Yaqi Duan, Munther Dahleh +2
The transition kernel of a continuous-state-action Markov decision process (MDP) admits a natural tensor structure. This paper proposes a tensor-inspired unsupervised learning meth…
Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning
Yaqi Duan, Chi Jin, Zhiyuan Li
This paper considers batch Reinforcement Learning (RL) with general value function approximation. Our study investigates the minimal assumptions to reliably estimate/minimize Bellm…
Bootstrapping Fitted Q-Evaluation for Off-Policy Inference
Botao Hao, Xiang Ji, Yaqi Duan +3
Bootstrapping provides a flexible and effective approach for assessing the quality of batch reinforcement learning, yet its theoretical property is less understood. In this paper,…