Relational Reinforcement Learning in Infinite Mario
This addresses the challenge of scaling reinforcement learning to complex environments like video games, though it appears incremental as it applies known relational methods to a new domain.
The paper tackled the problem of learning in large state and action spaces like computer games by using relational representations in reinforcement learning, resulting in agents that demonstrate learning behavior in such domains.
Relational representations in reinforcement learning allow for the use of structural information like the presence of objects and relationships between them in the description of value functions. Through this paper, we show that such representations allow for the inclusion of background knowledge that qualitatively describes a state and can be used to design agents that demonstrate learning behavior in domains with large state and actions spaces such as computer games.