NIPS Proceedingsβ

Satinder P. Singh

24 Papers

  • Reward Design via Online Gradient Ascent (2010)
  • Simple Local Models for Complex Dynamical Systems (2008)
  • Off-policy Learning with Options and Recognizers (2005)
  • Approximately Efficient Online Mechanism Design (2004)
  • Intrinsically Motivated Reinforcement Learning (2004)
  • An MDP-Based Approach to Online Mechanism Design (2003)
  • A Nonlinear Predictive State Representation (2003)
  • An Efficient, Exact Algorithm for Solving Tree-Structured Graphical Games (2001)
  • Policy Gradient Methods for Reinforcement Learning with Function Approximation (1999)
  • Reinforcement Learning for Spoken Dialogue Systems (1999)
  • Experimental Results on Learning Stochastic Memoryless Policies for Partially Observable Markov Decision Processes (1998)
  • Finite-Sample Convergence Rates for Q-Learning and Indirect Algorithms (1998)
  • Improved Switching among Temporally Abstract Actions (1998)
  • Optimizing Admission Control while Ensuring Quality of Service in Multimedia Networks via Reinforcement Learning (1998)
  • How to Dynamically Merge Markov Decision Processes (1997)
  • Analytical Mean Squared Error Curves in Temporal Difference Learning (1996)
  • Predicting Lifetimes in Dynamically Allocated Memory (1996)
  • Reinforcement Learning for Dynamic Channel Allocation in Cellular Telephone Systems (1996)
  • Improving Policies without Measuring Merits (1995)
  • Reinforcement Learning Algorithm for Partially Observable Markov Decision Problems (1994)
  • Reinforcement Learning with Soft State Aggregation (1994)
  • Convergence of Stochastic Iterative Dynamic Programming Algorithms (1993)
  • Robust Reinforcement Learning in Motion Planning (1993)
  • The Efficient Learning of Multiple Task Sequences (1991)