UCB-driven Utility Function Search for Multi-objective Reinforcement Learning

arXiv:2405.00410v1 Announce Type: new
Abstract: In Multi-objective Reinforcement Learning (MORL) agents are tasked with optimising decision-making behaviours that trade-off between multiple, possibly conflicting, objectives. MORL based on decomposition is a family of solution methods that employ a number of utility functions to decompose the multi-objective problem into individual single-objective problems solved simultaneously in order to approximate a Pareto front of policies. We focus on the case of linear utility functions parameterised by weight vectors w. We introduce a method based …

arxiv cs.lg function multi-objective reinforcement reinforcement learning search type utility