# Learning Complementary Policies for Human-AI Teams

arXiv: https://arxiv.org/abs/2302.02944 · HTML: https://mlsanity.com/paper/2302.02944/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 58 of its 125 references that are in the map.
- First posted on arXiv 6 Feb 2023.

## Builds on (most cited first, 30 of 58)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [Off-Policy Deep Reinforcement Learning without Exploration](https://mlsanity.com/paper/1812.02900/) (2018)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Behavioral Cloning from Observation](https://mlsanity.com/paper/1805.01954/) (2018)
- [Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learning](https://mlsanity.com/paper/1706.03461/) (2017)
- [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019)
- [Causal Effect Inference with Deep Latent-Variable Models](https://mlsanity.com/paper/1705.08821/) (2017)
- [Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance](https://mlsanity.com/paper/2006.14779/) (2020)
- [Smart "Predict, then Optimize"](https://mlsanity.com/paper/1710.08005/) (2017)
- [Learning Representations for Counterfactual Inference](https://mlsanity.com/paper/1605.03661/) (2016)
- [Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations](https://mlsanity.com/paper/2110.05719/) (2021)
- [Consistent Estimators for Learning to Defer to an Expert](https://mlsanity.com/paper/2006.01862/) (2020)
- [Generalisation in humans and deep neural networks](https://mlsanity.com/paper/1808.08750/) (2018)
- [Human uncertainty makes classification more robust](https://mlsanity.com/paper/1908.07086/) (2019)
- [Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer](https://mlsanity.com/paper/1711.06664/) (2017)
- [Doubly Robust Policy Evaluation and Optimization](https://mlsanity.com/paper/1503.02834/) (2015)
- [From Predictive to Prescriptive Analytics](https://mlsanity.com/paper/1402.5481/) (2014)
- [Learning From Noisy Labels By Regularized Estimation Of Annotator Confusion](https://mlsanity.com/paper/1902.03680/) (2019)
- [Learning to Complement Humans](https://mlsanity.com/paper/2005.00582/) (2020)
- [The Algorithmic Automation Problem: Prediction, Triage, and Human Effort](https://mlsanity.com/paper/1903.12220/) (2019)
- [Confounding-Robust Policy Improvement](https://mlsanity.com/paper/1805.08593/) (2018)
- [Towards Unbiased and Accurate Deferral to Multiple Experts](https://mlsanity.com/paper/2102.13004/) (2021)
- [Model Selection in Contextual Stochastic Bandit Problems](https://mlsanity.com/paper/2003.01704/) (2020)
- [Human-AI Collaboration via Conditional Delegation: A Case Study of Content Moderation](https://mlsanity.com/paper/2204.11788/) (2022)
- [Offline Multi-Action Policy Learning: Generalization and Optimization](https://mlsanity.com/paper/1810.04778/) (2018)
- [Off-policy Bandits with Deficient Support](https://mlsanity.com/paper/2006.09438/) (2020)

## Built on by (most cited first, 7 of 7)

- [Learning Personalized Decision Support Policies](https://mlsanity.com/paper/2304.06701/) (2023)
- [When Should We Orchestrate Multiple Agents?](https://mlsanity.com/paper/2503.13577/) (2025)
- [Confounding-Robust Policy Improvement with Human-AI Teams](https://mlsanity.com/paper/2310.08824/) (2023)
- [HR-Bandit: Human-AI Collaborated Linear Recourse Bandit](https://mlsanity.com/paper/2410.14640/) (2024)
- [When AI Persuades: Adversarial Explanation Attacks on Human Trust in AI-Assisted Decision Making](https://mlsanity.com/paper/2602.04003/) (2026)
- [Bayesian Inference for Correlated Human Experts and Classifiers](https://mlsanity.com/paper/2506.05636/) (2025)
- [Achieving Trustworthy Real-Time Decision Support Systems with Low-Latency Interpretable AI Models](https://mlsanity.com/paper/2506.20018/) (2025)

## Abstract (arXiv)

This paper tackles the critical challenge of human-AI complementarity in decision-making. Departing from the traditional focus on algorithmic performance in favor of performance of the human-AI team, and moving past the framing of collaboration as classification to focus on decision-making tasks, we introduce a novel approach to policy learning. Specifically, we develop a robust solution for human-AI collaboration when outcomes are only observed under assigned actions. We propose a deferral collaboration approach that maximizes decision rewards by exploiting the distinct strengths of humans and AI, strategically allocating instances among them. Critically, our method is robust to misspecifications in both the human behavior and reward models. Leveraging the insight that performance gains stem from divergent human and AI behavioral patterns, we demonstrate, using synthetic and real human responses, that our proposed method significantly outperforms independent human and algorithmic decision-making. Moreover, we show that substantial performance improvements are achievable by routing only a small fraction of instances to human decision-makers, highlighting the potential for efficient and effective human-AI collaboration in complex management settings.