SURREAL

Submitted by on Nov 27 2021 } Suggest Revision
By: Linxi Fan*, Yuke Zhu*, Jiren Zhu, Zihua Liu, Anchit Gupta, Joan Creus-Costa, Silvio Savarese, Li Fei-Fei
Resource Type:
Project
License:
MIT
Language:
Python
Data Format:

Description

SURREAL is an open-source scalable framework that supports state of-the-art distributed reinforcement learning algorithms. It is a principled distributed learning formulation that accommodates both on-policy and off-policy learning. Also related is the SURREAL Robotics Suite, an accessible set of benchmarking tasks in physical simulation for reproducible robot manipulation research.
Post comment
Cancel