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 (RL) aims to learn a policy using onlypre-collected and fixed data. Although avoiding the time-consuming onlineinteractions in RL, it poses challenges for out-of-distribution (OOD) stateactions and often suffers from data inefficiency for training. Despite manyefforts being devoted to addressing OOD state actions, the latter (datainefficiency) receives little attention in offline RL. To address this, thispaper proposes the cross-domain offline RL, which assumes offline dataincorporate additional source-domain data from varying transition dynamics(environments), and expects it to contribute to the offline data efficiency. Todo so, we identify a new challenge of OOD transition dynamics, beyond thecommon OOD state actions issue, when utilizing cross-domain offline data. Then,we propose our method BOSA, which employs two support-constrained objectives toaddress the above OOD issues. Through extensive experiments in the cross-domainoffline RL setting, we demonstrate BOSA can greatly improve offline dataefficiency: using only 10\% of the target data, BOSA could achieve {74.4\%} ofthe SOTA offline RL performance that uses 100\% of the target data.Additionally, we also show BOSA can be effortlessly plugged into model-basedoffline RL and noising data augmentation techniques (used for generatingsource-domain data), which naturally avoids the potential dynamics mismatchbetween target-domain data and newly generated source-domain data.

Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement Learning