Steven J. Bradtke

Publications by Year

Research Areas

Reinforcement Learning in Robotics, Neural Networks and Applications, AI-based Problem Solving and Planning, Advanced Adaptive Filtering Techniques, Adaptive Dynamic Programming Control

Most-Cited Works

• → Learning to act using real-time dynamic programming(1995)1,105 cited
• → Linear Least-Squares algorithms for temporal difference learning(1996)638 cited
• → Adaptive linear quadratic control using policy iteration(2005)414 cited
• Reinforcement Learning Methods for Continuous-Time Markov Decision Problems(1994)
• Reinforcement Learning Applied to Linear Quadratic Regulation(1992)
• → Incremental dynamic programming for on-line adaptive optimal control(1995)38 cited
• Some experiments with case-based search(1988)