On-Line Adaptation Of A Signal Predistorter Through Dual Reinforcement Learning (1996)
Several researchers have demonstrated how neural networks can be trained to compensate for nonlinear signal distortion in e.g. digital satellite communications systems. These networks, however, require that both the original signal and its distorted version are known. Therefore, they have to be trained off-line, and they cannot adapt to changing channel characteristics. In this paper, a novel dual reinforcement learning approach is proposed that can adapt on-line while the system is performing. Assuming that the channel characteristics are the same in both directions, two predistorters at each end of the communication channel co-adapt using the output of the other predistorter to determine their own reinforcement. Using the common Volterra Series model to simulate the channel, the system is shown to successfully learn to compensate for distortions up to 30%, which is significantly higher than what might be expected in an actual channel.
In Lorenza Saitta, editors, Machine Learning: Proceedings of the 13th Annual Conference (Bari, Italy), 175-181, 1996. San Francisco, CA: Morgan Kaufmann.

Shailesh Kumar Masters Alumni
Risto Miikkulainen Faculty risto [at] cs utexas edu