Controlling State-Space Explosion in Chunk Learning

Vladislav VekslerU.S. Air Force Research Laboratory
Kevin GluckU.S. Air Force Research Laboratory
Christopher MyersU.S. Air Force Research Laboratory
Jack HarrisU.S. Air Force Research Laboratory
Thomas MielkeU.S. Air Force Research Laboratory


Varying combinations of perceptual cues may be relevant for learning and action-selection. However, storing all possible cue combinations in memory is computationally implausible in sufficiently complex environments due to a state-space explosion. Some psychological models suggest that cue combinations, i.e. chunks, should be generated at a conservative rate (EPAM/CHREST; e.g. Feigenbaum & Simon, 1984). Other models suggest that chunk retrieval is based on statistical regularities in the environment (i.e. recency and frequency; Anderson & Schooler, 1991). We present a computational model of chunk generation based on these two principles, and demonstrate how combining these principles alleviates state-space explosion, producing great savings in memory while maintaining a high level of performance.


Controlling State-Space Explosion in Chunk Learning (1.1 MB)

Back to Table of Contents