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

To solve difficult tasks, humans ask questions to acquire knowledge fromexternal sources. In contrast, classical reinforcement learning agents lacksuch an ability and often resort to exploratory behavior. This is exacerbatedas few present-day environments support querying for knowledge. In order tostudy how agents can be taught to query external knowledge via language, wefirst introduce two new environments: the grid-world-based Q-BabyAI and thetext-based Q-TextWorld. In addition to physical interactions, an agent canquery an external knowledge source specialized for these environments to gatherinformation. Second, we propose the "Asking for Knowledge" (AFK) agent, whichlearns to generate language commands to query for meaningful knowledge thathelps solve the tasks. AFK leverages a non-parametric memory, a pointermechanism and an episodic exploration bonus to tackle (1) irrelevantinformation, (2) a large query language space, (3) delayed reward for makingmeaningful queries. Extensive experiments demonstrate that the AFK agentoutperforms recent baselines on the challenging Q-BabyAI and Q-TextWorldenvironments.

Asking for Knowledge: Training RL Agents to Query External Knowledge Using Language