Can I read A Review of the Deep Sea Treasure problem as a Multi-Objective Reinforcement Learning Benchmark on EtoBox?

A Review of the Deep Sea Treasure problem as a Multi-Objective Reinforcement Learning Benchmark by Cassimon, Amber; Eyckerman, Reinout; Mercelis, Siegfried; Latré, Steven; Hellinckx, Peter is a scholarly article available to read on EtoBox.

What is A Review of the Deep Sea Treasure problem as a Multi-Objective Reinforcement Learning Benchmark about?

In this paper, the authors investigate the Deep Sea Treasure (DST) problem as proposed by Vamplew et al. Through a number of proofs, the authors show the original DST problem to be quite basic, and not always representative of practical Multi-Objective Optimization problems. In an attempt to bring theory closer to practice, the authors propose an alternative, improved version of the DST problem, and prove that some of the properties that simplify the original DST problem no longer hold. The authors also provide a reference implementation and perform a comparison between their implementation, and other existing open-source implementations of the problem. Finally, the authors also provide a complete Pareto-front for their new DST problem.

Author

Cassimon, Amber; Eyckerman, Reinout; Mercelis, Siegfried; Latré, Steven; Hellinckx, Peter

Published

2021

Language

EN