A distributed version of Reinforcement Learning using MPI in order to speed-up the learning process. This project includes the usage of blocking and non-blocking communication tested on UPPMAX HPC Center.
alekodu/Distributed-Reinforcement-Learning
A distributed version of Reinforcement Learning using MPI in order to speed-up the learning process. This project includes the usage of blocking and non-blocking communication tested on UPPMAX HPC Center.
C