A research team from MIT and MIT-IBM Watson AI Lab proposes Curious Representation Learning (CRL), a framework that learns to understand the surrounding environment by training a reinforcement learning (RL) agent to maximize the error of a representation learner to gain an incentive to explore the environment.

Here is a quick read: MIT & IBM ‘Curiosity’ Framework Explores Embodied Environments to Learn Task-Agnostic Visual Representations.

The paper Curious Representation Learning for Embodied Intelligence is on arXiv.



Source link