CURL: Contrastive Unsupervised Representations for Reinforcement Learning

2020-04-08 · Aravind Srinivas, Michael Laskin, Pieter Abbeel

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.

📄 PDF Abstract BibTeX arXiv:2004.04136

Code (7)

MishaLaskin/curl 공식 구현 pytorch

KarlXing/RL-Visual-Continuous-Control pytorch

aravindsrinivas/curl_rainbow pytorch

asparius/barlowrl pytorch

gijskoning/ReproducingCURL pytorch

microsoft/Mask-based-Latent-Reconstruction pytorch

opendilab/DI-engine pytorch

Tasks

Atari GamesAtari Games 100kContinuous Control Contrastive Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

CURL: Contrastive Unsupervised Representation Learning for Reinforcement Learning

2020-01-01 · ICML 2020 1 · Michael Laskin, Pieter Abbeel, Aravind Srinivas

Reinforcement Learning for control tasks where the agent learns from raw high dimensional pixels has proven to be difficult and sample-inefficient. Operating on high-dimensional observational input poses a challenging c…

Contrastive Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

CURLing the Dream: Contrastive Representations for World Modeling in Reinforcement Learning

2024-08-11 · Victor Augusto Kich, Jair Augusto Bottega, Raul Steinmetz, Ricardo Bedin Grando 외

In this work, we present Curled-Dreamer, a novel reinforcement learning algorithm that integrates contrastive learning into the DreamerV3 framework to enhance performance in visual reinforcement learning tasks. By incorp…

Contrastive Learning reinforcement-learning Reinforcement Learning

PAC-Bayesian Contrastive Unsupervised Representation Learning

2019-10-10 · Kento Nozawa, Pascal Germain, Benjamin Guedj

Contrastive unsupervised representation learning (CURL) is the state-of-the-art technique to learn representations (as a set of features) from unlabelled data. While CURL has collected several empirical successes recentl…

Representation Learning

M2CURL: Sample-Efficient Multimodal Reinforcement Learning via Self-Supervised Representation Learning for Robotic Manipulation

2024-01-30 · Fotios Lygerakis, Vedant Dave, Elmar Rueckert

One of the most critical aspects of multimodal Reinforcement Learning (RL) is the effective integration of different observation modalities. Having robust and accurate representations derived from these modalities is key…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Representation Learning+2

Masked Contrastive Representation Learning for Reinforcement Learning

2020-10-15 · Jinhua Zhu, Yingce Xia, Lijun Wu, Jiajun Deng 외

Improving sample efficiency is a key research problem in reinforcement learning (RL), and CURL, which uses contrastive learning to extract high-level features from raw pixels of individual video frames, is an efficient a…

Atari Games Contrastive Learning reinforcement-learning Reinforcement Learning+2