On the existence of fixed points for approximate value iteration and temporal-difference learning

A Generalized Kalman Filter for Fixed Point Approximation and Efficient Temporal-Difference Learning

Discrete Event Dynamic Systems

Performance Loss Bounds for Approximate Value Iteration with State Aggregation

Mathematics of Operations Research

An analysis of reinforcement learning with function approximation

Proceedings of the 25th international conference on Machine learning

Tuning continual exploration in reinforcement learning: An optimality property of the Boltzmann strategy

Neurocomputing

Using control theory for analysis of reinforcement learning and optimal policy properties in grid-world problems

ICIC'09 Proceedings of the Intelligent computing 5th international conference on Emerging intelligent computing technology and applications

Approximate Dynamic Programming via a Smoothed Linear Program

Operations Research

Dynamic policy programming

The Journal of Machine Learning Research

Policy oscillation is overshooting

Neural Networks