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 RAPid-Learn: Learning to Recover and Plan Again, a hybrid planningand learning method, to tackle the problem of adapting to sudden and unexpectedchanges in an agent's environment (i.e., novelties). RAPid-Learn is designed toformulate and solve modifications to a task's Markov Decision Process (MDPs)on-the-fly and is capable of exploiting domain knowledge to learn any newdynamics caused by the environmental changes. It is capable of exploiting thedomain knowledge to learn action executors which can be further used to resolveexecution impasses, leading to a successful plan execution. This noveltyinformation is reflected in its updated domain model. We demonstrate itsefficacy by introducing a wide variety of novelties in a gridworld environmentinspired by Minecraft, and compare our algorithm with transfer learningbaselines from the literature. Our method is (1) effective even in the presenceof multiple novelties, (2) more sample efficient than transfer learning RLbaselines, and (3) robust to incomplete model information, as opposed to puresymbolic planning approaches.

RAPid-Learn: A Framework for Learning to Recover for Handling Novelties in Open-World Environments