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 work, we propose algorithms and methods that enable learningdexterous object manipulation using simulated one- or two-armed robots equippedwith multi-fingered hand end-effectors. Using a parallel GPU-acceleratedphysics simulator (Isaac Gym), we implement challenging tasks for these robots,including regrasping, grasp-and-throw, and object reorientation. To solve theseproblems we introduce a decentralized Population-Based Training (PBT) algorithmthat allows us to massively amplify the exploration capabilities of deepreinforcement learning. We find that this method significantly outperformsregular end-to-end learning and is able to discover robust control policies inchallenging tasks. Video demonstrations of learned behaviors and the code canbe found at https://sites.google.com/view/dexpbt

DexPBT: Scaling up Dexterous Manipulation for Hand-Arm Systems with Population Based Training