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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In this article, we propose a backpropagation-free approach to roboticcontrol through the neuro-cognitive computational framework of neuralgenerative coding (NGC), designing an agent built completely from powerfulpredictive coding/processing circuits that facilitate dynamic, online learningfrom sparse rewards, embodying the principles of planning-as-inference.Concretely, we craft an adaptive agent system, which we call active predictivecoding (ActPC), that balances an internally-generated epistemic signal (meantto encourage intelligent exploration) with an internally-generated instrumentalsignal (meant to encourage goal-seeking behavior) to ultimately learn how tocontrol various simulated robotic systems as well as a complex robotic armusing a realistic robotics simulator, i.e., the Surreal Robotics Suite, for theblock lifting task and can pick-and-place problems. Notably, our experimentalresults demonstrate that our proposed ActPC agent performs well in the face ofsparse (extrinsic) reward signals and is competitive with or outperformsseveral powerful backprop-based RL approaches.

Active Predicting Coding: Brain-Inspired Reinforcement Learning for Sparse Reward Robotic Control Problems