Critic Regularized Regression

Offline reinforcement learning (RL), also known as batch RL, offers the prospect of policy optimization from large pre-recorded datasets without online environment interaction. It addresses challenges with regard to the cost of data collection and safety, both of which are particularly pertinent to real-world applications of RL. Unfortunately, most off-policy algorithms perform poorly when learning from a fixed dataset. In this paper, we propose a novel offline RL algorithm to learn policies from data using a form of critic-regularized regression (CRR). We find that CRR performs surprisingly well and scales to tasks with high-dimensional state and action spaces -- outperforming several state-of-the-art offline RL algorithms by a significant margin on a wide range of benchmark tasks.

Authors

• Ziyu Wang - Huawei Technologies Ltd.
• Alexander Novikov
• Konrad Zolna
• Josh S. Merel
• Jost Tobias Springenberg
• Scott E. Reed
• Bobak Shahriari
• Noah Siegel
• Caglar Gulcehre
• Nicolas Heess
• Nando de Freitas University of British Columbia

Keywords

No keywords are indexed for this paper.