Data Structures for Deviation Payoffs

We present new data structures for representing symmetric normalform games. These data structures are optimized for efficiently computing the expected utility of each unilateral pure-strategy deviation from a symmetric mixed-strategy profile. The cumulative effect of numerous incremental innovations is a dramatic speedup in the computation of symmetric mixed-strategy Nash equilibria, making it practical to represent and solve games with dozens to hundreds of players. These data structures naturally extend to rolesymmetric and action-graph games with similar benefits.