We study the information content of equilibrium prices using the market communication model of Deng, Papadimitriou, and Safra [4]. We show that, in the worst case, communicating an...
Manyproblems,such as the sliding-tile puzzles, generate searchtrees wheredifferent nodeshavedifferent numbersof children, in this case dependingon the position of the blank. Wesho...
The effects of distinct agent interaction and activation structures are compared and contrasted in several multi-agent models of social phenomena. Random graphs and lattices repre...
We present tractable, exact algorithms for learning actions' effects and preconditions in partially observable domains. Our algorithms maintain a propositional logical repres...
In the Markov decision process (MDP) formalization of reinforcement learning, a single adaptive agent interacts with an environment defined by a probabilistic transition function....