Multi-agent Relational Reinforcement Learning

In this paper we report on using a relational state space in multi-agent reinforcement learning. There is growing evidence in the Reinforcement Learning research community that a relational representation of the state space has many benefits over a propositional one. Complex tasks as planning or information retrieval on the web can be represented more naturally in relational form. Yet, this relational structure has not been exploited for multi-agent reinforcement learning tasks and has only been studied in a single agent context so far. In this paper we explore the powerful possibilities of using Relational Reinforcement Learning (RRL) in complex multi-agent coordination tasks. More prewe consider an abstract multi-state coordination problem, which can be considered as a variation and extension of repeated stateless Dispersion Games. Our approach shows that RRL allows to represent a complex state space in a multi-agent environment more compactly and allows for fast convergence of lear...

• Type: Conference
• Year: 2005
• Where: LAMAS
• Authors: Tom Croonenborghs, Karl Tuyls, Jan Ramon, Maurice Bruynooghe
• Keywords: LAMAS 2005, Machine Learning, Multi-agent Reinforcement, Reinforcement Learning, State Space