CURL: Contrastive Unsupervised Representations for Reinforcement Learning
This improves sample efficiency for reinforcement learning agents in complex visual domains, though it is incremental as it builds on existing contrastive learning techniques.
The paper tackles the problem of sample-efficient reinforcement learning from raw pixels by introducing CURL, which uses contrastive learning to extract features and achieves 1.9x and 1.2x performance gains over prior methods on benchmarks.
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 https://github.com/MishaLaskin/curl.