2020
ICML
ICML 2020
CURL: Contrastive Unsupervised Representations for Reinforcement Learning
Abstract
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://www.github.com/MishaLaskin/curl.
🌉
Interdisciplinary Bridge
— Machine Learning and Reinforcement Learning
📈
Trend Setter
— Contrastive Learning
🧭
Keyword Pioneer
— unsupervised representation
🐣
Hot Topic Early Bird
— contrastive learning
🐝
Cross-Pollinator
— Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Speech & Audio
Authors
Topics
Machine Learning > Core Methods > Representation Learning
Machine Learning > Learning Types > Contrastive Learning
Reinforcement Learning > Methods > Deep RL
Deep Learning > Learning Types > Self-Supervised Learning
Deep Learning > Learning Types > Contrastive Learning
Deep Learning > Learning Types > Reinforcement Learning