[2108.08454] Improving Human Decision-Making with Machine Learning

A key aspect of human intelligence is their ability to convey their knowledge to others in succinct forms. However, despite their predictive power, current machine learning models are largely blackboxes, making it difficult for humans to extract useful insights. Focusing on sequential decision-making, we design a novel machine learning algorithm that conveys its insights to humans in the form of interpretable "tips". Our algorithm selects the tip that best bridges the gap in performance between human users and the optimal policy. We evaluate our approach through a series of randomized controlled user studies where participants manage a virtual kitchen. Our experiments show that the tips generated by our algorithm can significantly improve human performance relative to intuitive baselines. In addition, we discuss a number of empirical insights that can help inform the design of algorithms intended for human-AI interfaces. For instance, we find evidence that participants do not simply blindly follow our tips; instead, they combine them with their own experience to discover additional strategies for improving performance.

[2108.08454] Improving Human Sequential Decision-Making with Reinforcement Learning Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Machine Learning arXiv:2108.08454 (cs) [Submitted on 19 Aug 2021 ( v1 ), last revised 19 Mar 2024 (this version, v5)] Title: Improving Human Sequential Decision-Making with Reinforcement Learning Authors: Hamsa Bastani , Osbert Bastani , Wichinpong Park Sinchaisri View a PDF of the paper titled Improving Human Sequential Decision-Making with Reinforcem

related reading

• Deep Reinforcement Learning from Human Preferencesproceedings.neurips.cc
• DeepSeek-R1arxiv.org
• RLHF: Reinforcement Learning from Human Feedbackhuyenchip.com
• Three Challenges for AI-Assisted Decision-Making - PMCpmc.ncbi.nlm.nih.gov
• Reinforcement learning from human feedback - Wikipediaen.wikipedia.org
• How to Make Smart Decisions Without Getting Lucky - Farnam Streetfs.blog
• [1810.08575] Supervising strong learners by amplifying weak expertsar5iv.labs.arxiv.org
• [1906.09624] On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inferencearxiv.org
• 3.1 Importance of Interpretability | Interpretable Machine Learningchristophm.github.io
• [2208.10687] The Effect of Modeling Human Rationality Level on Learning Rewards from Multiple Feedback Typesar5iv.labs.arxiv.org
• Language Models can Solve Computer Tasksarxiv.org
• Learning through human feedback — Google DeepMinddeepmind.google