Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
R-max - a general polynomial time algorithm for near-optimal reinforcement learning
The Journal of Machine Learning Research
Efficient learning equilibrium
Artificial Intelligence
Selfish routing with incomplete information
Proceedings of the seventeenth annual ACM symposium on Parallelism in algorithms and architectures
Resource selection games with unknown number of players
AAMAS '06 Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems
Learning equilibrium as a generalization of learning to optimize
Artificial Intelligence
Optimal efficient learning equilibrium: imperfect monitoring in symmetric games
AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 2
Rational and convergent learning in stochastic games
IJCAI'01 Proceedings of the 17th international joint conference on Artificial intelligence - Volume 2
STACS'99 Proceedings of the 16th annual conference on Theoretical aspects of computer science
Price of anarchy of network routing games with incomplete information
WINE'05 Proceedings of the First international conference on Internet and Network Economics
Learning equilibria in repeated congestion games
Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems - Volume 1
| Hi-index | 0.00 |
We consider a resource selection game with incomplete information about the resource-cost functions. All the players know is the set of players, an upper bound on the possible costs, and that the cost functions are positive and nondecreasing. The game is played repeatedly and after every stage each player observes her cost, and the actions of all players. For every Ε 0 we prove the existence of a learning Ε-equilibrium, which is a profile of algorithms, one for each player such that a unilateral deviation of a player is, up to ε not beneficial for her regardless of the actual cost functions. Furthermore, the learning eqUilibrium yields an optimal social cost.