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

Symbolic planning models allow decision-making agents to sequence actions inarbitrary ways to achieve a variety of goals in dynamic domains. However, theyare typically handcrafted and tend to require precise formulations that are notrobust to human error. Reinforcement learning (RL) approaches do not requiresuch models, and instead learn domain dynamics by exploring the environment andcollecting rewards. However, RL approaches tend to require millions of episodesof experience and often learn policies that are not easily transferable toother tasks. In this paper, we address one aspect of the open problem ofintegrating these approaches: how can decision-making agents resolvediscrepancies in their symbolic planning models while attempting to accomplishgoals? We propose an integrated framework named SPOTTER that uses RL to augmentand support ("spot") a planning agent by discovering new operators needed bythe agent to accomplish goals that are initially unreachable for the agent.SPOTTER outperforms pure-RL approaches while also discovering transferablesymbolic knowledge and does not require supervision, successful plan traces orany a priori knowledge about the missing planning operator.

SPOTTER: Extending Symbolic Planning Operators through Targeted Reinforcement Learning