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

Planning with a learned model is arguably a key component of intelligence.There are several challenges in realizing such a component in large-scalereinforcement learning (RL) problems. One such challenge is dealing effectivelywith continuous action spaces when using tree-search planning (e.g., it is notfeasible to consider every action even at just the root node of the tree). Inthis paper we present a method for selecting affordances useful for planning --for learning which small number of actions/options from a continuous space ofactions/options to consider in the tree-expansion process during planning. Weconsider affordances that are goal-and-state-conditional mappings toactions/options as well as unconditional affordances that simply selectactions/options available in all states. Our selection method is gradientbased: we compute gradients through the planning procedure to update theparameters of the function that represents affordances. Our empirical workshows that it is feasible to learn to select both primitive-action and optionaffordances, and that simultaneously learning to select affordances andplanning with a learned value-equivalent model can outperform model-free RL.

GrASP: Gradient-Based Affordance Selection for Planning