6 papers · 1 filter
Optimal Data Acquisition for Reinforcement Learning: A Large Deviations Perspective
Mingjie Hu, Jian-Qiang Hu, Enlu Zhou
Data acquisition efficiency is a central challenge in deploying reinforcement learning in business and healthcare operations, where interactions are costly, slow, and often involve…
Evolving Robustness--Exploration Trade-off in Online Reinforcement Learning via Quantile Bayesian Risk MDPs
Meichen Song, Yuhao Wang, Enlu Zhou
In online reinforcement learning, data scarcity creates epistemic uncertainty that makes robustness important early in learning, whereas sufficient exploration is needed to learn t…
Adaptive Simulation Experiment for LLM Policy Optimization
Mingjie Hu, Siyang Gao, Jian-qiang Hu +1
Large language models (LLMs) have significant potential to improve operational efficiency in operations management. Deploying these models requires specifying a policy that governs…
Bayesian Risk-Sensitive Policy Optimization For MDPs With General Loss Functions
Xiaoshuang Wang, Yifan Lin, Enlu Zhou
Motivated by many application problems, we consider Markov decision processes (MDPs) with a general loss function and unknown parameters. To mitigate the epistemic uncertainty asso…
Online Bayesian Risk-Averse Reinforcement Learning
Yuhao Wang, Enlu Zhou
In this paper, we study the Bayesian risk-averse formulation in reinforcement learning (RL). To address the epistemic uncertainty due to a lack of data, we adopt the Bayesian Risk…
Reusing Historical Trajectories in Natural Policy Gradient via Importance Sampling: Convergence and Convergence Rate
Yifan Lin, Yuhao Wang, Enlu Zhou
Reinforcement learning provides a mathematical framework for learning-based control, whose success largely depends on the amount of data it can utilize. The efficient utilization o…