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 search of the simplest baseline capable of competing with DeepReinforcement Learning on locomotion tasks, we propose a biologically inspiredmodel-free open-loop strategy. Drawing upon prior knowledge and harnessing theelegance of simple oscillators to generate periodic joint motions, it achievesrespectable performance in five different locomotion environments, with anumber of tunable parameters that is a tiny fraction of the thousands typicallyrequired by RL algorithms. Unlike RL methods, which are prone to performancedegradation when exposed to sensor noise or failure, our open-loop oscillatorsexhibit remarkable robustness due to their lack of reliance on sensors.Furthermore, we showcase a successful transfer from simulation to reality usingan elastic quadruped, all without the need for randomization or rewardengineering. Overall, the proposed baseline and associated experimentshighlight the existing limitations of DRL for robotic applications, provideinsights on how to address them, and encourage reflection on the costs ofcomplexity and generality.

A Simple Open-Loop Baseline for Reinforcement Learning Locomotion Tasks