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

The goal of imitation learning is to mimic expert behavior fromdemonstrations, without access to an explicit reward signal. A popular class ofapproach infers the (unknown) reward function via inverse reinforcementlearning (IRL) followed by maximizing this reward function via reinforcementlearning (RL). The policies learned via these approaches are however verybrittle in practice and deteriorate quickly even with small test-timeperturbations due to compounding errors. We propose Imitation with Planning atTest-time (IMPLANT), a new meta-algorithm for imitation learning that utilizesdecision-time planning to correct for compounding errors of any base imitationpolicy. In contrast to existing approaches, we retain both the imitation policyand the rewards model at decision-time, thereby benefiting from the learningsignal of the two components. Empirically, we demonstrate that IMPLANTsignificantly outperforms benchmark imitation learning approaches on standardcontrol environments and excels at zero-shot generalization when subject tochallenging perturbations in test-time dynamics.

Imitating, Fast and Slow: Robust learning from demonstrations via decision-time planning