We present a decentralized, asynchronous market protocol for allocating and scheduling tasks among agents that contend for scarce resources, constrained by a hierarchical task dep...
cal maps provide a useful abstraction for robotic navigation and planning. Although stochastic mapscan theoreticallybe learned using the Baum-Welch algorithm,without strong prior ...
Stochastic games generalize Markov decision processes MDPs to a multiagent setting by allowing the state transitions to depend jointly on all player actions, and having rewards de...
Michael J. Kearns, Yishay Mansour, Satinder P. Sin...
Constructive learning algorithms offer an attractive approach for the incremental construction of near-minimal neural-network architectures for pattern classification. They help ov...
The performance of on-line algorithms for learning dichotomies is studied. In on-line learning, the number of examples P is equivalent to the learning time, since each example is ...