SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.15134 · NeurIPS · 2020

Critic Regularized Regression

Nicolas Heess, Ziyu Wang, Alexander Novikov, Konrad Żołna, Josh Merel, Jost Springenberg, Scott Reed, Noah Siegel

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2006.15134")
get_code_for_paper("2006.15134")
have("2006.15134")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2006.15134.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2006.15134.svg)](https://syntology.ai/paper/2006.15134)

Connect an agent — have() is free.