Title: Relational reinforcement learning
Authors: Dzeroski, Saso
De Raedt, Luc
Driessens, Kurt
Issue Date: May-2001
Publisher: Department of Computer Science, K.U.Leuven, Leuven, Belgium
Series Title: CW Reports vol:CW311
Abstract: Relational reinforcement learning is presented, a learning technique that combines reinforcement learning with relational learning or inductive logic programming. Due to the use of a more expressive representation language to represent states, actions and Q-functions, relational reinforcement learning can be potentially applied to a new range of learning tasks. One such task that we investigate is planning in the blocks world, where it is assumed that the effects of the actions are unknown to the agent and the agent has to learn a policy. Within this simple domain we show that relational reinforcement learning solves some existing problems with reinforcement learning. In particular, relational reinforcement learning allows us to employ structural representations, to abstract from specific goals pursued and to exploit the results of previous learning phases when addressing new (more complex) situations.
Publication status: published
KU Leuven publication type: IR
Appears in Collections:Informatics Section

Files in This Item:
File Status SizeFormat
2001_rep_dzeroski.pdf Published 498KbAdobe PDFView/Open


All items in Lirias are protected by copyright, with all rights reserved.