PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

EPrints submitted by Nahum Shimkin

Click here to see user's record.

Number of EPrints submitted by this user: 2

Markov Decision Processes with Arbitrarily Varying Rewards
Jia Yuan Yu, Shie Mannor and Nahum Shimkin
Mathematics of Operations Research Volume 34, Number 3, pp. 737-757, 2009.

Adaptive-Resolution Reinforcement Learning with Efficient Exploration in Deterministic Domains
Andrey Bernstein and Nahum Shimkin
Machine Learning Journal 2009.