Timezone: »

Diverse Randomized Agents Vote to Win
Albert Jiang · Leandro Soriano Marcolino · Ariel Procaccia · Tuomas Sandholm · Nisarg Shah · Milind Tambe

Thu Dec 11 11:00 AM -- 03:00 PM (PST) @ Level 2, room 210D

We investigate the power of voting among diverse, randomized software agents. With teams of computer Go agents in mind, we develop a novel theoretical model of two-stage noisy voting that builds on recent work in machine learning. This model allows us to reason about a collection of agents with different biases (determined by the first-stage noise models), which, furthermore, apply randomized algorithms to evaluate alternatives and produce votes (captured by the second-stage noise models). We analytically demonstrate that a uniform team, consisting of multiple instances of any single agent, must make a significant number of mistakes, whereas a diverse team converges to perfection as the number of agents grows. Our experiments, which pit teams of computer Go agents against strong agents, provide evidence for the effectiveness of voting when agents are diverse.

Author Information

Albert Jiang (USC)
Leandro Soriano Marcolino (University of Southern California)
Ariel Procaccia (Carnegie Mellon University)
Tuomas Sandholm (CMU, Strategic Machine, Strategy Robot, Optimized Markets)
Nisarg Shah (Carnegie Mellon University)
Milind Tambe (USC)

More from the Same Authors