DeepAI AI Chat
Log In Sign Up

Relationship Explainable Multi-objective Optimization Via Vector Value Function Based Reinforcement Learning

by   Huixin Zhan, et al.
The University of Texas at San Antonio

Solving multi-objective optimization problems is important in various applications where users are interested in obtaining optimal policies subject to multiple, yet often conflicting objectives. A typical approach to obtain optimal policies is to first construct a loss function that is based on the scalarization of individual objectives, and then find the optimal policy that minimizes the loss. However, optimizing the scalarized (and weighted) loss does not necessarily provide a guarantee of high performance on each possibly conflicting objective. In this paper, we propose a vector value based reinforcement learning approach that seeks to explicitly learn the inter-objective relationship and optimize multiple objectives based on the learned relationship. In particular, the proposed method is to first define relationship matrix, a mathematical representation of the inter-objective relationship, and then create one actor and multiple critics that can co-learn the relationship matrix and action selection. The proposed approach can quantify the inter-objective relationship via reinforcement learning when the impact of one objective on another is unknown a prior. We also provide rigorous convergence analysis of the proposed approach and present a quantitative evaluation of the approach based on two testing scenarios.


page 1

page 2


Relationship Explainable Multi-objective Reinforcement Learning with Semantic Explainability Generation

Solving multi-objective optimization problems is important in various ap...

Provable Multi-Objective Reinforcement Learning with Generative Models

Multi-objective reinforcement learning (MORL) is an extension of ordinar...

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

Many sequential decision-making problems need optimization of different ...

IMO^3: Interactive Multi-Objective Off-Policy Optimization

Most real-world optimization problems have multiple objectives. A system...

Expected Scalarised Returns Dominance: A New Solution Concept for Multi-Objective Decision Making

In many real-world scenarios, the utility of a user is derived from the ...

Measuring and Assessing Latent Variation in Alliance Design and Objectives

The alliance literature is bifurcated between an empirically-driven appr...

Model-Advantage Optimization for Model-Based Reinforcement Learning

Model-based Reinforcement Learning (MBRL) algorithms have been tradition...