NIPS Proceedingsβ

Pascal Poupart

7 Papers

  • Cost-Sensitive Exploration in Bayesian Reinforcement Learning (2012)
  • Symbolic Dynamic Programming for Continuous State and Observation POMDPs (2012)
  • Automated Refinement of Bayes Networks' Parameters based on Test Ordering Constraints (2011)
  • Automated Hierarchy Discovery for Planning in Partially Observable Environments (2006)
  • VDCBPI: an Approximate Scalable Algorithm for Large POMDPs (2004)
  • Bounded Finite State Controllers (2003)
  • Value-Directed Compression of POMDPs (2002)