NIPS Proceedingsβ

Richard S. Sutton

19 Papers

  • Universal Option Models (2014)
  • Weighted importance sampling for off-policy learning with linear function approximation (2014)
  • Convergent Temporal-Difference Learning with Arbitrary Smooth Function Approximation (2009)
  • Multi-Step Dyna Planning for Policy Evaluation and Control (2009)
  • A computational model of hippocampal function in trace conditioning (2008)
  • A Convergent $O(n)$ Temporal-difference Algorithm for Off-policy Learning with Linear Function Approximation (2008)
  • Incremental Natural Actor-Critic Algorithms (2007)
  • iLSTD: Eligibility Traces and Convergence Analysis (2006)
  • Off-policy Learning with Options and Recognizers (2005)
  • Temporal Abstraction in Temporal-difference Networks (2005)
  • Temporal-Difference Networks (2004)
  • Predictive Representations of State (2001)
  • Policy Gradient Methods for Reinforcement Learning with Function Approximation (1999)
  • Improved Switching among Temporally Abstract Actions (1998)
  • Learning Instance-Independent Value Functions to Enhance Local Search (1998)
  • Multi-time Models for Temporally Abstract Planning (1997)
  • Generalization in Reinforcement Learning: Successful Examples Using Sparse Coarse Coding (1995)
  • Iterative Construction of Sparse Polynomial Approximations (1991)
  • Integrated Modeling and Control Based on Reinforcement Learning and Dynamic Programming (1990)