15 citations · 80 across the 14 of their papers we have counts for
6 papers · 1 filter
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…
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…
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…