This paper addresses the issue of policy evaluation in Markov Decision Processes, using linear function approximation. It provides a unified view of algorithms such as TD(), LSTD()...
Boolean satisfiability problems are an important benchmark for questions about complexity, algorithms, heuristics and threshold phenomena. Recent work on heuristics, and the satis...
Parikshit Gopalan, Phokion G. Kolaitis, Elitza N. ...
of proposed research. A short bibliography is optional. Domain theory has been developed around 40 years since 1970s by D. Scott, and S. Abramsky revealed the "junction betwee...
Let X be a discrete random variable with support S and f : S S be a bijection. Then it is wellknown that the entropy of X is the same as the entropy of f(X). This entropy preserva...
We investigate here concept learning from incomplete examples. Our first purpose is to discuss to what extent logical learning settings have to be modified in order to cope with da...