papers AI Learner
The Github is limit! Click to go to the new site.

Baconian: A Unified Opensource Framework for Model-Based Reinforcement Learning

2019-04-23
Linsen Dong, Guanyu Gao, Yuanlong Li, Yonggang Wen

Abstract

Model-Based Reinforcement Learning (MBRL) is one category of Reinforcement Learning (RL) methods which can improve sampling efficiency by modeling and approximating system dynamics. It has been widely adopted in the research of robotics, autonomous driving, etc. Despite its popularity, there still lacks some sophisticated and reusable opensource frameworks to facilitate MBRL research and experiments. To fill this gap, we develop a flexible and modularized framework, Baconian, which allows researchers to easily implement a MBRL testbed by customizing or building upon our provided modules and algorithms. Our framework can free the users from re-implementing popular MBRL algorithms from scratch thus greatly saves the users’ efforts.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.10762

PDF

http://arxiv.org/pdf/1904.10762


Similar Posts

Comments