English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Offline reinforcement learning proposes to learn policies from largecollected datasets without interacting with the physical environment. Thesealgorithms have made it possible to learn useful skills from data that can thenbe deployed in the environment in real-world settings where interactions may becostly or dangerous, such as autonomous driving or factories. However, currentalgorithms overfit to the dataset they are trained on and exhibit poorout-of-distribution generalization to the environment when deployed. In thispaper, we study the effectiveness of performing data augmentations on the statespace, and study 7 different augmentation schemes and how they behave withexisting offline RL algorithms. We then combine the best data performingaugmentation scheme with a state-of-the-art Q-learning technique, and improvethe function approximation of the Q-networks by smoothening out the learnedstate-action space. We experimentally show that using this Surprisingly SimpleSelf-Supervision technique in RL (S4RL), we significantly improve over thecurrent state-of-the-art algorithms on offline robot learning environments suchas MetaWorld [1] and RoboSuite [2,3], and benchmark datasets such as D4RL [4].

S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning