QL2, a simple reinforcement learning scheme for two-player zero-sum Markov games
(2008) Neurocomputing — Vol. 72, n° 7-9, p. 1494-1507 (2008)
Files
No attached file found for this publication.
Details
- Authors
- Affiliations
Louvain School of Management Operations and Information
Citations
Frénay, B., & Saerens, M. (2008). QL2, a simple reinforcement learning scheme for two-player zero-sum Markov games. Neurocomputing, 72(7-9), 1494-1507. https://hdl.handle.net/2078.5/249958 (Original work published 2008)