Sciweavers

50 search results - page 3 / 10
» Nash Convergence of Gradient Dynamics in General-Sum Games
Sort
View
WINE
2009
Springer
127views Economy» more  WINE 2009»
14 years 5 months ago
Nash Dynamics in Congestion Games with Similar Resources
We study convergence of ε-Nash dynamics in congestion games when delay functions of all resources are similar. Delay functions are said to be similar if their values are within a...
Anand Bhalgat, Tanmoy Chakraborty, Sanjeev Khanna
ANOR
2005
80views more  ANOR 2005»
13 years 10 months ago
Entropic Penalties in Finite Games
The main objects here are finite-strategy games in which entropic terms are subtracted from the payoffs. After such subtraction each Nash equilibrium solves an explicit, unconstra...
Sjur Didrik Flåm, E. Cavazzuti
ATAL
2003
Springer
14 years 4 months ago
Towards a pareto-optimal solution in general-sum games
Multiagent learning literature has investigated iterated twoplayer games to develop mechanisms that allow agents to learn to converge on Nash Equilibrium strategy profiles. Such ...
Sandip Sen, Stéphane Airiau, Rajatish Mukhe...
SIGECOM
2010
ACM
173views ECommerce» more  SIGECOM 2010»
13 years 11 months ago
Approximating pure nash equilibrium in cut, party affiliation, and satisfiability games
Cut games and party affiliation games are well-known classes of potential games. Schaffer and Yannakakis showed that computing pure Nash equilibrium in these games is PLScomplete....
Anand Bhalgat, Tanmoy Chakraborty, Sanjeev Khanna
AAAI
2010
14 years 6 days ago
Multi-Agent Learning with Policy Prediction
Due to the non-stationary environment, learning in multi-agent systems is a challenging problem. This paper first introduces a new gradient-based learning algorithm, augmenting th...
Chongjie Zhang, Victor R. Lesser