Internet Archive Scholar

CURL: Contrastive Unsupervised Representations for Reinforcement Learning [article]

Aravind Srinivas, Michael Laskin, Pieter Abbeel
2020 arXiv   pre-print

Preserved Fulltext

Web Archive Capture PDF (4.1 MB)
https://web.archive.org/web/20200929024012/https://arxiv.org/pdf/2004.04136v4.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Other Versions

2020 pre-print
arXiv:2004.04136v3 fatcat:jbw5cqbt5bbvvhptmvyfffivly
2020 pre-print
arXiv:2004.04136v1 fatcat:z7fzhhjnfjbxxms3hbkgmvxxvq
2020 pre-print
arXiv:2004.04136v2 fatcat:mj4cuph755gljari65jgnxoste
We present CURL: Contrastive Unsupervised Representations for Reinforcement Learning. CURL extracts high-level features from raw pixels using contrastive learning and performs off-policy control on top of the extracted features. CURL outperforms prior pixel-based methods, both model-based and model-free, on complex tasks in the DeepMind Control Suite and Atari Games showing 1.9x and 1.2x performance gains at the 100K environment and interaction steps benchmarks respectively. On the DeepMind
more » ... rol Suite, CURL is the first image-based algorithm to nearly match the sample-efficiency of methods that use state-based features. Our code is open-sourced and available at https://github.com/MishaLaskin/curl.
arXiv:2004.04136v4 fatcat:fek5n6xsn5f23efn2anivekvde
Multiple Versions
Citation

Aravind Srinivas, Michael Laskin, Pieter Abbeel. "CURL: Contrastive Unsupervised Representations for Reinforcement Learning." arXiv (2020)