page 1  (17 pages)
2to next section

Some Experiments with a Hybrid Model for

Learning Sequential Decision Making

Ron Sun

Todd Peterson

The University of Alabama

Tuscaloosa, AL 35487

EMAIL: [email protected]

PHONE: (205) 348-1667

March 28, 1997

KEY WORDS: connectionist learning, multi-strategy learning, reinforcement learning,

To deal with reactive sequential decision tasks, we present a learning model Clarion, which is a hybrid connectionist model consisting of both localist and distributed representations, based on the two-level approach proposed in Sun (1995). The model learns and utilizes procedural and declarative knowledge, tapping into the synergy of the two types of processes. It unifies neural, reinforcement, and symbolic methods to perform on-line, bottom-up learning. Experiments in various situations are reported that shed light on the working of the model.