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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

We present the integration of a NAO robot in Webots with the Reinforcement Learning framework from OpenAI: Gym. We then try different reward functions to measure the ability of a single algorithm to learn, in order to determine the key characteristics, variables, and parameters that this function should have in order to reach observable results. This is a working proyect so the results are not final. This article concludes that there is still work to be done in order to reach the objective, but that actual results are already measurable. On the long term, we intend to design a hierarchical control system based on Reinforcement Learning, and compare it to other control systems currently being used

Integración de aprendizaje por refuerzo a simulador físico y análisis de funciones de recompensa para robots humanoides