Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems

05/04/2020
by   Sergey Levine, et al.
29

In this tutorial article, we aim to provide the reader with the conceptual tools needed to get started on research on offline reinforcement learning algorithms: reinforcement learning algorithms that utilize previously collected data, without additional online data collection. Offline reinforcement learning algorithms hold tremendous promise for making it possible to turn large datasets into powerful decision making engines. Effective offline reinforcement learning methods would be able to extract policies with the maximum possible utility out of the available data, thereby allowing automation of a wide range of decision-making domains, from healthcare and education to robotics. However, the limitations of current algorithms make this difficult. We will aim to provide the reader with an understanding of these challenges, particularly in the context of modern deep reinforcement learning methods, and describe some potential solutions that have been explored in recent work to mitigate these challenges, along with recent applications, and a discussion of perspectives on open problems in the field.

READ FULL TEXT

Authors

page 27

page 28

page 30

06/09/2022

Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations

Offline reinforcement learning has shown great promise in leveraging lar...
03/02/2022

A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems

With the widespread adoption of deep learning, reinforcement learning (R...
11/29/2020

Offline Reinforcement Learning Hands-On

Offline Reinforcement Learning (RL) aims to turn large datasets into pow...
05/19/2022

Data Valuation for Offline Reinforcement Learning

The success of deep reinforcement learning (DRL) hinges on the availabil...
11/26/2021

Measuring Data Quality for Dataset Selection in Offline Reinforcement Learning

Recently developed offline reinforcement learning algorithms have made i...
12/12/2012

The Thing That We Tried Didn't Work Very Well : Deictic Representation in Reinforcement Learning

Most reinforcement learning methods operate on propositional representat...
10/10/2021

A Closer Look at Advantage-Filtered Behavioral Cloning in High-Noise Datasets

Recent Offline Reinforcement Learning methods have succeeded in learning...

Code Repositories

DBRL

Dataset Batch(offline) Reinforcement Learning for recommender system


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.