Name
Abstract | ||
|---|---|---|
Despite increasing deployment of agent technologies in several business and industry domains, user confidence in fully automated agent driven applications is noticeably lacking. The main reasons for such lack of trust in complete automation are scalability and nonexistence of reasonable guarantees in the performance of selfadapting software. In this paper we address the latter issue in the context of learning agents in a Multiagent System (MAS). Performance guarantees for most existing on-line Multiagent Learning (MAL) algorithms are realizable only in the limit, thereby seriously limiting its practical utility. Our goal is to provide certain meaningful guarantees about the performance of a learner in a MAS, while it is learning. In particular, we present a novel MAL algorithm that (i) converges to a best response against stationary opponents, (ii) converges to a Nash equilibrium in self-play and (iii) achieves a constant bounded expected regret at any time (no-average-regret asymptotically) in arbitrary sized general-sum games with non-negative payoffs, and against any number of opponents. |
Year | Venue | Keywords |
|---|---|---|
2004 | AAAI | certain meaningful guarantee,nash equilibrium,strategic interaction,complete automation,multiagent system,best response,performance guarantee,novel mal algorithm,automated agent,existing on-line multiagent learning,agent technology,performance bounded reinforcement,reinforcement learning |
Field | DocType | ISBN |
Mathematical optimization,Software deployment,Regret,Computer science,Best response,Automation,Artificial intelligence,Nash equilibrium,Machine learning,Scalability,Reinforcement learning,Bounded function | Conference | 0-262-51183-5 |
Citations | PageRank | References |
21 | 1.16 | 21 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Bikramjit Banerjee | 1 | 284 | 32.63 |
| Jing Peng | 2 | 673 | 48.37 |