Reinforcement Learning for Adaptive Routing
Abstract
Reinforcement learning means learning a policy--a mapping of observations into actions--based on feedback from the environment. The learning can be viewed as browsing a set of policies while evaluating them by trial through interaction with the environment. We present an application of gradient ascent algorithm for reinforcement learning to a complex domain of packet routing in network communication and compare the performance of this algorithm to other routing methods on a benchmark problem.
- Publication:
-
arXiv e-prints
- Pub Date:
- March 2007
- DOI:
- 10.48550/arXiv.cs/0703138
- arXiv:
- arXiv:cs/0703138
- Bibcode:
- 2007cs........3138P
- Keywords:
-
- Computer Science - Machine Learning;
- Computer Science - Artificial Intelligence;
- Computer Science - Networking and Internet Architecture;
- C.2.1;
- C.2.2;
- C.2.4;
- C.2.6;
- F.1.1;
- I.2.6;
- I.2.8;
- I.2.9
- E-Print:
- In Proceedings of the Intnl Joint Conf on Neural Networks (IJCNN), 2002