NIPS Proceedingsβ

Benjamin Van Roy

12 Papers

  • Deep Exploration via Bootstrapped DQN (2016)
  • 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)