Code:
Experiment design: https://colab.research.google.com/drive/1hWtDZ_L6s0Zw78ziWDoLXjd1mKsgiESd?usp=sharing
Selective prediction: https://github.com/google-deepmind/codoc/blob/main/codoc_experiments.ipynb
Power analysis: https://colab.research.google.com/drive/1mNEJ_5eC3jgngxY39FknMJl7hHMep5la?usp=sharing
Links:
https://plato.stanford.edu/entries/bounded-rationality/
https://kpu.pressbooks.pub/psychmethods4e/
https://news.uchicago.edu/explainer/what-is-behavioral-economics
https://docs.google.com/presentation/d/1s8cb7biXJ3FflVaa3MoyAr1XifQBzTzPFKyKeCn-cUI/edit?usp=sharing
https://github.com/google-deepmind/codoc
https://deepmind.google/discover/blog/codoc-developing-reliable-ai-tools-for-healthcare/
https://www.nature.com/articles/s41591-023-02437-x%20
https://dl.acm.org/doi/abs/10.1145/3600211.3604692
https://arxiv.org/abs/2212.07430
https://openreview.net/pdf?id=4ImZxqmT1K
Human-in-the-Loop RL: https://sites.google.com/ualberta.ca/cmput656f23/home
Interactive Machine Learning: https://sites.google.com/ualberta.ca/cmput656/home
AAAI-24 Bridge Program: Collaborative AI & Modeling of Humans: https://sites.google.com/view/collab-ai-and-human-modeling/home
A brief guide to designing and evaluating human-centered interactive machine learning. Mathewson & Pilarski: https://arxiv.org/abs/2204.09622
A Conceptual Framework for Externally-Influenced Agents: An Assisted Reinforcement Learning Review.” Adam Bignold, Francisco Cruz, Taylor, Tim Brys, Richard Dazeley, Peter Vamplew, and Cameron Foale. 2021. https://arxiv.org/abs/2007.01544
Humans are not Boltzmann Distributions: Challenges and Opportunities for Modelling Human Feedback and Interaction in Reinforcement Learning: https://arxiv.org/abs/2206.13316
Reinforcement Learning Requires Human-in-the-Loop Framing and Approaches, HHAI 2023: https://irll.ca/files/publications/23HHAI.pdf
Can You Improve My Code? Optimizing Programs with Local Search. IJCAI 2023: https://arxiv.org/abs/2307.05603
Updates in Human-AI Teams: Understanding and Addressing the Performance/Compatibility Tradeoff: https://dl.acm.org/doi/10.1609/aaai.v33i01.33012429
Layered evaluation of interactive adaptive systems: framework and formative methods: https://aura.abdn.ac.uk/bitstream/2164/2218/1/USER637.pdf