Unlike traditional reinforcement learning (RL), market-based RL is in principle applicable to worlds described by partially observable Markov Decision Processes (POMDPs), where an ...
Reactive planning using assumptions is a well-known approach to tackle complex planning problems for nondeterministic, partially observable domains. However, assumptions may be wr...
We present tractable, exact algorithms for learning actions' effects and preconditions in partially observable domains. Our algorithms maintain a propositional logical repres...
We identify a class of mechanical systems for which a globally exponentially stable reduced order observer can be designed. The class is characterized by (the solvability of) a set...
Aneesh Venkatraman, Romeo Ortega, Ioannis Sarras, ...
—This paper presents a method for learning decision theoretic models of human behaviors from video data. Our system learns relationships between the movements of a person, the co...