4 papers
Learning to Cut: Reinforcement Learning for Benders Decomposition
Haochen Cai, Xian Yu
Benders decomposition (BD) is a widely used solution approach for solving two-stage stochastic programs arising in real-world decision-making under uncertainty. However, it often s…
Residuals-based Offline Reinforcement Learning
Qing Zhu, Xian Yu
Offline reinforcement learning (RL) has received increasing attention for learning policies from previously collected data without interaction with the real environment, which is p…
Reward Redistribution via Gaussian Process Likelihood Estimation
Minheng Xiao, Xian Yu
In many practical reinforcement learning tasks, feedback is only provided at the end of a long horizon, leading to sparse and delayed rewards. Existing reward redistribution method…
Policy Gradient Methods for Risk-Sensitive Distributional Reinforcement Learning with Provable Convergence
Minheng Xiao, Xian Yu, Lei Ying
Risk-sensitive reinforcement learning (RL) is crucial for maintaining reliable performance in high-stakes applications. While traditional RL methods aim to learn a point estimate o…