## An exact distributed newton method for reinforcement learning

- Rasul Tutunov, Haitham Bou-Ammar, Ali Jadbabaie
- 2016 IEEE 55th Conference on Decision and Control…
- 2016

Highly Influenced

@inproceedings{Mokhtari2015NetworkN, title={Network Newton – Part II : Convergence Rate and Implementation}, author={Aryan Mokhtari and Qing Ling and Alejandro R. Ribeiro}, year={2015} }

- Published 2015

The use of network Newton methods for the decentralized optimization of a sum cost distributed through agents of a network is considered. Network Newton methods reinterpret distributed gradient descent as a penalty method, observe that the corresponding Hessian is sparse, and approximate the Newton step by truncating a Taylor expansion of the inverse Hessian. Truncating the series at K terms yields the NN-K that requires aggregating information from K hops away. Network Newton is introduced and… CONTINUE READING