
A dynamic weight-based preference inference (DWPI) algorithm that can accurately infer user preferences from demonstrations, including sub-optimal ones, in multi-objective reinforcement learning settings.


coremsg

inferring-user-preferences-from-demonstrations-in-multi-objective-reinforcement-learning


Inferring User Preferences from Demonstrations in Multi-Objective Reinforcement Learning


title_rewrite


This paper proposes a novel demonstration-guided multi-objective reinforcement learning (DG-MORL) algorithm that utilizes prior demonstrations to enhance exploration efficiency and policy performance in complex multi-objective reinforcement learning tasks.


demonstration-guided-multi-objective-reinforcement-learning-enhancing-exploration-efficiency-and-policy-performance


Demonstration-Guided Multi-Objective Reinforcement Learning: Enhancing Exploration Efficiency and Policy Performance
