Sciweavers

Share
NIPS
2004

Schema Learning: Experience-Based Construction of Predictive Action Models

9 years 12 months ago
Schema Learning: Experience-Based Construction of Predictive Action Models
Schema learning is a way to discover probabilistic, constructivist, predictive action models (schemas) from experience. It includes methods for finding and using hidden state to make predictions more accurate. We extend the original schema mechanism [1] to handle arbitrary discrete-valued sensors, improve the original learning criteria to handle POMDP domains, and better maintain hidden state by using schema predictions. These extensions show large improvement over the original schema mechanism in several rewardless POMDPs, and achieve very low prediction error in a difficult speech modeling task. Further, we compare extended schema learning to the recently introduced predictive state representations [2], and find their predictions of next-step action effects to be approximately equal in accuracy. This work lays the foundation for a schema-based system of integrated learning and planning.
Michael P. Holmes, Charles Lee Isbell Jr.
Added 31 Oct 2010
Updated 31 Oct 2010
Type Conference
Year 2004
Where NIPS
Authors Michael P. Holmes, Charles Lee Isbell Jr.
Comments (0)
books