Convergence of synchronous reinforcement learning with linear function approximation - researchr publication related

researchr

You are not signed in
Sign in
Sign up

Artur Merke, Ralf Schoknecht. Convergence of synchronous reinforcement learning with linear function approximation. In Carla E. Brodley, editor, Machine Learning, Proceedings of the Twenty-first International Conference (ICML 2004), Banff, Alberta, Canada, July 4-8, 2004. Volume 69 of ACM International Conference Proceeding Series, ACM, 2004. [doi]

The following publications are possibly variants of this publication:

A Necessary Condition of Convergence for Reinforcement Learning with Function ApproximationArtur Merke, Ralf Schoknecht. icml 2002: 411-418

Optimality of Reinforcement Learning Algorithms with Linear Function ApproximationRalf Schoknecht. nips 2003: 1555-1562 [doi]

Convergent Combinations of Reinforcement Learning with Linear Function ApproximationRalf Schoknecht, Artur Merke. nips 2003: 1579-1586 [doi]

runs on WebDSL