A Case Study of Learning in an Uncertain Environment using a Cognitive Architecture: Soar Plays Dice.
John LairdJohn L. Tishman Professor of Engineering
Tuesday, November 29, 2011|
4:00pm - 5:00pm
3725 Beyster Bldg.
Add to Google Calendar
About the Event
The emphasis of my research is on cognitive architecture, where the goal is to develop the fixed processes, memories, representations, and interfaces that support end-to-end behavior in intelligent systems. In this talk I will present a case study of how multiple learning mechanisms (chunking and reinforcement learning) are integrated in Soar, and how they combine to produce novel learning in a multiplayer dice game where uncertainty is rampant. Many AI game systems emphasize either complex evaluation functions or learning by experience. In this talk, I will demonstrate how it is straightforward to encode symbolic heuristics and opponent modeling as an evaluation function in a Soar agent. I will also demonstrate how that complex processing can be automatically compiled by chunking into selection rules, which are tuned by reinforcement learning leading to significant improvements in performance. This work may provide insight into the origins of value functions in RL for large state spaces, and as to how those value functions can be initialized and then tuned by experience. This research is performed using existing mechanisms in Soar, without modification.
Open to: Public