We study the problem of an apprentice learning to behave in an environment with an unknown reward function by observing the behavior of an expert. We follow on the work of Abbeel ...
: Automated deduction systems can considerably be improved by replacing axioms with special purpose inference mechanisms. For example replacing in resolution based systems certain ...
We present a simple two-person Bucket Game, based on throwing balls into buckets, and we discuss possible players’ strategies. We use these strategies to create an approximation ...
We present an algorithm to compute the (pre)-kernel of a TU-game N, v with a system of n 2 1 linear programming problems. In contrast to the algorithms using convergence methods t...
Children do not learn the meanings of words from parsing and understanding gigabytes of text; instead meanings are learned from competent speakers who relate language to what'...