CURL: Contrastive Unsupervised Representations for Reinforcement Learning [article]

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