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

Sequential decision problems in applications such as manipulation inwarehouses, multi-step meal preparation, and routing in autonomous vehiclenetworks often involve reasoning about uncertainty, planning over discretemodes as well as continuous states, and reacting to dynamic updates. Toformalize such problems generally, we introduce a class of Markov DecisionProcesses (MDPs) called Dynamic Multimodal Stochastic Shortest Paths (DMSSPs).Much of the work in these domains solves deterministic variants, which canyield poor results when the uncertainty has downstream effects. We develop aHybrid Stochastic Planning (HSP) algorithm, which uses domain-agnosticabstractions to efficiently unify heuristic search for planning over discretemodes, approximate dynamic programming for stochastic planning over continuousstates, and hierarchical interleaved planning and execution. In the domain ofautonomous multimodal routing, HSP obtains significantly higher qualitysolutions than a state-of-the-art Upper Confidence Trees algorithm and atwo-level Receding Horizon Control algorithm.

Hybrid Planning for Dynamic Multimodal Stochastic Shortest Paths