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

Reinforcement learning (RL) algorithms have been successfully used to developcontrol policies for dynamical systems. For many such systems, these policiesare trained in a simulated environment. Due to discrepancies between thesimulated model and the true system dynamics, RL trained policies often fail togeneralize and adapt appropriately when deployed in the real-world environment.Current research in bridging this sim-to-real gap has largely focused onimprovements in simulation design and on the development of improved andspecialized RL algorithms for robust control policy generation. In this paperwe apply principles from adaptive control and system identification to developthe model-reference adaptive control & reinforcement learning (MRAC-RL)framework. We propose a set of novel MRAC algorithms applicable to a broadrange of linear and nonlinear systems, and derive the associated control laws.The MRAC-RL framework utilizes an inner-loop adaptive controller that allows asimulation-trained outer-loop policy to adapt and operate effectively in a testenvironment, even when parametric model uncertainty exists. We demonstrate thatthe MRAC-RL approach improves upon state-of-the-art RL algorithms in developingcontrol policies that can be applied to systems with modeling errors.

MRAC-RL: A Framework for On-Line Policy Adaptation Under Parametric Model Uncertainty