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

Hierarchical reinforcement learning (HRL) incorporates temporal abstractioninto reinforcement learning (RL) by explicitly taking advantage of hierarchicalstructure. Modern HRL typically designs a hierarchical agent composed of ahigh-level policy and low-level policies. The high-level policy selects whichlow-level policy to activate at a lower frequency and the activated low-levelpolicy selects an action at each time step. Recent HRL algorithms have achievedperformance gains over standard RL algorithms in synthetic navigation tasks.However, we cannot apply these HRL algorithms to real-world navigation tasks.One of the main challenges is that real-world navigation tasks require an agentto perform safe and interactive behaviors in dynamic environments. In thispaper, we propose imagination-augmented HRL (IAHRL) that efficiently integratesimagination into HRL to enable an agent to learn safe and interactive behaviorsin real-world navigation tasks. Imagination is to predict the consequences ofactions without interactions with actual environments. The key idea behindIAHRL is that the low-level policies imagine safe and structured behaviors, andthen the high-level policy infers interactions with surrounding objects byinterpreting the imagined behaviors. We also introduce a new attentionmechanism that allows our high-level policy to be permutation-invariant to theorder of surrounding objects and to prioritize our agent over them. To evaluateIAHRL, we introduce five complex urban driving tasks, which are among the mostchallenging real-world navigation tasks. The experimental results indicate thatIAHRL enables an agent to perform safe and interactive behaviors, achievinghigher success rates and lower average episode steps than baselines.

Imagination-Augmented Hierarchical Reinforcement Learning for Safe and Interactive Autonomous Driving in Urban Environments