NIPS Proceedingsβ

Sridhar Mahadevan

7 Papers

  • Projected Natural Actor-Critic (2013)
  • Regularized Off-Policy TD-Learning (2012)
  • Basis Construction from Power Series Expansions of Value Functions (2010)
  • Value Function Approximation with Diffusion Wavelets and Laplacian Eigenfunctions (2005)
  • Coarticulation in Markov Decision Processes (2004)
  • Learning to Take Concurrent Actions (2002)
  • Hierarchical Memory-Based Reinforcement Learning (2000)