Function Approximation in Hierarchical Relational Reinforcement Learning
نویسندگان
چکیده
Recently there have been a number of dif ferent approaches developed for hierarchi cal reinforcement learning in propositional setting We propose a hierarchical version of relational reinforcement learning HRRL We describe a value function approximation method inspired by logic programming which is suitable for HRRL
منابع مشابه
Abstraction and Generalization in Reinforcement Learning: A Summary and Framework
ion and Generalization in Reinforcement Learning: A Summary and Framework Marc Ponsen, Matthew E. Taylor, and Karl Tuyls 1 Universiteit Maastricht, Maastricht, The Netherlands {m.ponsen,k.tuyls}@maastrichtuniversity.nl 2 The University of Southern California, Los Angeles, CA [email protected] Abstract. In this paper we survey the basics of reinforcement learning, generalization and abstraction. W...
متن کاملThe Carli Architecture–Efficient Value Function Specialization for Relational Reinforcement Learning
We introduce Carli–a modular architecture supporting efficient value function specialization for relational reinforcement learning. Using a Rete data structure to support efficient relational representations, it implements an initially general hierarchical tile coding and specializes it over time using a fringe. This hierarchical tile coding constitutes a form of linear function approximation i...
متن کاملReinforcement Learning and Function Approximation
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 resu...
متن کاملA Non-Strict Hierarchical Reinforcement Learning for Interactive Systems and Robots
Conversational systems and robots that use reinforcement learning for policy optimization in large domains often face the problem of limited scalability. This problem has been addressed either by using function approximation techniques that estimate the approximate true value function of a policy or by using a hierarchical decomposition of a learning task into subtasks. We present a novel appro...
متن کاملHierarchical Dialogue Policy Learning using Flexible State Transitions and Linear Function Approximation
Conversational agents that use reinforcement learning for policy optimization in large domains often face the problem of limited scalability. This problem can be addressed either by using function approximation techniques that estimate an approximate true value function, or by using a hierarchical decomposition of a learning task into subtasks. In this paper, we present a novel approach for dia...
متن کامل