We propose an impasse-driven method for generating memory retrieval requests and integrating their contents dynamically and asynchronously into the current reasoning context of an agent. This method extends our previous theory of agent architecture, called experience-based agency (Ram & Francis 1996), by proposing a general method that can replace and augment task-specific mechanisms for generating memory retrievals and invoking integration mechanisms. As part of an overall agent architecture, this method has promise as a way to introduce in a principled way efficient high-level memory operations into systems based on reactive task-network decomposition.
Read the paper:
Can Your Architecture Do This? A Proposal for Impasse-Driven Asynchronous Memory Retrieval and Integration
by Anthony Francis, Ashwin Ram
AAAI-97 Workshop on Robots, Softbots, Immobots: Theories of Action, Planning and Control, Providence, RI, July 1997www.cc.gatech.edu/faculty/ashwin/papers/er-97-03.pdf