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

In this paper, a novel Scaffolding Reflection in Reinforcement Learning(SR2L) is proposed for solving the confinement escape problem (CEP). In CEP, anevader's objective is to attempt escaping a confinement region patrolled bymultiple pursuers. Meanwhile, the pursuers aim to reach and capture the evader.The inverse solution for pursuers to try and capture has been extensivelystudied in the literature. However, the problem of evaders escaping from theregion is still an open issue. The SR2L employs an actor-critic framework toenable the evader to escape the confinement region. A time-varying staterepresentation and reward function have been developed for proper convergence.The formulation uses the sensor information about the observable environmentand prior knowledge of the confinement boundary. The conventional IndependentActor-Critic (IAC) method fails to converge due to sparseness in the reward.The effect becomes evident when operating in such a dynamic environment with alarge area. In SR2L, along with the developed reward function, we use thescaffolding reflection method to improve the convergence significantly whileincreasing its efficiency. In SR2L, a motion planner is used as a scaffold forthe actor-critic network to observe, compare and learn the action-reward pair.It enables the evader to achieve the required objective while using lesserresources and time. Convergence studies show that SR2L learns faster andconverges to higher rewards as compared to IAC. Extensive Monte-Carlosimulations show that a SR2L consistently outperforms conventional IAC and themotion planner itself as the baselines.

Scaffolding Reflection in Reinforcement Learning Framework for Confinement Escape Problem