This problem arises in a number of mechanism design contexts, where intervening on a system constitutes changing the rules of the game. Calculating counterfactual value requires reasoning about how rule changes affect equilibrium behavior of the agents. Under strong assumptions this counterfactual value is point-identified, but these assumptions are often implausible. The authors present a scheme for relaxing these assumptions, and characterizing the set of values that are compatible with the observed data under this relaxation. The relaxation of point-identification assumptions is presented in terms of a second game, which the authors call the Revelation Game.

Fox News correspondent David Spunt has the latest on the debate surrounding President Donald Trump's efforts to overhaul the FBI and Justice Department on'Special Report.' FBI employees who "simply followed orders" with respect to their investigations into Jan. Bove's memo this week accused Acting FBI Director Brian Driscoll of refusing to reply to requests from President Donald Trump's administration to identify "the core team in Washington, D.C. responsible for the investigation relating to events on January 6, 2021." "That insubordination necessitated, among other things, the directive in my January 31, 2025 memo to identify all agents assigned to investigations relating to January 6, 2021. In light of acting leadership's refusal to comply with the narrower request, the written directive was intended to obtain a complete data set that the Justice Department can reliably pare down to the core team that will be the focus of the weaponization review pursuant to the Executive Order," Bove wrote.

We focus on human-robot collaborative transport, in which a robot and a user collaboratively move an object to a goal pose. In the absence of explicit communication, this problem is challenging because it demands tight implicit coordination between two heterogeneous agents, who have very different sensing, actuation, and reasoning capabilities. Our key insight is that the two agents can coordinate fluently by encoding subtle, communicative signals into actions that affect the state of the transported object. To this end, we design an inference mechanism that probabilistically maps observations of joint actions executed by the two agents to a set of joint strategies of workspace traversal. Based on this mechanism, we define a cost representing the human's uncertainty over the unfolding traversal strategy and introduce it into a model predictive controller that balances between uncertainty minimization and efficiency maximization. We deploy our framework on a mobile manipulator (Hello Robot Stretch) and evaluate it in a within-subjects lab study (N=24). We show that our framework enables greater team performance and empowers the robot to be perceived as a significantly more fluent and competent partner compared to baselines lacking a communicative mechanism.

Control policies that can achieve high task performance and satisfy safety constraints are desirable for any system, including multi-agent systems (MAS). One promising technique for ensuring the safety of MAS is distributed control barrier functions (CBF). However, it is difficult to design distributed CBF-based policies for MAS that can tackle unknown discrete-time dynamics, partial observability, changing neighborhoods, and input constraints, especially when a distributed high-performance nominal policy that can achieve the task is unavailable. To tackle these challenges, we propose DGPPO, a new framework that simultaneously learns both a discrete graph CBF which handles neighborhood changes and input constraints, and a distributed high-performance safe policy for MAS with unknown discrete-time dynamics. The results suggest that, compared with existing methods, our DGPPO framework obtains policies that achieve high task performance (matching baselines that ignore the safety constraints), and high safety rates (matching the most conservative baselines), with a constant set of hyperparameters across all environments. Multi-agent systems (MAS) have gained significant attention in recent years due to their potential applications in various domains such as warehouse robotics (Kattepur et al., 2018), autonomous vehicles (Shalev-Shwartz et al., 2016), traffic routing (Wu et al., 2020) and power systems Biagioni et al. (2022). However, a big challenge for MAS is designing distributed control policies that can achieve high task performance while ensuring safety, especially when the two are conflicting. In the single-agent continuous-time case, control barrier functions (CBF) are an effective tool to resolve the conflict via the solution of a safety filter quadratic program (QP) (Xu et al., 2015; Ames et al., 2017), minimally modifying a given performance-oriented nominal policy to be safe. While distributed CBFs have been proposed for the multi-agent (Wang et al., 2017) and partially observable cases (Zhang et al., 2025), they have a limitation of requiring known continuous-time dynamics and a nominal policy that can achieve high task performance (albeit not necessarily safely). While the aforementioned assumptions are reasonable for many applications, they do not apply when the dynamics are unknown and a performance-oriented nominal policy is not available. The challenge of requiring a nominal policy has been addressed by approaches that combine CBFs with reinforcement learning (RL) (Cheng et al., 2019; Emam et al., 2022), where the nominal policy is learned via an unconstrained RL algorithm to maximize task performance while the CBF is used as a safety filter to ensure safety.

Medication adherence is critical for the recovery of adolescents and young adults (AYAs) who have undergone hematopoietic cell transplantation (HCT). However, maintaining adherence is challenging for AYAs after hospital discharge, who experience both individual (e.g. physical and emotional symptoms) and interpersonal barriers (e.g., relational difficulties with their care partner, who is often involved in medication management). To optimize the effectiveness of a three-component digital intervention targeting both members of the dyad as well as their relationship, we propose a novel Multi-Agent Reinforcement Learning (MARL) approach to personalize the delivery of interventions. By incorporating the domain knowledge, the MARL framework, where each agent is responsible for the delivery of one intervention component, allows for faster learning compared with a flattened agent. Evaluation using a dyadic simulator environment, based on real clinical data, shows a significant improvement in medication adherence (approximately 3%) compared to purely random intervention delivery. The effectiveness of this approach will be further evaluated in an upcoming trial.

Learning from active human involvement enables the human subject to actively intervene and demonstrate to the AI agent during training. The interaction and corrective feedback from human brings safety and AI alignment to the learning process. In this work, we propose a new reward-free active human involvement method called Proxy Value Propagation for policy optimization. Our key insight is that a proxy value function can be designed to express human intents, wherein state-action pairs in the human demonstration are labeled with high values, while those agents' actions that are intervened receive low values. Through the TD-learning framework, labeled values of demonstrated state-action pairs are further propagated to other unlabeled data generated from agents' exploration. The proxy value function thus induces a policy that faithfully emulates human behaviors. Human-in-the-loop experiments show the generality and efficiency of our method. With minimal modification to existing reinforcement learning algorithms, our method can learn to solve continuous and discrete control tasks with various human control devices, including the challenging task of driving in Grand Theft Auto V. Demo video and code are available at: https://metadriverse.github.io/pvp

Recently, mobile AI agents have gained increasing attention. Given a task, mobile AI agents can interact with mobile devices in multiple steps and finally form a GUI flow that solves the task. However, existing agents tend to focus on most task-relevant elements at each step, leading to local optimal solutions and ignoring the overall GUI flow. To address this issue, we constructed a training dataset called MobileReach, which breaks the task into page reaching and operation subtasks. Furthermore, we propose ReachAgent, a two-stage framework that focuses on improving its task-completion abilities. It utilizes the page reaching and page operation subtasks, along with reward-based preference GUI flows, to further enhance the agent. Experimental results show that ReachAgent significantly improves the IoU Acc and Text Acc by 7.12% and 7.69% on the step-level and 4.72% and 4.63% on the task-level compared to the SOTA agent. Our data and code will be released upon acceptance.

Self-play has powered breakthroughs in two-player and multi-player games. Here we show that self-play is a surprisingly effective strategy in another domain. We show that robust and naturalistic driving emerges entirely from self-play in simulation at unprecedented scale -- 1.6~billion~km of driving. This is enabled by Gigaflow, a batched simulator that can synthesize and train on 42 years of subjective driving experience per hour on a single 8-GPU node. The resulting policy achieves state-of-the-art performance on three independent autonomous driving benchmarks. The policy outperforms the prior state of the art when tested on recorded real-world scenarios, amidst human drivers, without ever seeing human data during training. The policy is realistic when assessed against human references and achieves unprecedented robustness, averaging 17.5 years of continuous driving between incidents in simulation.

Effective budget allocation is crucial for optimizing the performance of digital advertising campaigns. However, the development of practical budget allocation algorithms remain limited, primarily due to the lack of public datasets and comprehensive simulation environments capable of verifying the intricacies of real-world advertising. While multi-armed bandit (MAB) algorithms have been extensively studied, their efficacy diminishes in non-stationary environments where quick adaptation to changing market dynamics is essential. In this paper, we advance the field of budget allocation in digital advertising by introducing three key contributions. First, we develop a simulation environment designed to mimic multichannel advertising campaigns over extended time horizons, incorporating logged real-world data. Second, we propose an enhanced combinatorial bandit budget allocation strategy that leverages a saturating mean function and a targeted exploration mechanism with change-point detection. This approach dynamically adapts to changing market conditions, improving allocation efficiency by filtering target regions based on domain knowledge. Finally, we present both theoretical analysis and empirical results, demonstrating that our method consistently outperforms baseline strategies, achieving higher rewards and lower regret across multiple real-world campaigns.

Game-theoretic models are effective tools for modeling multi-agent interactions, especially when robots need to coordinate with humans. However, applying these models requires inferring their specifications from observed behaviors -- a challenging task known as the inverse game problem. Existing inverse game approaches often struggle to account for behavioral uncertainty and measurement noise, and leverage both offline and online data. To address these limitations, we propose an inverse game method that integrates a generative trajectory model into a differentiable mixed-strategy game framework. By representing the mixed strategy with a conditional variational autoencoder (CVAE), our method can infer high-dimensional, multi-modal behavior distributions from noisy measurements while adapting in real-time to new observations. We extensively evaluate our method in a simulated navigation benchmark, where the observations are generated by an unknown game model. Despite the model mismatch, our method can infer Nash-optimal actions comparable to those of the ground-truth model and the oracle inverse game baseline, even in the presence of uncertain agent objectives and noisy measurements.