Free-flow road networks, such as suburban highways, are increasingly experiencing traffic congestion due to growing commuter inflow and limited infrastructure. Traditional control mechanisms, such as traffic signals or local heuristics, are ineffective or infeasible in these high-speed, signal-free environments. We introduce self-regulating cars, a reinforcement learning-based traffic control protocol that dynamically modulates vehicle speeds to optimize throughput and prevent congestion, without requiring new physical infrastructure. Our approach integrates classical traffic flow theory, gap acceptance models, and microscopic simulation into a physics-informed RL framework. By abstracting roads into super-segments, the agent captures emergent flow dynamics and learns robust speed modulation policies from instantaneous traffic observations. Evaluated in the high-fidelity PTV Vissim simulator on a real-world highway network, our method improves total throughput by 5%, reduces average delay by 13%, and decreases total stops by 3% compared to the no-control setting. It also achieves smoother, congestion-resistant flow while generalizing across varied traffic patterns, demonstrating its potential for scalable, ML-driven traffic management.

Variations in hidden parameters, such as a robot's mass distribution or friction, pose safety risks during execution. We develop a runtime shielding mechanism for reinforcement learning, building on the formalism of constrained hidden-parameter Markov decision processes. Function encoders enable real-time inference of hidden parameters from observations, allowing the shield and the underlying policy to adapt online. The shield constrains the action space by forecasting future safety risks (such as obstacle proximity) and accounts for uncertainty via conformal prediction. We prove that the proposed mechanism satisfies probabilistic safety guarantees and yields optimal policies among the set of safety-compliant policies. Experiments across diverse environments with varying hidden parameters show that our method significantly reduces safety violations and achieves strong out-of-distribution generalization, while incurring minimal runtime overhead.

Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in understanding common visual elements, largely due to their large-scale datasets and advanced training strategies. However, their effectiveness in medical applications remains limited due to the inherent discrepancies between data and tasks in medical scenarios and those in the general domain. Concretely, existing medical MLLMs face the following critical limitations: (1) limited coverage of medical knowledge beyond imaging, (2) heightened susceptibility to hallucinations due to suboptimal data curation processes, (3) lack of reasoning capabilities tailored for complex medical scenarios. To address these challenges, we first propose a comprehensive data curation procedure that (1) efficiently acquires rich medical knowledge data not only from medical imaging but also from extensive medical texts and general-domain data; and (2) synthesizes accurate medical captions, visual question answering (VQA), and reasoning samples. As a result, we build a multimodal dataset enriched with extensive medical knowledge. Building on the curated data, we introduce our medical-specialized MLLM: Lingshu. Lingshu undergoes multi-stage training to embed medical expertise and enhance its task-solving capabilities progressively. Besides, we preliminarily explore the potential of applying reinforcement learning with verifiable rewards paradigm to enhance Lingshu's medical reasoning ability. Additionally, we develop MedEvalKit, a unified evaluation framework that consolidates leading multimodal and textual medical benchmarks for standardized, fair, and efficient model assessment. We evaluate the performance of Lingshu on three fundamental medical tasks, multimodal QA, text-based QA, and medical report generation. The results show that Lingshu consistently outperforms the existing open-source multimodal models on most tasks ...

Open-ended learning (OEL) -- which emphasizes training agents that achieve broad capability over narrow competency -- is emerging as a paradigm to develop artificial intelligence (AI) agents to achieve robustness and generalization. However, despite promising results that demonstrate the benefits of OEL, applying OEL to develop autonomous agents for real-world cybersecurity applications remains a challenge. We propose a training approach, inspired by OEL, to develop autonomous network defenders. Our results demonstrate that like in other domains, OEL principles can translate into more robust and generalizable agents for cyber defense. To apply OEL to network defense, it is necessary to address several technical challenges. Most importantly, it is critical to provide a task representation approach over a broad universe of tasks that maintains a consistent interface over goals, rewards and action spaces. This way, the learning agent can train with varying network conditions, attacker behaviors, and defender goals while being able to build on previously gained knowledge. With our tools and results, we aim to fundamentally impact research that applies AI to solve cybersecurity problems. Specifically, as researchers develop gyms and benchmarks for cyber defense, it is paramount that they consider diverse tasks with consistent representations, such as those we propose in our work.

Learning to cooperate in distributed partially observable environments with no communication abilities poses significant challenges for multi-agent deep reinforcement learning (MARL). This paper addresses key concerns in this domain, focusing on inferring state representations from individual agent observations and leveraging these representations to enhance agents' exploration and collaborative task execution policies. To this end, we propose a novel state modelling framework for cooperative MARL, where agents infer meaningful belief representations of the non-observable state, with respect to optimizing their own policies, while filtering redundant and less informative joint state information. Building upon this framework, we propose the MARL SMPE algorithm. In SMPE, agents enhance their own policy's discriminative abilities under partial observability, explicitly by incorporating their beliefs into the policy network, and implicitly by adopting an adversarial type of exploration policies which encourages agents to discover novel, high-value states while improving the discriminative abilities of others. Experimentally, we show that SMPE outperforms state-of-the-art MARL algorithms in complex fully cooperative tasks from the MPE, LBF, and RWARE benchmarks.

High-dose-rate (HDR) brachytherapy plays a critical role in the treatment of locally advanced cervical cancer but remains highly dependent on manual treatment planning expertise. The objective of this study is to develop a fully automated HDR brachytherapy planning framework that integrates reinforcement learning (RL) and dose-based optimization to generate clinically acceptable treatment plans with improved consistency and efficiency. We propose a hierarchical two-stage autoplanning framework. In the first stage, a deep Q-network (DQN)-based RL agent iteratively selects treatment planning parameters (TPPs), which control the trade-offs between target coverage and organ-at-risk (OAR) sparing. The agent's state representation includes both dose-volume histogram (DVH) metrics and current TPP values, while its reward function incorporates clinical dose objectives and safety constraints, including D90, V150, V200 for targets, and D2cc for all relevant OARs (bladder, rectum, sigmoid, small bowel, and large bowel). In the second stage, a customized Adam-based optimizer computes the corresponding dwell time distribution for the selected TPPs using a clinically informed loss function. The framework was evaluated on a cohort of patients with complex applicator geometries. The proposed framework successfully learned clinically meaningful TPP adjustments across diverse patient anatomies. For the unseen test patients, the RL-based automated planning method achieved an average score of 93.89%, outperforming the clinical plans which averaged 91.86%. These findings are notable given that score improvements were achieved while maintaining full target coverage and reducing CTV hot spots in most cases.

Recent work has shown that reinforcement learning agents can develop policies that exploit spurious correlations between rewards and observations. This phenomenon, known as policy confounding, arises because the agent's policy influences both past and future observation variables, creating a feedback loop that can hinder the agent's ability to generalize beyond its usual trajectories. In this paper, we show that the advantage function, commonly used in policy gradient methods, not only reduces the variance of gradient estimates but also mitigates the effects of policy confounding. By adjusting action values relative to the state representation, the advantage function downweights state-action pairs that are more likely under the current policy, breaking spurious correlations and encouraging the agent to focus on causal factors. We provide both analytical and empirical evidence demonstrating that training with the advantage function leads to improved out-of-trajectory performance.

-- Diagnostic errors remain a major cause of preventable deaths, particularly in resource-limited regions. Medical training simulators, including robopatients, play a vital role in reducing these errors by mimicking real patients for procedural training such as palpation. However, generating multimodal feedback, especially auditory pain expressions, remains challenging due to the complex relationship between palpation behavior and sound. The high-dimensional nature of pain sounds makes exploration challenging with conventional methods. This study introduces a novel experimental paradigm for pain expressivity in robopatients where they dynamically generate auditory pain expressions in response to palpation force, by co-optimizing human feedback using machine learning. Using Proximal Policy Optimization (PPO), a reinforcement learning (RL) technique optimized for continuous adaptation, our robot iteratively refines pain sounds based on real-time human feedback. This robot initializes randomized pain responses to palpation forces, and the RL agent learns to adjust these sounds to align with human preferences. The results demonstrated that the system adapts to an individual's palpation forces and sound preferences and captures a broad spectrum of pain intensity, from mild discomfort to acute distress, through RL-guided exploration of the auditory pain space. The study further showed that pain sound perception exhibits saturation at lower forces with gender-specific thresholds. These findings highlight the system's potential to enhance abdominal palpation training by offering a controllable and immersive simulation platform. While specific statistics vary by region, diagnostic errors are a universal concern. Misdiagnoses may contribute to the nearly 7 million children who die each year from preventable causes, particularly in low-and middle-income countries [1]. These findings underscore the critical need for systemic improvements in diagnostic processes, enhanced communication among healthcare providers, and increased patient engagement to mitigate the risks associated with diagnostic errors. Palpation is one of the primary examination methods used by physicians to examine patients in various conditions ranging from simple abdominal pain to more serious conditions such as acute appendicitis and breast, soft tissue tumors.

The competition over natural reserves of minerals is expected to increase in part because of the linear-economy paradigm based on take-make-dispose. Simultaneously, the linear economy considers end-of-use products as waste rather than as a resource, which results in large volumes of waste whose management remains an unsolved problem. Since a transition to a circular economy can mitigate these open issues, in this paper we begin by enhancing the notion of circularity based on compartmental dynamical thermodynamics, namely, $λ$, and then, we model a thermodynamical material network processing a batch of 2 solid materials of criticality coefficients of 0.1 and 0.95, with a robotic disassembler compartment controlled via reinforcement learning (RL), and processing 2-7 kg of materials. Subsequently, we focused on the design of the robotic disassembler compartment using state-of-the-art RL algorithms and assessing the algorithm performance with respect to $λ$ (Fig. 1). The highest circularity is -2.1 achieved in the case of disassembling 2 parts of 1 kg each, whereas it reduces to -7.2 in the case of disassembling 4 parts of 1 kg each contained inside a chassis of 3 kg. Finally, a sensitivity analysis highlighted that the impact on $λ$ of the performance of an RL controller has a positive correlation with the quantity and the criticality of the materials to be disassembled. This work also gives the principles of the emerging research fields indicated as circular intelligence and robotics (CIRO). Source code is publicly available.

While increasingly large models have revolutionized much of the machine learning landscape, training even mid-sized networks for Reinforcement Learning (RL) is still proving to be a struggle. This, however, severely limits the complexity of policies we are able to learn. To enable increased network capacity while maintaining network trainability, we propose GrowNN, a simple yet effective method that utilizes progressive network growth during training. We start training a small network to learn an initial policy. Then we add layers without changing the encoded function. Subsequent updates can utilize the added layers to learn a more expressive policy, adding capacity as the policy's complexity increases. GrowNN can be seamlessly integrated into most existing RL agents. Our experiments on MiniHack and Mujoco show improved agent performance, with incrementally GrowNN-deeper networks outperforming their respective static counterparts of the same size by up to 48% on MiniHack Room and 72% on Ant.