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
Evolution and Optimum Seeking: The Sixth Generation
Evolution and Optimum Seeking: The Sixth Generation
An Algorithm for Distributed Reinforcement Learning in Cooperative Multi-Agent Systems
ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
A Cooperative Coevolutionary Approach to Function Optimization
PPSN III Proceedings of the International Conference on Evolutionary Computation. The Third Conference on Parallel Problem Solving from Nature: Parallel Problem Solving from Nature
Reinforcement learning of coordination in cooperative multi-agent systems
Eighteenth national conference on Artificial intelligence
Selecting informative actions improves cooperative multiagent learning
AAMAS '06 Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems
Theoretical Advantages of Lenient Learners: An Evolutionary Game Theoretic Perspective
The Journal of Machine Learning Research
The dynamics of reinforcement social learning in cooperative multiagent systems
IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
Hi-index | 0.00 |
In concurrent learning algorithms, an agent's perception of the joint search space depends on the actions currently chosen by the other agents. These perceptions change as each agent's action selection is influenced by its learning. We observe that agents that show lenience to their teammates achieve more accurate perceptions of the overall learning task. Additionally, lenience appears more beneficial at early stages of learning, when the agent's teammates are merely exploring their actions, and less helpful as the agents start to converge. We propose two multiagent learning algorithms where agents exhibit a variable degree of lenience, and we demonstrate their advantages in several coordination problems.