“CURL: Contrastive Unsupervised Representations for Reinforcement Learning”, 2020-04-08 (; similar):
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 1.9× and 1.2× 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 Github.