OGBench: Benchmarking Offline Goal-Conditioned RL

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Park, Seohong, Frans, Kevin, Eysenbach, Benjamin, Levine, Sergey
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916612757520384
author Park, Seohong
Frans, Kevin
Eysenbach, Benjamin
Levine, Sergey
author_facet Park, Seohong
Frans, Kevin
Eysenbach, Benjamin
Levine, Sergey
contents Offline goal-conditioned reinforcement learning (GCRL) is a major problem in reinforcement learning (RL) because it provides a simple, unsupervised, and domain-agnostic way to acquire diverse behaviors and representations from unlabeled data without rewards. Despite the importance of this setting, we lack a standard benchmark that can systematically evaluate the capabilities of offline GCRL algorithms. In this work, we propose OGBench, a new, high-quality benchmark for algorithms research in offline goal-conditioned RL. OGBench consists of 8 types of environments, 85 datasets, and reference implementations of 6 representative offline GCRL algorithms. We have designed these challenging and realistic environments and datasets to directly probe different capabilities of algorithms, such as stitching, long-horizon reasoning, and the ability to handle high-dimensional inputs and stochasticity. While representative algorithms may rank similarly on prior benchmarks, our experiments reveal stark strengths and weaknesses in these different capabilities, providing a strong foundation for building new algorithms. Project page: https://seohong.me/projects/ogbench
format Preprint
id arxiv_https___arxiv_org_abs_2410_20092
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle OGBench: Benchmarking Offline Goal-Conditioned RL
Park, Seohong
Frans, Kevin
Eysenbach, Benjamin
Levine, Sergey
Machine Learning
Artificial Intelligence
Offline goal-conditioned reinforcement learning (GCRL) is a major problem in reinforcement learning (RL) because it provides a simple, unsupervised, and domain-agnostic way to acquire diverse behaviors and representations from unlabeled data without rewards. Despite the importance of this setting, we lack a standard benchmark that can systematically evaluate the capabilities of offline GCRL algorithms. In this work, we propose OGBench, a new, high-quality benchmark for algorithms research in offline goal-conditioned RL. OGBench consists of 8 types of environments, 85 datasets, and reference implementations of 6 representative offline GCRL algorithms. We have designed these challenging and realistic environments and datasets to directly probe different capabilities of algorithms, such as stitching, long-horizon reasoning, and the ability to handle high-dimensional inputs and stochasticity. While representative algorithms may rank similarly on prior benchmarks, our experiments reveal stark strengths and weaknesses in these different capabilities, providing a strong foundation for building new algorithms. Project page: https://seohong.me/projects/ogbench
title OGBench: Benchmarking Offline Goal-Conditioned RL
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2410.20092