Deep reinforcement learning for multi-agent interaction

Ibrahim H. Ahmed, Cillian Brewitt, Ignacio Carlucho, Filippos Christianos, Mhairi Dunion, Elliot Fosong, Samuel Garcin, Shangmin Guo, Balint Gyevnar, Trevor McInroe, Georgios Papoudakis, Arrasy Rahman, Lukas Schäfer, Massimiliano Tamborski, Giuseppe Vecchio, Cheng Wang, Stefano V. Albrecht*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

4 Citations (Scopus)

Abstract

The development of autonomous agents which can interact with other agents to accomplish a given task is a core area of research in artificial intelligence and machine learning. Towards this goal, the Autonomous Agents Research Group develops novel machine learning algorithms for autonomous systems control, with a specific focus on deep reinforcement learning and multi-agent reinforcement learning. Research problems include scalable learning of coordinated agent policies and inter-agent communication; reasoning about the behaviours, goals, and composition of other agents from limited observations; and sample-efficient learning based on intrinsic motivation, curriculum learning, causal inference, and representation learning. This article provides a broad overview of the ongoing research portfolio of the group and discusses open problems for future directions.

Original languageEnglish
Pages (from-to)357-368
Number of pages12
JournalAI Communications
Volume35
Issue number4
DOIs
Publication statusPublished - 20 Sept 2022

Keywords

  • ad hoc teamwork
  • agent/opponent modelling
  • autonomous driving
  • Deep reinforcement learning
  • goal recognition
  • multi-agent reinforcement learning
  • multi-robot warehouse

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Deep reinforcement learning for multi-agent interaction'. Together they form a unique fingerprint.

Cite this