Plan2Explore: Plan to Explore via Self-Supervised World Models
A self-supervised reinforcement learning agent that tackles task-specific and the sample efficiency challenges.
self-supervised-learning reinforcement-learning plan2explore article code paper video arxiv:2005.05960 research

Reinforcement learning allows solving complex tasks, however, the learning tends to be task-specific and the sample efficiency remains a challenge. We present Plan2Explore, a self-supervised reinforcement learning agent that tackles both these challenges through a new approach to self-supervised exploration and fast adaptation to new tasks, which need not be known during exploration.

Don't forget to tag @ramanans1 in your comment, otherwise they may not be notified.

Authors community post
Robotics Master's student at University of Pennsylvania - Research Assistant at GRASP Lab
Share this project
Similar projects
Learning To Classify Images Without Labels
A two-step approach where feature learning and clustering are decoupled.
OpenSelfSup: Self-Supervised Learning Toolbox and Benchmark
An open source unsupervised representation learning toolbox based on PyTorch.
Self-supervised representation learning on videos
Everything you need to know about video-based approaches on self-supervised learning
The Illustrated Self-Supervised Learning
A visual introduction to self-supervised learning methods in Computer Vision