In this chapter we review fundamentals of machine learning for movement-based interaction in performing arts, describing typical interaction paradigms, workflows, and processes. Using examples, we describe how different tasks typically found in machine learning can be used or modified in this context. In particular, computational models can be used not only to recognize “which” gestures or human body movements are performed, but also “how” they are performed. Therefore, notions of expressivity, style, and movement qualities must be considered. Moreover, movement-based interactive systems face other specific challenges, from both machine learning and human–computer interaction perspectives that we review in this chapter: designing movements, limited datasets, and human learning.

This chapter describes how nonexpert humans can train reinforcement learning (RL) agents. There are numerous ways to learn from human instruction – some have been studied more than others since this is an open field of research. A traditional machine learning approach focuses on the objective performance of the RL agent, optimizing metrics such as training time and reward. Verifying these RL systems is often done with simulated rather than real human input. We believe that to be a limiting approach. In this chapter, we will show: (1) a few methods of humans teaching RL agents; (2) how a great deal of information can be learned from testing these agents with human-subject studies; and (3) how objective performance does not need to be sacrificed in order to create a positive user experience. We can create a much better interactive machine learning system when designing and verifying from a human-centered perspective. We’ll cover different teaching methods, including advice and critique, and how they impact the user experience and objective performance of the agent. We’ll also discus how teaching methods are impacted by many factors, such as rhetorical arguments, immediacy of feedback, and issues of language processing. We’ll also cover a three-step process for the design and verification of interactive machine learning algorithms, and recommendations to improve the human experience.

In today’s data-driven world, the demand for advanced intelligent systems to automate and enhance complex tasks is growing. However, developing effective artificial intelligence (AI) often depends on extensive, high-quality training data, which can be costly and time-consuming to obtain. This chapter highlights the potential of human–AI collaboration by integrating human expertise into machine learning workflows to address data limitations and enhance model performance. We explore foundational concepts such as Human-in-the-Loop systems, Active Learning, Crowdsourcing, and Interactive Machine Learning, outlining their interconnections as key paradigms. Through practical applications in diverse domains such as healthcare, finance, and agriculture, along with real-world case studies in education and law, we demonstrate how strategically incorporating human expertise into machine learning workflows can significantly enhance AI performance. From an information science perspective, this chapter emphasizes the powerful human–AI partnership that can drive the next generation of AI systems, enabling continuous learning from human experts and advancing capability and performance.