Most reinforcement learning methods operate on propositional representations of the world state. Such representations are often intractably large and generalize poorly. Using a deictic representation is believed to be a viable alternative: they promise generalization while allowing the use of existing reinforcement-learning methods. Yet, there are few experiments on learning with deictic representations reported in the literature. In this paper we explore the effectiveness of two forms of deictic representation and a naive propositional representation in a simple blocks-world domain. We find, empirically, that the deictic representations actually worsen performance. We conclude with a discussion of possible causes of these results and strategies for more effective learning in domains with objects.
| Identifer | oai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/6685 |
| Date | 10 April 2002 |
| Creators | Finney, Sarah, Gardiol, Natalia H., Kaelbling, Leslie Pack, Oates, Tim |
| Source Sets | M.I.T. Theses and Dissertation |
| Language | en_US |
| Detected Language | English |
| Format | 41 p., 5712208 bytes, 1294450 bytes, application/postscript, application/pdf |
| Relation | AIM-2002-006 |
Page generated in 0.002 seconds