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

Integrating rule-based policies into reinforcement learning promises toimprove data efficiency and generalization in cooperative pursuit problems.However, most implementations do not properly distinguish the influence ofneighboring robots in observation embedding or inter-robot interaction rules,leading to information loss and inefficient cooperation. This paper proposes acooperative pursuit algorithm named Decentralized Adaptive COOperative Pursuitvia Attention (DACOOP-A) by empowering reinforcement learning with artificialpotential field and attention mechanisms. An attention-based framework isdeveloped to emphasize important neighbors by concurrently integrating thelearned attention scores into observation embedding and inter-robot interactionrules. A KL divergence regularization is introduced to alleviate the resultantlearning stability issue. Improvements in data efficiency and generalizationare demonstrated through numerical simulations. Extensive quantitative analysisand ablation studies are performed to illustrate the advantages of the proposedmodules. Real-world experiments are performed to justify the feasibility ofdeploying DACOOP-A in physical systems.

DACOOP-A: Decentralized Adaptive Cooperative Pursuit via Attention