Technical Note: \cal Q-Learning
Machine Learning
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
Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Fast Planning in Stochastic Games
UAI '00 Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence
On the convergence of stochastic iterative dynamic programming algorithms
Neural Computation
Sequential optimality and coordination in multiagent systems
IJCAI'99 Proceedings of the 16th international joint conference on Artifical intelligence - Volume 1
Learning Multi-agent Strategies in Multi-stage Collaborative Games
IDEAL '02 Proceedings of the Third International Conference on Intelligent Data Engineering and Automated Learning
Hi-index | 0.01 |
An alternative approach to learning decision strategies in multi-state multiple agent systems is presented here. The method, which uses a game theoretic construction of "best response with error" does not rely on direct communication between the agents in the system. Limited experiments show that the method can find Nash equilibrium points at least for a 2 player multi-stage coordination game and converges more quickly than a comparable co-evolution method.