Predictive state representations (PSRs) have recently been proposed as an alternative to partially observable Markov decision processes (POMDPs) for representing the state of a dy...
Matthew Rosencrantz, Geoffrey J. Gordon, Sebastian...
In large multiagent games, partial observability, coordination, and credit assignment persistently plague attempts to design good learning algorithms. We provide a simple and efï¬...
Partially Observable Markov Decision Processes (POMDPs) have succeeded in planning domains that require balancing actions that increase an agent's knowledge and actions that ...
Abstract. We report our work towards building user models of learner’s development based upon evidence of their interactions with an e-learning website composed of multimedia lea...
Learning general truths from the observation of simple domains and, further, learning how to use this knowledge are essential capabilities for any intelligent agent to understand ...
Paulo Santos, Derek R. Magee, Anthony G. Cohn, Dav...