Achieving network optima using Stackelberg routing strategies
IEEE/ACM Transactions on Networking (TON)
The dynamics of reinforcement learning in cooperative multiagent systems
AAAI '98/IAAI '98 Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence
Stackelberg scheduling strategies
STOC '01 Proceedings of the thirty-third annual ACM symposium on Theory of computing
Multiagent learning using a variable learning rate
Artificial Intelligence
Learning to play network games: does rationality yield nash equilibrium?
Learning to play network games: does rationality yield nash equilibrium?
Nash q-learning for general-sum stochastic games
The Journal of Machine Learning Research
Fairness and optimality in congestion games
Proceedings of the 6th ACM conference on Electronic commerce
Welfare maximization in congestion games
EC '06 Proceedings of the 7th ACM conference on Electronic commerce
From External to Internal Regret
The Journal of Machine Learning Research
STACS'99 Proceedings of the 16th annual conference on Theoretical aspects of computer science
On the price of anarchy and stability of correlated equilibria of linear congestion games,,
ESA'05 Proceedings of the 13th annual European conference on Algorithms
Learning to achieve socially optimal solutions in general-sum games
PRICAI'12 Proceedings of the 12th Pacific Rim international conference on Trends in Artificial Intelligence
Manipulating convention emergence using influencer agents
Autonomous Agents and Multi-Agent Systems
Learning influence in complex social networks
Proceedings of the 2013 international conference on Autonomous agents and multi-agent systems
| Hi-index | 0.01 |
In this paper, we investigate multi-agent learning (MAL) in a multi-agent resource selection problem (MARS) in which a large group of agents are competing for common resources. Since agents in such a setting are self-interested, MAL in MARS domains typically focuses on the convergence to a set of non-cooperative equilibria. As seen in the example of prisoner's dilemma, however, selfish equilibria are not necessarily optimal with respect to the natural objective function of a target problem, e.g., resource utilization in the case of MARS. Conversely, a centrally administered optimization of physically distributed agents is infeasible in many real-life applications such as transportation traffic problems. In order to explore the possibility for a middle ground solution, we analyze two types of costs for evaluating MAL algorithms in this context. The quality loss of a selfish algorithm can be quantitatively measured by the price of anarchy, i.e., the ratio of the objective function value of a selfish solution to that of an optimal solution. Analogously, we introduce the price of monarchy of a learning algorithm to quantify the practical cost of coordination in terms of communication cost. We then introduce a multi-agent social learning approach named A Few Good Agents (AFGA) that motivates self-interested agents to cooperate with one another to reduce the price of anarchy, while bounding the price of monarchy at the same time. A preliminary set of experiments on the El Farol bar problem, a simple example of MARS, show promising results.