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

This paper contributes a preliminary report on the advantages anddisadvantages of incorporating simultaneous human control and feedback signalsin the training of a reinforcement learning robotic agent. While robotichuman-machine interfaces have become increasingly complex in both form andfunction, control remains challenging for users. This has resulted in anincreasing gap between user control approaches and the number of robotic motorswhich can be controlled. One way to address this gap is to shift some autonomyto the robot. Semi-autonomous actions of the robotic agent can then be shapedby human feedback, simplifying user control. Most prior work on agent shapingby humans has incorporated training with feedback, or has included indirectcontrol signals. By contrast, in this paper we explore how a human can provideconcurrent feedback signals and real-time myoelectric control signals to traina robot's actor-critic reinforcement learning control system. Using both aphysical and a simulated robotic system, we compare training performance on asimple movement task when reward is derived from the environment, when rewardis provided by the human, and combinations of these two approaches. Our resultsindicate that some benefit can be gained with the inclusion of human generatedfeedback.

Simultaneous Control and Human Feedback in the Training of a Robotic Agent with Actor-Critic Reinforcement Learning