Relational Reinforcement Learning for Agents in Worlds with Objects

In reinforcement learning, an agent tries to learn a policy, i.e., how to select an action in a given state of the environment, so that it maximizes the total amount of reward it receives when interacting with the environment. We argue that a relational representation of states is natural and useful when the environment is complex and involves many interrelated objects. Relational reinforcement learning works on such relational representations and can be used to approach problems that are currently out of reach for classical reinforcement learning approaches.

• Type: Journal
• Year: 2002
• Where: AAMAS
• Authors: Saso Dzeroski
• Keywords: AAMAS 2002, Intelligent Agents, Interrelated Objects, Reinforcement, Relational Representations