C2RL: Convolutional-Contrastive Learning for Reinforcement Learning Based on Self-Pretraining for Strong Augmentation

C2RL: Convolutional-Contrastive Learning for Reinforcement Learning Based on Self-Pretraining for Strong Augmentation

Reinforcement learning agents that have not been seen during training must be robust in test environments. However, the generalization problem is challenging to solve in reinforcement learning using high-dimensional images as the input. The addition of a self-supervised learning framework with data...

Full description

Bibliographic Details
Main Authors: Sanghoon Park, Jihun Kim, Han-You Jeong, Tae-Kyoung Kim, Jinwoo Yoo
Format: Article
Language:English
Published: MDPI AG 2023-05-01
Series:Sensors
Subjects:
deep reinforcement learning
self-supervised learning
contrastive learning
generalization
data augmentation
network randomization
Online Access:https://www.mdpi.com/1424-8220/23/10/4946

Internet

https://www.mdpi.com/1424-8220/23/10/4946

Similar Items