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

The design of reward functions in reinforcement learning is a human skillthat comes with experience. Unfortunately, there is not any methodology in theliterature that could guide a human to design the reward function or to allow ahuman to transfer the skills developed in designing reward functions to anotherhuman and in a systematic manner. In this paper, we use SystematicInstructional Design, an approach in human education, to engineer a machineeducation methodology to design reward functions for reinforcement learning. Wedemonstrate the methodology in designing a hierarchical genetic reinforcementlearner that adopts a neural network representation to evolve a swarmcontroller for an agent shepherding a boids-based swarm. The results revealthat the methodology is able to guide the design of hierarchical reinforcementlearners, with each model in the hierarchy learning incrementally through amulti-part reward function. The hierarchy acts as a decision fusion functionthat combines the individual behaviours and skills learnt by each instructionto create a smart shepherd to control the swarm.

Machine Teaching in Hierarchical Genetic Reinforcement Learning: Curriculum Design of Reward Functions for Swarm Shepherding