NIPS Proceedingsβ

Doina Precup

16 Papers

  • Basis refinement strategies for linear value function approximation in MDPs (2015)
  • Data Generation as Sequential Decision Making (2015)
  • Learning with Pseudo-Ensembles (2014)
  • Optimizing Energy Production Using Policy Search and Predictive State Representations (2014)
  • Bellman Error Based Feature Generation using Random Projections on Sparse Spaces (2013)
  • Learning from Limited Demonstrations (2013)
  • On-line Reinforcement Learning Using Incremental Kernel-Based Stochastic Factorization (2012)
  • Value Pursuit Iteration (2012)
  • Reinforcement Learning using Kernel-Based Stochastic Factorization (2011)
  • Convergent Temporal-Difference Learning with Arbitrary Smooth Function Approximation (2009)
  • Bounding Performance Loss in Approximate MDP Homomorphisms (2008)
  • Off-policy Learning with Options and Recognizers (2005)
  • A Convergent Form of Approximate Policy Iteration (2002)
  • Improved Switching among Temporally Abstract Actions (1998)
  • Learning to Schedule Straight-Line Code (1997)
  • Multi-time Models for Temporally Abstract Planning (1997)