A Framework for Mapping DRL Algorithms with Prioritized Replay Buffer onto Heterogeneous Platforms

Abstract

The computation primitives of DRL with Prioritized Replay Buffer include environment emulation, neural network inference, sampling from Prioritized Replay Buffer, updating Prioritized Replay Buffer and neural network training. The speed of running these primitives varies for various DRL algorithms, making a fixed mapping of DRL algorithms inefficient. In this work, we propose a framework for mapping DRL algorithms onto heterogeneous platforms consisting of a multi-core CPU, a GPU and a FPGA.

Yuan Meng

PhD Candidate in Computer Engineering

I co-optimize algorithm and hardware for deploying parallel AI workloads on heterogeneous platforms.