Paper Info
Title
Deep reinforcement learning for multi-agent interaction
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.
Year
DOI
Venue
2022
10.3233/AIC-220116
AI COMMUNICATIONS
Keywords
DocType
Volume
Deep reinforcement learning, multi-agent reinforcement learning, ad hoc teamwork, agent/opponent modelling, goal recognition, autonomous driving, multi-robot warehouse
Journal
35
Issue
ISSN
Citations 
4
0921-7126
0
PageRank 
References 
Authors
0.34
0
17
Name
Order
Citations
PageRank
Ibrahim H. Ahmed100.34
Cillian Brewitt201.01
Ignacio Carlucho300.34
Filippos Christianos403.38
Mhairi Dunion500.34
Elliot Fosong600.34
Samuel Garcin700.34
Shangmin Guo800.34
Balint Gyevnar901.01
Trevor McInroe1000.34
Georgios Papoudakis1100.34
Arrasy Rahman1200.34
Lukas Schäfer1301.35
Massimiliano Tamborski1400.34
Giuseppe Vecchio1500.34
Wang Cheng1610320.70
Stefano V. Albrecht1710310.61