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

Despite advances in hierarchical reinforcement learning, its applications topath planning in autonomous driving on highways are challenging. One reason isthat conventional hierarchical reinforcement learning approaches are notamenable to autonomous driving due to its riskiness: the agent must moveavoiding multiple obstacles such as other agents that are highly unpredictable,thus safe regions are small, scattered, and changeable over time. To overcomethis challenge, we propose a spatially hierarchical reinforcement learningmethod for state space and policy space. The high-level policy selects not onlybehavioral sub-policy but also regions to pay mind to in state space and foroutline in policy space. Subsequently, the low-level policy elaborates theshort-term goal position of the agent within the outline of the region selectedby the high-level command. The network structure and optimization suggested inour method are as concise as those of single-level methods. Experiments on theenvironment with various shapes of roads showed that our method finds thenearly optimal policies from early episodes, outperforming a baselinehierarchical reinforcement learning method, especially in narrow and complexroads. The resulting trajectories on the roads were similar to those of humanstrategies on the behavioral planning level.

Spatially and Seamlessly Hierarchical Reinforcement Learning for State Space and Policy space in Autonomous Driving