论文信息 - Reinforcement learning for autonomic network repair

Reinforcement learning for autonomic network repair

We report on our efforts to formulate autonomic network repair as a reinforcement-learning problem. Our implemented system is able to learn to efficiently restore network connectivity after a failure.

Michael L. Littman | Nishkam Ravi | E. Fenson | R. Howard

[1] Richard P. Martin,et al. Mendosis: A SAN-based Fault Injection Test-bed for the Construction of Highly Available Network Services , 2001 .

[2] Richard S. Sutton,et al. Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[3] Michael L. Littman,et al. An Instance-Based State Representation for Network Repair , 2004, AAAI.