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

Reinforcement learning is an emerging approach to control dynamical systemsfor which classical approaches are difficult to apply. However, trained agentsmay not generalize against the variations of system parameters. This paperpresents the concept of dual-scale homogeneity, an important property inunderstating the scaling behavior of nonlinear systems. Furthermore, it alsopresents an effective yet simple approach to designing a parameter-dependentcontrol law that homogenizes a nonlinear system. The presented approach isapplied to two systems, demonstrating its ability to provide a consistentperformance irrespective of parameters variations. To demonstrate thepracticality of the proposed approach, the control policy is generated by adeep deterministic policy gradient to control the load position of a quadrotorwith a slung load. The proposed synergy between the homogeneity transformationsand reinforcement learning yields superior performance compared to other recentlearning-based control techniques. It achieves a success rate of 96% inbringing the load to its designated target with a 3D RMSE of 0.0253 m. Thevideo that shows the experimental results along with a summary of the paper isavailable at this link.

Reinforcement Learning Generalization for Nonlinear Systems Through Dual-Scale Homogeneity Transformations