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

We introduce a novel co-design method for autonomous moving agents' shapeattributes and locomotion by combining deep reinforcement learning andevolution with user control. Our main inspiration comes from evolution, whichhas led to wide variability and adaptation in Nature and has the potential tosignificantly improve design and behavior simultaneously. Our method takes aninput agent with optional simple constraints such as leg parts that should notevolve or allowed ranges of changes. It uses physics-based simulation todetermine its locomotion and finds a behavior policy for the input design,later used as a baseline for comparison. The agent is then randomly modifiedwithin the allowed ranges creating a new generation of several hundred agents.The generation is trained by transferring the previous policy, whichsignificantly speeds up the training. The best-performing agents are selected,and a new generation is formed using their crossover and mutations. The nextgenerations are then trained until satisfactory results are reached. We show awide variety of evolved agents, and our results show that even with only 10% ofchanges, the overall performance of the evolved agents improves 50%. If moresignificant changes to the initial design are allowed, our experiments'performance improves even more to 150%. Contrary to related work, our co-designworks on a single GPU and provides satisfactory results by training thousandsof agents within one hour.

Co-design of Embodied Neural Intelligence via Constrained Evolution