Visual Pretraining via Contrastive Predictive Model for Pixel-Based Reinforcement Learning

Visual Pretraining via Contrastive Predictive Model for Pixel-Based Reinforcement Learning

In an attempt to overcome the limitations of reward-driven representation learning in vision-based reinforcement learning (RL), an unsupervised learning framework referred to as the visual pretraining via contrastive predictive model (VPCPM) is proposed to learn the representations detached from the...

Full description

Bibliographic Details
Main Authors: Tung M. Luu, Thang Vu, Thanh Nguyen, Chang D. Yoo
Format: Article
Language:English
Published: MDPI AG 2022-08-01
Series:Sensors
Subjects:
representation learning
vision-based deep reinforcement learning
deep reinforcement learning
sample efficiency
Online Access:https://www.mdpi.com/1424-8220/22/17/6504

Internet

https://www.mdpi.com/1424-8220/22/17/6504

Similar Items