paper-with-me

Papers

UCB-driven Utility Function Search for Multi-objective Reinforcement Learning

2024-05-01 · Yucheng Shi, Alexandros Agapitos, David Lynch, Giorgio Cruciata, Cengis Hasan, Hao Wang, Yayu Yao, Aleksandar Milenovic

In Multi-objective Reinforcement Learning (MORL) agents are tasked with optimising decision-making behaviours that trade-off between multiple, possibly conflicting, objectives. MORL based on decomposition is a family of solution methods that employ a number of utility functions to decompose the multi-objective problem into individual single-objective problems solved simultaneously in order to approximate a Pareto front of policies. We focus on the case of linear utility functions parameterised by weight vectors w. We introduce a method based on Upper Confidence Bound to efficiently search for the most promising weight vectors during different stages of the learning process, with the aim of maximising the hypervolume of the resulting Pareto front. The proposed method is shown to outperform various MORL baselines on Mujoco benchmark problems across different random seeds. The code is online at: https://github.com/SYCAMORE-1/ucb-MOPPO.

📄 PDF Abstract BibTeX arXiv:2405.00410

Code (1)

sycamore-1/ucb-moppo 공식 구현 pytorch

Tasks

Decision MakingMuJoCoMulti-Objective Reinforcement Learningreinforcement-learningReinforcement Learning

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

User-Preference Meets Pareto-Optimality: Multi-Objective Bayesian Optimization with Local Gradient Search

2025-02-10 · Joshua Hang Sai Ip, Ankush Chakrabarty, Ali Mesbah, Diego Romeres

Incorporating user preferences into multi-objective Bayesian optimization (MOBO) allows for personalization of the optimization procedure. Preferences are often abstracted in the form of an unknown utility function, esti…

Bayesian Optimization

Multi-Objective Multi-Agent Decision Making: A Utility-based Analysis and Survey

2019-09-06 · Roxana Rădulescu, Patrick Mannion, Diederik M. Roijers, Ann Nowé

The majority of multi-agent system (MAS) implementations aim to optimise agents' policies with respect to a single objective, despite the fact that many real-world problem domains are inherently multi-objective in nature…

Decision Making

Utility-Based Reinforcement Learning: Unifying Single-objective and Multi-objective Reinforcement Learning

2024-02-05 · Peter Vamplew, Cameron Foale, Conor F. Hayes, Patrick Mannion 외

Research in multi-objective reinforcement learning (MORL) has introduced the utility-based paradigm, which makes use of both environmental rewards and a function that defines the utility derived by the user from those re…

Multi-Objective Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

A utility-based analysis of equilibria in multi-objective normal form games

2020-01-17 · Roxana Rădulescu, Patrick Mannion, Yijie Zhang, Diederik M. Roijers 외

In multi-objective multi-agent systems (MOMAS), agents explicitly consider the possible tradeoffs between conflicting objective functions. We argue that compromises between competing objectives in MOMAS should be analyse…

Form

Deep Multi-Objective Reinforcement Learning for Utility-Based Infrastructural Maintenance Optimization

2024-06-10 · Jesse van Remmerden, Maurice Kenter, Diederik M. Roijers, Charalampos Andriotis 외

In this paper, we introduce Multi-Objective Deep Centralized Multi-Agent Actor-Critic (MO- DCMAC), a multi-objective reinforcement learning (MORL) method for infrastructural maintenance optimization, an area traditionall…

Multi-Objective Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)