NIPS Proceedings^β

Benjamin Van Roy

11 Papers

Learning to Optimize via Information-Directed Sampling (2014)

Model-based Reinforcement Learning and the Eluder Dimension (2014)

Near-optimal Reinforcement Learning in Factored MDPs (2014)

Efficient Exploration and Value Function Generalization in Deterministic Systems (2013)

Eluder Dimension and the Sample Complexity of Optimistic Exploration (2013)

(More) Efficient Reinforcement Learning via Posterior Sampling (2013)

Oblivious Equilibrium: A Mean Field Approximation for Large-Scale Dynamic Games (2005)

An Analysis of Turbo Decoding with Gaussian Densities (1999)

Analysis of Temporal-Diffference Learning with Function Approximation (1996)

Approximate Solutions to Optimal Stopping Problems (1996)

Stable LInear Approximations to Dynamic Programming for Stochastic Control Problems with Local Transitions (1995)