M
Michael Kearns
Researcher at University of Pennsylvania
Publications - 278
Citations - 25590
Michael Kearns is an academic researcher from University of Pennsylvania. The author has contributed to research in topics: Reinforcement learning & Stability (learning theory). The author has an hindex of 77, co-authored 251 publications receiving 23200 citations. Previous affiliations of Michael Kearns include AT&T Labs & Alcatel-Lucent.
Papers
More filters
Book
An Introduction to Computational Learning Theory
Michael Kearns,Umesh Vazirani +1 more
TL;DR: The probably approximately correct learning model Occam's razor the Vapnik-Chervonenkis dimension weak and strong learning learning in the presence of noise inherent unpredictability reducibility in PAC learning learning finite automata is described.
Proceedings Article
Near-Optimal Reinforcement Learning in Polynominal Time
Michael Kearns,Satinder Singh +1 more
TL;DR: New algorithms for reinforcement learning are presented and it is proved that they have polynomial bounds on the resources required to achieve near-optimal return in general Markov decision processes.
Journal ArticleDOI
Near-Optimal Reinforcement Learning in Polynomial Time
Michael Kearns,Satinder Singh +1 more
TL;DR: In this paper, the authors show that the number of actions required to approach the optimal return is lower bounded by the mixing time of the optimal policy (in the undiscounted case) or by the horizon time T in the discounted case.
Proceedings Article
Graphical models for game theory
TL;DR: The main result is a provably correct and efficient algorithm for computing approximate Nash equilibria in one-stage games represented by trees or sparse graphs.
Proceedings ArticleDOI
Efficient noise-tolerant learning from statistical queries
TL;DR: This paper formalizes a new but related model of learning from statistical queries, and demonstrates the generality of the statistical query model, showing that practically every class learnable in Valiant’s model and its variants can also be learned in the new model (and thus can be learning in the presence of noise).