A practical guide to multi-objective reinforcement learning and planning

CF Hayes, R Rădulescu, E Bargiacchi… - Autonomous Agents and …, 2022‏ - Springer
Real-world sequential decision-making tasks are generally complex, requiring trade-offs
between multiple, often conflicting, objectives. Despite this, the majority of research in …

A toolkit for reliable benchmarking and research in multi-objective reinforcement learning

F Felten, LN Alegre, A Nowe… - Advances in …, 2023‏ - proceedings.neurips.cc
Multi-objective reinforcement learning algorithms (MORL) extend standard reinforcement
learning (RL) to scenarios where agents must optimize multiple---potentially conflicting …

Multi-objective multi-agent decision making: a utility-based analysis and survey

R Rădulescu, P Mannion, DM Roijers… - Autonomous Agents and …, 2020‏ - Springer
The majority of multi-agent system implementations aim to optimise agents' policies with
respect to a single objective, despite the fact that many real-world problem domains are …

Promptable behaviors: Personalizing multi-objective rewards from human preferences

M Hwang, L Weihs, C Park, K Lee… - Proceedings of the …, 2024‏ - openaccess.thecvf.com
Customizing robotic behaviors to be aligned with diverse human preferences is an
underexplored challenge in the field of embodied AI. In this paper we present Promptable …

Actor-critic multi-objective reinforcement learning for non-linear utility functions

M Reymond, CF Hayes, D Steckelmacher… - Autonomous Agents and …, 2023‏ - Springer
We propose a novel multi-objective reinforcement learning algorithm that successfully learns
the optimal policy even for non-linear utility functions. Non-linear utility functions pose a …

Multi-objective reinforcement learning based on decomposition: A taxonomy and framework

F Felten, EG Talbi, G Danoy - Journal of Artificial Intelligence Research, 2024‏ - jair.org
Multi-objective reinforcement learning (MORL) extends traditional RL by seeking policies
making different compromises among conflicting objectives. The recent surge of interest in …

The impact of environmental stochasticity on value-based multiobjective reinforcement learning

P Vamplew, C Foale, R Dazeley - Neural Computing and Applications, 2022‏ - Springer
A common approach to address multiobjective problems using reinforcement learning
methods is to extend model-free, value-based algorithms such as Q-learning to use a vector …

[PDF][PDF] Distributional monte carlo tree search for risk-aware and multi-objective reinforcement learning

CF Hayes, M Reymond, DM Roijers, E Howley… - Proceedings of the 20th …, 2021‏ - ifaamas.org
In many risk-aware and multi-objective reinforcement learning settings, the utility of the user
is derived from the single execution of a policy. In these settings, making decisions based on …

Learning pareto set for multi-objective continuous robot control

T Shu, K Shang, C Gong, Y Nan, H Ishibuchi - arxiv preprint arxiv …, 2024‏ - arxiv.org
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 …

Robust Multiobjective Reinforcement Learning Considering Environmental Uncertainties

X He, J Hao, X Chen, J Wang, X Ji… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
Numerous real-world decision or control problems involve multiple conflicting objectives
whose relative importance (preference) is required to be weighed in different scenarios …