Abstract | ||
---|---|---|
A central question in game theory, learning, and other fields is how a rational intel- ligent agent should behave in a complex environment, given that it cannot perform unbounded computations. We study strategic aspects of this question by formulat- ing a simple model of a game with additional costs (computational or otherwise) for each strategy. While a zero-sum game with strategy costs is no longer zero- sum, we show that its Nash equilibria have an interesting structure and the game has a new type of "value." We also show that potential games with strategy costs remain potential games. Both zero-sum and potential games with strategy costs maintain a very appealing property: simple learning dynamics converge to Nash equilibrium. |
Year | Venue | Keywords |
---|---|---|
2006 | NIPS | nash equilibrium,game theory,nash equilibria,working paper,bounded rationality,zero sum game |
Field | DocType | Citations |
Coordination game,Combinatorial game theory,Mathematical economics,Mathematical optimization,Computer science,Best response,Repeated game,Game theory,Symmetric game,Sequential game,Bondareva–Shapley theorem | Conference | 6 |
PageRank | References | Authors |
0.50 | 5 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Eli Ben-Sasson | 1 | 1641 | 86.98 |
Adam Tauman Kalai | 2 | 1620 | 115.10 |
Ehud Kalai | 3 | 135 | 44.65 |