[2P1] [General Session] 7. Agent

[2P1-03] Parallelization of evolution of reinforcement learning agents using GPGPU

〇Yoshiki Senga¹, Kouichi Moriyama¹, Atsuko Mutoh¹, Tohgoroh Matsui², Inuzuka Nobuhiro¹ (1. Nagoya Institute of Technology, 2. Chubu University)

Keywords:GPGPU, AI, Reinforcement Learning

GPGPU is a parallel computation technology using GPU that has huge number of processor cores for parallelly
calculating colors of pixels on a monitor. In a previous work, we used GPGPU to parallelize many runs of reinforcement learning agents for calculating their tness in a simulation of evolution.
It speeded up the simulation surprisingly. However, the evolution part was sequentially run in CPU and the
communication between CPU and GPU happened in every generation. Hence, this work uses GPGPU to parallelize
the evolution part in addition to the tness calculation. It makes the simulation even faster due to parallelism and
the reduction of latency between CPU and GPU.