Automated voice calls with health information are a proven method for disseminating maternal and child health information among beneficiaries and are deployed in several programs around the world. However, these programs often suffer from beneficiary dropoffs and poor engagement. In previous work, through real-world trials, we showed that an AI model, specifically a restless bandit model, could identify beneficiaries who would benefit most from live service call interventions, preventing dropoffs and boosting engagement. However, one key question has remained open so far: does such improved listenership via AI-targeted interventions translate into beneficiaries' improved knowledge and health behaviors? We present a first study that shows not only listenership improvements due to AI interventions, but also simultaneously links these improvements to health behavior changes. Specifically, we demonstrate that AI-scheduled interventions, which enhance listenership, lead to statistically significant improvements in beneficiaries' health behaviors such as taking iron or calcium supplements in the postnatal period, as well as understanding of critical health topics during pregnancy and infancy. This underscores the potential of AI to drive meaningful improvements in maternal and child health.

Applying Reinforcement Learning (RL) to Restless Multi-Arm Bandits (RMABs) offers a promising avenue for addressing allocation problems with resource constraints and temporal dynamics. However, classic RMAB models largely overlook the challenges of (systematic) data errors - a common occurrence in real-world scenarios due to factors like varying data collection protocols and intentional noise for differential privacy. We demonstrate that conventional RL algorithms used to train RMABs can struggle to perform well in such settings. To solve this problem, we propose the first communication learning approach in RMABs, where we study which arms, when involved in communication, are most effective in mitigating the influence of such systematic data errors. In our setup, the arms receive Q-function parameters from similar arms as messages to guide behavioral policies, steering Q-function updates. We learn communication strategies by considering the joint utility of messages across all pairs of arms and using a Q-network architecture that decomposes the joint utility. Both theoretical and empirical evidence validate the effectiveness of our method in significantly improving RMAB performance across diverse problems.

Protecting against adversarial attacks is a common multiagent problem. Attackers in the real world are predominantly human actors, and the protection methods often incorporate opponent models to improve the performance when facing humans. Previous results show that modeling human behavior can significantly improve the performance of the algorithms. However, modeling humans correctly is a complex problem, and the models are often simplified and assume humans make mistakes according to some distribution or train parameters for the whole population from which they sample. In this work, we use data gathered by psychologists who identified personality types that increase the likelihood of performing malicious acts. However, in the previous work, the tests on a handmade game could not show strategic differences between the models. We created a novel model that links its parameters to psychological traits. We optimized over parametrized games and created games in which the differences are profound. Our work can help with automatic game generation when we need a game in which some models will behave differently and to identify situations in which the models do not align.

Stackelberg Security Games are often used to model strategic interactions in high-stakes security settings. The majority of existing models focus on single-defender settings where a single entity assumes command of all security assets. However, many realistic scenarios feature multiple heterogeneous defenders with their own interests and priorities embedded in a more complex system. Furthermore, defenders rarely choose targets to protect. Instead, they have a multitude of defensive resources or schedules at its disposal, each with different protective capabilities. In this paper, we study security games featuring multiple defenders and schedules simultaneously. We show that unlike prior work on multi-defender security games, the introduction of schedules can cause non-existence of equilibrium even under rather restricted environments. We prove that under the mild restriction that any subset of a schedule is also a schedule, non-existence of equilibrium is not only avoided, but can be computed in polynomial time in games with two defenders. Under additional assumptions, our algorithm can be extended to games with more than two defenders and its computation scaled up in special classes of games with compactly represented schedules such as those used in patrolling applications. Experimental results suggest that our methods scale gracefully with game size, making our algorithms amongst the few that can tackle multiple heterogeneous defenders.

Designing cyber defense systems to account for cognitive biases in human decision making has demonstrated significant success in improving performance against human attackers. However, much of the attention in this area has focused on relatively simple accounts of biases in human attackers, and little is known about adversarial behavior or how defenses could be improved by disrupting attacker's behavior. In this work, we present a novel model of human decision-making inspired by the cognitive faculties of Instance-Based Learning Theory, Theory of Mind, and Transfer of Learning. This model functions by learning from both roles in a security scenario: defender and attacker, and by making predictions of the opponent's beliefs, intentions, and actions. The proposed model can better defend against attacks from a wide range of opponents compared to alternatives that attempt to perform optimally without accounting for human biases. Additionally, the proposed model performs better against a range of human-like behavior by explicitly modeling human transfer of learning, which has not yet been applied to cyber defense scenarios. Results from simulation experiments demonstrate the potential usefulness of cognitively inspired models of agents trained in attack and defense roles and how these insights could potentially be used in real-world cybersecurity.

Reinforcement Learning (RL) algorithms have been successfully applied to real world situations like illegal smuggling, poaching, deforestation, climate change, airport security, etc. These scenarios can be framed as Stackelberg security games (SSGs) where defenders and attackers compete to control target resources. The algorithm's competency is assessed by which agent is controlling the targets. This review investigates modeling of SSGs in RL with a focus on possible improvements of target representations in RL algorithms.

Multi-defender Stackelberg Security Games (MSSG) have recently gained increasing attention in the literature. However, the solutions offered to date are highly sensitive, wherein even small perturbations in the attacker's utility or slight uncertainties thereof can dramatically change the defenders' resulting payoffs and alter the equilibrium. In this paper, we introduce a robust model for MSSGs, which admits solutions that are resistant to small perturbations or uncertainties in the game's parameters. First, we formally define the notion of robustness, as well as the robust MSSG model. Then, for the non-cooperative setting, we prove the existence of a robust approximate equilibrium in any such game, and provide an efficient construction thereof. For the cooperative setting, we show that any such game admits a robust approximate alpha-core, provide an efficient construction thereof, and prove that stronger types of the core may be empty. Interestingly, the robust solutions can substantially increase the defenders' utilities over those of the non-robust ones.

Lily Xu knew from a young age how much the environment and conservation mattered to her. By 9 years old, she'd already decided to eat vegetarian because, as she put it, "I didn't want to hurt animals." Xu grew up believing her passions would always be separate from her professional interest in computer science. Then she became a graduate student in Milind Tambe's Teamcore Lab, and everything changed. Xu is now doing award-winning research into using machine learning and artificial intelligence to help conservation and anti-poaching efforts around the world.

The illegal animal trade is a global scourge but a lucrative one, worth $8 to 10 billion annually, according to the United Nations Office on Drugs and Crime (UNODC) -- trailing only human, drug and weapons trafficking in value. With so much money to be made, conservationists and wildlife rangers face overwhelming odds against well-organized poaching operations fueled by incessant demand for illicit animal products. The results of this protracted conflict have been nothing short of devastating for the species caught in the middle. At the start of the 20th century, more than 100,000 tigers are estimated to have roamed throughout Southeast Asia. Today, due to a combination of habitat loss and aggressive poaching, fewer than 4,000 currently remain in the wild.

Google has announced the setting up of Google Research India, an artificial intelligence research team in Bangalore, Karnataka, that will focus on advancing computer science and applying AI research to solve big problems in healthcare, agriculture and education, among other areas. The company said artificial intelligence is opening up the next phase of the technology revolution and India, with its world-class engineering talent, strong computer science programs and entrepreneurial drive, has the potential to lead the way in using this to tackle big challenges. In fact, there are already many examples of this happening in India, from detecting diabetic eye disease to improving flood forecasting and teaching kids to read. To take this trend further, Google has set up the Google Research India lab which will focus on two pillars: advancing fundamental computer science and AI research by building a strong team and partnering with the research community across the country, and applying this research to tackle big problems in core areas. Google Research India will be headed by Manish Gupta, computer scientist and a fellow of the Association for Computing Machinery with a background in deep learning across video analysis and education, compilers and computer systems.