A Survey on Interactive Reinforcement Learning: Design Principles and Open Challenges
Interactive reinforcement learning (RL) has been successfully used in various applications in different fields, which has also motivated HCI researchers to contribute in this area. In this paper, we survey interactive RL to empower human-computer interaction (HCI) researchers with the technical background in RL needed to design new interaction techniques and propose new applications. We elucidate the roles played by HCI researchers in interactive RL, identifying ideas and promising research directions. Furthermore, we propose generic design principles that will provide researchers with a guide to effectively implement interactive RL applications.
Research Questions / Practical Problems
Question signals indexed for this paper.
- 100%
Effects of Communication Directionality and AI Agent Differences in Human-AI Interaction
CHI '21· Human-LLM Collaboration +1
- 100%
AI Knowledge: Improving AI Delegation through Human Enablement
CHI '23· Human-LLM Collaboration +1
- 100%
Towards Human-AI Deliberation: Design and Evaluation of LLM-Empowered Deliberative AI for AI-Assisted Decision-Making
CHI '25· Human-LLM Collaboration +1
- 80%
You Complete Me: Human-AI Teams and Complementary Expertise
CHI '22· Human-LLM Collaboration +1
- 80%
Competent but Rigid: Identifying the Gap in Empowering AI to Participate Equally in Group Decision-Making
CHI '23· Human-LLM Collaboration +1
- 80%
Why Johnny Can’t Prompt: How Non-AI Experts Try (and Fail) to Design LLM Prompts
CHI '23· Human-LLM Collaboration +1
- 80%
Automatic Macro Mining from Interaction Traces at Scale
CHI '24· Human-LLM Collaboration +1
- 80%
From Text to Trust: Empowering AI-assisted Decision Making with Adaptive LLM-powered Analysis
CHI '25· Human-LLM Collaboration +2
- 80%
Which Contributions Deserve Credit? Perceptions of Attribution in Human-AI Co-Creation
CHI '25· Human-LLM Collaboration +2
- 80%
Satisficing vs. Maximizing in Prompt Writing: Trait and Task Effects in Human–AI Interaction
CHI '26· Generative AI (Text, Image, Music, Video) +2
Based on Jaccard similarity of research subtopics & professions (≥60%)