Learning Pareto Set for Multi-Objective Continuous Robot Control

TL;DR

This paper introduces a resource-efficient MORL algorithm that learns a continuous Pareto set representation using a hypernet, enabling quick generation of policies for various preferences in complex robot control tasks.

Contribution

It proposes a novel hypernet-based MORL method that efficiently approximates the Pareto set in high-dimensional spaces, reducing resource consumption compared to existing algorithms.

Findings

Achieves best overall performance with fewer training parameters.

The Pareto set forms a curved surface in parameter space, offering new insights.

Outperforms two state-of-the-art MORL algorithms on robot control problems.

Abstract

For a control problem with multiple conflicting objectives, there exists a set of Pareto-optimal policies called the Pareto set instead of a single optimal policy. When a multi-objective control problem is continuous and complex, traditional multi-objective reinforcement learning (MORL) algorithms search for many Pareto-optimal deep policies to approximate the Pareto set, which is quite resource-consuming. In this paper, we propose a simple and resource-efficient MORL algorithm that learns a continuous representation of the Pareto set in a high-dimensional policy parameter space using a single hypernet. The learned hypernet can directly generate various well-trained policy networks for different user preferences. We compare our method with two state-of-the-art MORL algorithms on seven multi-objective continuous robot control problems. Experimental results show that our method achieves the best overall performance with the least training parameters. An interesting observation is that the Pareto set is well approximated by a curved line or surface in a high-dimensional parameter space. This observation will provide insight for researchers to design new MORL algorithms.