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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We study how an autonomous agent learns to perform a task from demonstrationsin a different domain, such as a different environment or different agent. Suchcross-domain imitation learning is required to, for example, train anartificial agent from demonstrations of a human expert. We propose a scalableframework that enables cross-domain imitation learning without access toadditional demonstrations or further domain knowledge. We jointly train thelearner agent's policy and learn a mapping between the learner and expertdomains with adversarial training. We effect this by using a mutual informationcriterion to find an embedding of the expert's state space that containstask-relevant information and is invariant to domain specifics. This stepsignificantly simplifies estimating the mapping between the learner and expertdomains and hence facilitates end-to-end learning. We demonstrate successfultransfer of policies between considerably different domains, without extrasupervision such as additional demonstrations, and in situations where othermethods fail.

Learn what matters: cross-domain imitation learning with task-relevant embeddings