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 propose a novel framework for Deep Reinforcement Learning (DRL) in modularrobotics using traditional robotic tools that extend state-of-the-art DRLimplementations and provide an end-to-end approach which trains a robotdirectly from joint states. Moreover, we present a novel technique to transferthese DLR methods into the real robot, aiming to close the simulation-realitygap. We demonstrate the robustness of the performance of state-of-the-art DRLmethods for continuous action spaces in modular robots, with an empirical studyboth in simulation and in the real robot where we also evaluate howaccelerating the simulation time affects the robot's performance. Our resultsshow that extending the modular robot from 3 degrees-of-freedom (DoF), to 4DoF, does not affect the robot's learning. This paves the way towards trainingmodular robots using DRL techniques.

Evaluation of Deep Reinforcement Learning Methods for Modular Robots