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

Deep Reinforcement Learning (RL) has shown great success in learning complexcontrol policies for a variety of applications in robotics. However, in mostsuch cases, the hardware of the robot has been considered immutable, modeled aspart of the environment. In this study, we explore the problem of learninghardware and control parameters together in a unified RL framework. To achievethis, we propose to model the robot body as a "hardware policy", analogous toand optimized jointly with its computational counterpart. We show that, bymodeling such hardware policies as auto-differentiable computational graphs,the ensuing optimization problem can be solved efficiently by gradient-basedalgorithms from the Policy Optimization family. We present two such designexamples: a toy mass-spring problem, and a real-world problem of designing anunderactuated hand. We compare our method against traditional co-optimizationapproaches, and also demonstrate its effectiveness by building a physicalprototype based on the learned hardware parameters. Videos and more details areavailable at https://roamlab.github.io/hwasp/ .

Hardware as Policy: Mechanical and Computational Co-Optimization using Deep Reinforcement Learning