Reinforcement Learning and Function Approximation

All Papers

Relational reinforcement learning combines traditional reinforcement learning with a strong emphasis on a relational (rather than attribute-value) representation. Earlier work used relational reinforcement learning on a learning version of the classic Blocks World planning problem (a version where the learner does not know what the result of taking an action will be). "Structural" learning results have been obtained, such as learning in a mixed 3-5 block environment and being able to perform in a 3 or 10 block environment.