English

A Scale-Independent Multi-Objective Reinforcement Learning with Convergence Analysis

Machine Learning 2023-02-28 v4

Abstract

Many sequential decision-making problems need optimization of different objectives which possibly conflict with each other. The conventional way to deal with a multi-task problem is to establish a scalar objective function based on a linear combination of different objectives. However, for the case of having conflicting objectives with different scales, this method needs a trial-and-error approach to properly find proper weights for the combination. As such, in most cases, this approach cannot guarantee an optimal Pareto solution. In this paper, we develop a single-agent scale-independent multi-objective reinforcement learning on the basis of the Advantage Actor-Critic (A2C) algorithm. A convergence analysis is then done for the devised multi-objective algorithm providing a convergence-in-mean guarantee. We then perform some experiments over a multi-task problem to evaluate the performance of the proposed algorithm. Simulation results show the superiority of developed multi-objective A2C approach against the single-objective algorithm.

Keywords

Cite

@article{arxiv.2302.04179,
  title  = {A Scale-Independent Multi-Objective Reinforcement Learning with Convergence Analysis},
  author = {Mohsen Amidzadeh},
  journal= {arXiv preprint arXiv:2302.04179},
  year   = {2023}
}
R2 v1 2026-06-28T08:35:13.504Z