2011-05-01
Research note: Policy invariance under reward transformations for general-sum stochastic games
Publication
Publication
Journal of Artificial Intelligence Research , Volume 41 p. 397- 406
We extend the potential-based shapingmethod fromMarkov decision processes to multi-player general-sum stochastic games. We prove that the Nash equilibria in a stochastic game remains unchanged after potential-based shaping is applied to the environment. The property of policy invariance provides a possible way of speeding convergence when learning to play a stochastic game.
Additional Metadata | |
---|---|
dx.doi.org/10.1613/jair.3384 | |
Journal of Artificial Intelligence Research | |
Organisation | Department of Systems and Computer Engineering |
Lu, X. (Xiaosong), Schwartz, H.M, & Givigi Jr., S.N. (Sidney N.). (2011). Research note: Policy invariance under reward transformations for general-sum stochastic games. Journal of Artificial Intelligence Research, 41, 397–406. doi:10.1613/jair.3384
|