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

Preference-based reinforcement learning (PbRL) can enable robots to learn toperform tasks based on an individual's preferences without requiring ahand-crafted reward function. However, existing approaches either assume accessto a high-fidelity simulator or analytic model or take a model-free approachthat requires extensive, possibly unsafe online environment interactions. Inthis paper, we study the benefits and challenges of using a learned dynamicsmodel when performing PbRL. In particular, we provide evidence that a learneddynamics model offers the following benefits when performing PbRL: (1)preference elicitation and policy optimization require significantly fewerenvironment interactions than model-free PbRL, (2) diverse preference queriescan be synthesized safely and efficiently as a byproduct of standardmodel-based RL, and (3) reward pre-training based on suboptimal demonstrationscan be performed without any environmental interaction. Our paper providesempirical evidence that learned dynamics models enable robots to learncustomized policies based on user preferences in ways that are safer and moresample efficient than prior preference learning approaches.

Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models