A survey of multi-objective sequential decision-making
TLDR
This article surveys algorithms designed for sequential decision-making problems with multiple objectives and proposes a taxonomy that classifies multi-objective methods according to the applicable scenario, the nature of the scalarization function, and the type of policies considered.Abstract:
Sequential decision-making problems with multiple objectives arise naturally in practice and pose unique challenges for research in decision-theoretic planning and learning, which has largely focused on single-objective settings. This article surveys algorithms designed for sequential decision-making problems with multiple objectives. Though there is a growing body of literature on this subject, little of it makes explicit under what circumstances special methods are needed to solve multi-objective problems. Therefore, we identify three distinct scenarios in which converting such a problem to a single-objective one is impossible, infeasible, or undesirable. Furthermore, we propose a taxonomy that classifies multi-objective methods according to the applicable scenario, the nature of the scalarization function (which projects multi-objective values to scalar ones), and the type of policies considered. We show how these factors determine the nature of an optimal solution, which can be a single policy, a convex hull, or a Pareto front. Using this taxonomy, we survey the literature on multi-objective methods for planning and learning. Finally, we discuss key applications of such methods and outline opportunities for future work.read more
Citations
More filters
Proceedings Article
Multi-objective mdps with conditional lexicographic reward preferences
TL;DR: A rich model called Lexicographic MDP (LMDP) and a corresponding planning algorithm called LVI that generalize previous work by allowing for conditional lexicographic preferences with slack are introduced and the convergence characteristics of LVI are analyzed.
Proceedings ArticleDOI
Policy gradient approaches for multi-objective sequential decision making
TL;DR: Two different Multi-Objective Reinforcement-Learning (MORL) approaches that, starting from an initial policy, perform gradient-based policy-search procedures aimed at finding a set of non-dominated policies are presented and compared to state-of-the-art MORL algorithms on three MORL benchmark problems.
Proceedings ArticleDOI
Model-based multi-objective reinforcement learning
TL;DR: This paper has supplied the agent with two different exploration strategies and compare their effectiveness in estimating accurate models within a reasonable amount of time, and results show that the method with the best exploration strategy is able to quickly learn all Pareto optimal policies for the Deep Sea Treasure problem.
Proceedings Article
Budget allocation using weakly coupled, constrained Markov decision processes
Craig Boutilier,Tyler Lu +1 more
TL;DR: This work considers the problem of budget (or other resource) allocation in sequential decision problems involving a large number of concurrently running sub-processes, whose only interaction is through their consumption of budget, and introduces budgeted MDPs, an MDP model in which policies/values are a function of available budget.
Proceedings ArticleDOI
Multi-objective reinforcement learning-based deep neural networks for cognitive space communications
Paulo Victor R. Ferreira,Randy Paffenroth,Alexander M. Wyglinski,Timothy M. Hackett,Sven G. Bilén,Richard C. Reinhart,Dale J. Mortensen +6 more
TL;DR: A novel hybrid radio resource allocation management control algorithm that integrates multi-objective reinforcement learning and deep artificial neural networks is proposed that enables on-line learning by interactions with the environment and restricts poor resource allocation performance through ‘virtual environment exploration’.
References
More filters
Book
Dynamic Programming
TL;DR: The more the authors study the information processing aspects of the mind, the more perplexed and impressed they become, and it will be a very long time before they understand these processes sufficiently to reproduce them.
Book
Markov Decision Processes: Discrete Stochastic Dynamic Programming
TL;DR: Puterman as discussed by the authors provides a uniquely up-to-date, unified, and rigorous treatment of the theoretical, computational, and applied research on Markov decision process models, focusing primarily on infinite horizon discrete time models and models with discrete time spaces while also examining models with arbitrary state spaces, finite horizon models, and continuous time discrete state models.
Book
Introduction to Reinforcement Learning
TL;DR: In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning.
Book
Evolutionary algorithms for solving multi-objective problems
TL;DR: This paper presents a meta-anatomy of the multi-Criteria Decision Making process, which aims to provide a scaffolding for the future development of multi-criteria decision-making systems.
Proceedings Article
Policy Gradient Methods for Reinforcement Learning with Function Approximation
TL;DR: This paper proves for the first time that a version of policy iteration with arbitrary differentiable function approximation is convergent to a locally optimal policy.
Related Papers (5)
Human-level control through deep reinforcement learning
Mastering the game of Go with deep neural networks and tree search
David Silver,Aja Huang,Chris J. Maddison,Arthur Guez,Laurent Sifre,George van den Driessche,Julian Schrittwieser,Ioannis Antonoglou,Veda Panneershelvam,Marc Lanctot,Sander Dieleman,Dominik Grewe,John Nham,Nal Kalchbrenner,Ilya Sutskever,Timothy P. Lillicrap,Madeleine Leach,Koray Kavukcuoglu,Thore Graepel,Demis Hassabis +19 more