On No-Regret Learning, Fictitious Play, and Nash Equilibrium
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Efficient algorithms for online decision problems
Journal of Computer and System Sciences - Special issue: Learning theory 2003
Proceedings of the twenty-fifth annual ACM symposium on Principles of distributed computing
Multi-agent learning for engineers
Artificial Intelligence
Efficient no-regret multiagent learning
AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 1
Payoff-Based Dynamics for Multiplayer Weakly Acyclic Games
SIAM Journal on Control and Optimization
Meta-level Control of Multiagent Learning in Dynamic Repeated Resource Sharing Problems
PRICAI '08 Proceedings of the 10th Pacific Rim International Conference on Artificial Intelligence: Trends in Artificial Intelligence
Multiagent learning in large anonymous games
Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems - Volume 2
Cooperative control and potential games
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
An architectural view of game theoretic control
ACM SIGMETRICS Performance Evaluation Review
Multiagent learning in large anonymous games
Journal of Artificial Intelligence Research
On the existence of pure strategy nash equilibria in integer-splittable weighted congestion games
SAGT'11 Proceedings of the 4th international conference on Algorithmic game theory
Distributed selfish load balancing on networks
Proceedings of the twenty-second annual ACM-SIAM symposium on Discrete Algorithms
Recursive adaptation of stepsize parameter for non-stationary environments
ALA'09 Proceedings of the Second international conference on Adaptive and Learning Agents
Automatica (Journal of IFAC)
A classification of weakly acyclic games
SAGT'12 Proceedings of the 5th international conference on Algorithmic Game Theory
Hedonic coalition formation for optimal deployment
Automatica (Journal of IFAC)
Hi-index | 0.00 |
No-regret algorithms have been proposed to control a wide variety of multi-agent systems. The appeal of no-regret algorithms is that they are easily implementable in large scale multi-agent systems because players make decisions using only retrospective or "regret based" information. Furthermore, there are existing results proving that the collective behavior will asymptotically converge to a set of points of "no-regret" in any game. We illustrate, through a simple example, that no-regret points need not reflect desirable operating conditions for a multi-agent system. Multi-agent systems often exhibit an additional structure (i.e. being "weakly acyclic") that has not been exploited in the context of no-regret algorithms. In this paper, we introduce a modification of the traditional no-regret algorithms by (i) exponentially discounting the memory and (ii) bringing in a notion of inertia in players' decision process. We show how these modifications can lead to an entire class of regret based algorithms that provide almost sure convergence to a pure Nash equilibrium in any weakly acyclic game.