Skip to yearly menu bar Skip to main content


CURL: Contrastive Unsupervised Representations for Reinforcement Learning

Michael Laskin · Aravind Srinivas · Pieter Abbeel

Keywords: [ Deep Reinforcement Learning ] [ Representation Learning ] [ Algorithms ] [ Reinforcement Learning - Deep RL ]


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 Control 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

Chat is not available.