2020/05/15 by Abbas Abdolmaleki, Abdolmaleki, Abbas, Sandy H. Huang +16 · 3 citations
Computer Science · #Advanced Multi-Objective Optimization Algorithms #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Reinforcement Learning in Robotics #Robotics (cs.RO)
paper · pdf · doi:10.48550/arxiv.2005.07513
openalex publication_date 2020/05/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Many real-world problems require trading off multiple competing objectives. However, these objectives are often in different units and/or scales, which can make it challenging for practitioners to express numerical preferences over objectives in their native units. In this paper we propose a novel algorithm for multi-objective reinforcement learning that enables setting desired preferences for objectives in a scale-invariant way. We propose to learn an action distribution for each objective, and we use supervised learning to fit a parametric policy to a combination of these distributions. We demonstrate the effectiveness of our approach on challenging high-dimensional real and simulated robotics tasks, and show that setting different preferences in our framework allows us to trace out the space of nondominated solutions.