15 citations · 80 across the 14 of their papers we have counts for
14 papers
Tuning-Free Covariance-Aware Sequential Shrinkage for Multi-Source Estimation
Wenbo Jing, Xi Chen, Yaqi Duan +2
Modern statistical learning problems often involve multiple related data sets, in which learning efficiency on a target set can be improved by borrowing information from related so…
Policy evaluation from a single path: Multi-step methods, mixing and mis-specification
Yaqi Duan, Martin J. Wainwright
We study non-parametric estimation of the value function of an infinite-horizon -discounted Markov reward process (MRP) using observations from a single trajectory. We provide n…
Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism
Ming Yin, Yaqi Duan, Mengdi Wang +1
Offline reinforcement learning, which seeks to utilize offline/historical data to optimize sequential decision-making strategies, has gained surging prominence in recent studies. D…
Adaptive and Robust Multi-Task Learning
Yaqi Duan, Kaizheng Wang
We study the multi-task learning problem that aims to simultaneously analyze multiple datasets collected from different sources and learn one model for each of them. We propose a f…
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,…
Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient
Botao Hao, Yaqi Duan, Tor Lattimore +2
This paper provides a statistical analysis of high-dimensional batch Reinforcement Learning (RL) using sparse linear function approximation. When there is a large number of candida…
Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation
Yaqi Duan, Mengdi Wang
This paper studies the statistical theory of batch data reinforcement learning with function approximation. Consider the off-policy evaluation problem, which is to estimate the cum…
Learning low-dimensional state embeddings and metastable clusters from time series data
Yifan Sun, Yaqi Duan, Hao Gong +1
This paper studies how to find compact state embeddings from high-dimensional Markov state trajectories, where the transition kernel has a small intrinsic rank. In the spirit of di…
State Aggregation Learning from Markov Transition Data
Yaqi Duan, Zheng Tracy Ke, Mengdi Wang
State aggregation is a popular model reduction method rooted in optimal control. It reduces the complexity of engineering systems by mapping the system's states into a small number…
Adaptive Low-Nonnegative-Rank Approximation for State Aggregation of Markov Chains
Yaqi Duan, Mengdi Wang, Zaiwen Wen +1
This paper develops a low-nonnegative-rank approximation method to identify the state aggregation structure of a finite-state Markov chain under an assumption that the state space…