Meiling Yu — accepted AI-conference papers

2026

Near-Minimax Multi-Objective RL under Predictable Adversarial Preferences and Preference-Free Exploration in Linear MDPs

ICML 2026poster

Multi-objective reinforcement learning (MORL) must often support preferences that change online or are specified only after data collection. We study finite-horizon MORL with vector feedback in linear MDPs under two protocols: (i) predictable adversarial preferences revealed before each episode, and…

Cited by 0 Source ↗Scholar ↗

2026

Time-Consistent Robust Multi-Objective Reinforcement Learning via a Bellman–Isaacs Weight-Adversary Recursion

Mingxi Hu, Meiling Yu

ICML 2026poster

Most multi-objective reinforcement learning (MORL) methods either condition on a fixed preference weight $w$ or consider episodic robustness where an adversary selects a single $w$ per episode. We study a time-consistent robustness model with reactive preferences: after each transition, an opponent …

Cited by 0 Source ↗Scholar ↗