DeepAI AI Chat
Log In Sign Up

Benchmarks for Deep Off-Policy Evaluation

by   Justin Fu, et al.

Off-policy evaluation (OPE) holds the promise of being able to leverage large, offline datasets for both evaluating and selecting complex policies for decision making. The ability to learn offline is particularly important in many real-world domains, such as in healthcare, recommender systems, or robotics, where online data collection is an expensive and potentially dangerous process. Being able to accurately evaluate and select high-performing policies without requiring online interaction could yield significant benefits in safety, time, and cost for these applications. While many OPE methods have been proposed in recent years, comparing results between papers is difficult because currently there is a lack of a comprehensive and unified benchmark, and measuring algorithmic progress has been challenging due to the lack of difficult evaluation tasks. In order to address this gap, we present a collection of policies that in conjunction with existing offline datasets can be used for benchmarking off-policy evaluation. Our tasks include a range of challenging high-dimensional continuous control problems, with wide selections of datasets and policies for performing policy selection. The goal of our benchmark is to provide a standardized measure of progress that is motivated from a set of principles designed to challenge and test the limits of existing OPE methods. We perform an evaluation of state-of-the-art algorithms and provide open-source access to our data and code to foster future research in this area.


page 4

page 5

page 15


Evaluating the Robustness of Off-Policy Evaluation

Off-policy Evaluation (OPE), or offline evaluation in general, evaluates...

Active Offline Policy Selection

This paper addresses the problem of policy selection in domains with abu...

D4RL: Datasets for Deep Data-Driven Reinforcement Learning

The offline reinforcement learning (RL) problem, also referred to as bat...

Offline Recommender System Evaluation under Unobserved Confounding

Off-Policy Estimation (OPE) methods allow us to learn and evaluate decis...

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

In this tutorial article, we aim to provide the reader with the conceptu...

Data-Driven Off-Policy Estimator Selection: An Application in User Marketing on An Online Content Delivery Service

Off-policy evaluation (OPE) is the method that attempts to estimate the ...

Dungeons and Data: A Large-Scale NetHack Dataset

Recent breakthroughs in the development of agents to solve challenging s...