A Framework for Mapping DRL Algorithms With Prioritized Replay Buffer Onto Heterogeneous Platforms-Reference-Cited by-同舟云学术

A Framework for Mapping DRL Algorithms With Prioritized Replay Buffer Onto Heterogeneous Platforms

Author:

Zhang Chi¹^ORCID,Meng Yuan²^ORCID,Prasanna Viktor²^ORCID

Affiliation:

1. Department of Computer Science, University of Southern California, Los Angeles, CA, USA

2. Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA

Funder

NSF

AMD Xilinx

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Computational Theory and Mathematics,Hardware and Architecture,Signal Processing

Link

Reference33 articles.

1. cuDNN: Efficient primitives for deep learning;chetlur,2014

2. Pytorch: An imperative style, high-performance deep learning library;paszke;Proc Int Conf Neural Inf Process,2019

3. Continuous control with deep reinforcement learning;lillicrap,2016

4. Playing atari with deep reinforcement learning;mnih,2013

Cited by 6 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献