Utility-based Reinforcement Learning: Unifying Single-objective And Multi-objective Reinforcement Learning

Abstract

Research in multi-objective reinforcement learning (MORL) has introduced the utility-based paradigm, which makes use of both environmental rewards and a function that defines the utility derived by the user from those rewards. In this paper we extend this paradigm to the context of single-objective reinforcement learning (RL), and outline multiple potential benefits including the ability to perform multi-policy learning across tasks relating to uncertain objectives, risk-aware RL, discounting, and safe RL. We also examine the algorithmic implications of adopting a utility-based approach.

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keyvamplew2024utility

Related papers

• On Generalization Across Environments In Multi-objective Reinforcement Learning (2025)0.00
• Issues With Value-based Multi-objective Reinforcement Learning: Value Function Interference And Overestimation Sensitivity (2024)0.00
• Addressing The Issue Of Stochastic Environments And Local Decision-making In Multi-objective Reinforcement Learning (2022)0.00
• A Generalized Algorithm For Multi-objective Reinforcement Learning And Policy Adaptation (2019)0.00
• Multi-objective Reinforcement Learning Based On Decomposition: A Taxonomy And Framework (2023)9.92
• Provable Multi-objective Reinforcement Learning With Generative Models (2020)0.00
• An Empirical Investigation Of Value-based Multi-objective Reinforcement Learning For Stochastic Environments (2024)0.00
• Interpretability By Design For Efficient Multi-objective Reinforcement Learning (2025)0.00