On the limitations of scalarisation for multi-objective reinforcement learning of pareto fronts

Multiobjective reinforcement learning (MORL) extends RL to problems with multiple conflicting objectives. This paper argues for designing MORL systems to produce a set of solutions approximating the Pareto front, and shows that the common MORL technique of scalarisation has fundamental limitations when used to find Pareto-optimal policies. The work is supported by the presentation of three new MORL benchmarks with known Pareto fronts. © 2008 Springer Berlin Heidelberg.