DeepAI AI Chat
Log In Sign Up

Multi-Objective Deep Reinforcement Learning

by   Hossam Mossalam, et al.
University of Oxford

We propose Deep Optimistic Linear Support Learning (DOL) to solve high-dimensional multi-objective decision problems where the relative importances of the objectives are not known a priori. Using features from the high-dimensional inputs, DOL computes the convex coverage set containing all potential optimal solutions of the convex combinations of the objectives. To our knowledge, this is the first time that deep reinforcement learning has succeeded in learning multi-objective policies. In addition, we provide a testbed with two experiments to be used as a benchmark for deep multi-objective reinforcement learning.


page 1

page 2

page 3

page 4


gTLO: A Generalized and Non-linear Multi-Objective Deep Reinforcement Learning Approach

In real-world decision optimization, often multiple competing objectives...

A Multi-Objective Deep Reinforcement Learning Framework

This paper presents a new multi-objective deep reinforcement learning (M...

Provable Multi-Objective Reinforcement Learning with Generative Models

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

Deep W-Networks: Solving Multi-Objective Optimisation Problems With Deep Reinforcement Learning

In this paper, we build on advances introduced by the Deep Q-Networks (D...

Taming Lagrangian Chaos with Multi-Objective Reinforcement Learning

We consider the problem of two active particles in 2D complex flows with...