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

We propose a framework that leverages foundation models as teachers, guidinga reinforcement learning agent to acquire semantically meaningful behaviorwithout human feedback. In our framework, the agent receives task instructionsgrounded in a training environment from large language models. Then, avision-language model guides the agent in learning the multi-tasklanguage-conditioned policy by providing reward feedback. We demonstrate thatour method can learn semantically meaningful skills in a challenging open-endedMineDojo environment while prior unsupervised skill discovery methods struggle.Additionally, we discuss observed challenges of using off-the-shelf foundationmodels as teachers and our efforts to address them.

LiFT: Unsupervised Reinforcement Learning with Foundation Models as Teachers