350 search results - page 4 / 70 » On Strategy Improvement Algorithms for Simple Stochastic Gam... |
ICML
1998
IEEE
15 years 10 months ago
1998
IEEE
In this paper, we adopt general-sum stochastic games as a framework for multiagent reinforcement learning. Our work extends previous work by Littman on zero-sum stochastic games t...
SIGECOM
2003
ACM
15 years 2 months ago
2003
ACM
We prove the existence of -Nash equilibrium strategies with support logarithmic in the number of pure strategies. We also show that the payoffs to all players in any (exact) Nash...
CORR
2008
Springer
14 years 9 months ago
2008
Springer
We consider concurrent games played on graphs. At every round of the game, each player simultaneously and independently selects a move; the moves jointly determine the transition ...
TON
2008
14 years 9 months ago
2008
Distributed power control is an important issue in wireless networks. Recently, noncooperative game theory has been applied to investigate interesting solutions to this problem. Th...
110
click to vote
CSL
2008
Springer
14 years 11 months ago
2008
Springer
This paper presents a novel strategy improvement algorithm for parity and payoff games, which is guaranteed to select, in each improvement step, an optimal combination of local str...