Efficient learning of multi-step best response
Proceedings of the fourth international joint conference on Autonomous agents and multiagent systems
Performance bounded reinforcement learning in strategic interactions
AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Efficient no-regret multiagent learning
AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 1
Hi-index | 0.00 |
Multiagent Learning (MAL) is significantly complicated relative to Machine Learning (ML) by the fact that multiple learners render each other's environments non-stationary. While ML focuses on learning a fixed target function, MAL deals with learning a "moving target function". In contrast to classical Reinforcement Learning, MAL deals with an extra level of uncertainty in the form of the behaviors of the other learners in the domain. Existing learning methods provide guarantees about the performance of the learners only in the limit since a learner approaches its desired behavior asymptotically. There is little insight into how well or how poorly an on-line learner can perform while it is learning. This is the core problem studied in this thesis, resulting in the following contributions.