Multi-UAV pursuit-evasion, where pursuers aim to capture evaders, poses a key challenge for UAV swarm intelligence. Multi-agent reinforcement learning (MARL) has demonstrated potential in modeling cooperative behaviors, but most RL-based approaches remain constrained to simplified simulations with limited dynamics or fixed scenarios. Previous attempts to deploy RL policy to real-world pursuit-evasion are largely restricted to two-dimensional scenarios, such as ground vehicles or UAVs at fixed altitudes. In this paper, we address multi-UAV pursuit-evasion by considering UAV dynamics and physical constraints. We introduce an evader prediction-enhanced network to tackle partial observability in cooperative strategy learning. Additionally, we propose an adaptive environment generator within MARL training, enabling higher exploration efficiency and better policy generalization across diverse scenarios. Simulations show our method significantly outperforms all baselines in challenging scenarios, generalizing to unseen scenarios with a 100% capture rate. Finally, we derive a feasible policy via a two-stage reward refinement and deploy the policy on real quadrotors in a zero-shot manner. To our knowledge, this is the first work to derive and deploy an RL-based policy using collective thrust and body rates control commands for multi-UAV pursuit-evasion in unknown environments. The open-source code and videos are available at https://sites.google.com/view/pursuit-evasion-rl.

We present a sequential version of the kernelized Stein discrepancy, which allows for conducting goodness-of-fit tests for unnormalized densities that are continuously monitored and adaptively stopped. That is, the sample size need not be fixed prior to data collection; the practitioner can choose whether to stop the test or continue to gather evidence at any time while controlling the false discovery rate. In stark contrast to related literature, we do not impose uniform boundedness on the Stein kernel. Instead, we exploit the potential boundedness of the Stein kernel at arbitrary point evaluations to define test martingales, that give way to the subsequent novel sequential tests. We prove the validity of the test, as well as an asymptotic lower bound for the logarithmic growth of the wealth process under the alternative. We further illustrate the empirical performance of the test with a variety of distributions, including restricted Boltzmann machines.

In the field of locomotion task of quadruped robots, Blind Policy and Perceptive Policy each have their own advantages and limitations. The Blind Policy relies on preset sensor information and algorithms, suitable for known and structured environments, but it lacks adaptability in complex or unknown environments. The Perceptive Policy uses visual sensors to obtain detailed environmental information, allowing it to adapt to complex terrains, but its effectiveness is limited under occluded conditions, especially when perception fails. Unlike the Blind Policy, the Perceptive Policy is not as robust under these conditions. To address these challenges, we propose a MBC:Multi-Brain collaborative system that incorporates the concepts of Multi-Agent Reinforcement Learning and introduces collaboration between the Blind Policy and the Perceptive Policy. By applying this multi-policy collaborative model to a quadruped robot, the robot can maintain stable locomotion even when the perceptual system is impaired or observational data is incomplete. Our simulations and real-world experiments demonstrate that this system significantly improves the robot's passability and robustness against perception failures in complex environments, validating the effectiveness of multi-policy collaboration in enhancing robotic motion performance.

Abstract--Partially Observable Markov Decision Processes (POMDPs) provide a structured framework for decision-making under uncertainty, but their application requires efficient belief updates. Sequential Importance Resampling Particle Filters (SIRPF), also known as Bootstrap Particle Filters, are commonly used as belief updaters in large approximate POMDP solvers, but they face challenges such as particle deprivation and high computational costs as the system's state dimension grows. To address these issues, this study introduces Rao-Blackwellized POMDP (RB-POMDP) approximate solvers and outlines generic methods to apply Rao-Blackwellization in both belief updates and online planning. POMCPOW (left) and RB-POMCPOW (right) Tree Structure Comparison. Moreover, as Partially Observable Markov Decision Processes (POMDPs) the system's effective dimension grows, a substantial increase are a powerful mathematical framework for modeling in the number of particles may be required to maintain decision-making under uncertainty where an agent operates performance, resulting in high computational costs (e.g. Rao-Blackwellized Particle Filtering (RBPF) offer a promising POMDPs have been widely applied to various domains such solution to address some of these limitations of the SIRPF.

We introduce a novel tagging scheme for discontinuous named entity recognition based on an explicit description of the inner structure of discontinuous mentions. We rely on a weighted finite state automaton for both marginal and maximum a posteriori inference. As such, our method is sound in the sense that (1) well-formedness of predicted tag sequences is ensured via the automaton structure and (2) there is an unambiguous mapping between well-formed sequences of tags and (discontinuous) mentions. We evaluate our approach on three English datasets in the biomedical domain, and report comparable results to state-of-the-art while having a way simpler and faster model.

Probabilistic logical models are a core component of neurosymbolic AI and are important models in their own right for tasks that require high explainability. Unlike neural networks, logical models are often handcrafted using domain expertise, making their development costly and prone to errors. While there are algorithms that learn logical models from data, they are generally prohibitively expensive, limiting their applicability in real-world settings. In this work, we introduce precision and recall for logical rules and define their composition as rule utility -- a cost-effective measure to evaluate the predictive power of logical models. Further, we introduce SPECTRUM, a scalable framework for learning logical models from relational data. Its scalability derives from a linear-time algorithm that mines recurrent structures in the data along with a second algorithm that, using the cheap utility measure, efficiently ranks rules built from these structures. Moreover, we derive theoretical guarantees on the utility of the learnt logical model. As a result, SPECTRUM learns more accurate logical models orders of magnitude faster than previous methods on real-world datasets.

Computational modeling is a critical tool for understanding consciousness, but is it enough on its own? This paper discusses the necessity for an ontological basis of consciousness, and introduces a formal framework for grounding computational descriptions into an ontological substrate. Utilizing this technique, a method is demonstrated for estimating the difference in qualitative experience between two systems. This framework has wide applicability to computational theories of consciousness.

Appropriate medication dosages in the intensive care unit (ICU) are critical for patient survival. Heparin, used to treat thrombosis and inhibit blood clotting in the ICU, requires careful administration due to its complexity and sensitivity to various factors, including patient clinical characteristics, underlying medical conditions, and potential drug interactions. Incorrect dosing can lead to severe complications such as strokes or excessive bleeding. To address these challenges, this study proposes a reinforcement learning (RL)-based personalized optimal heparin dosing policy that guides dosing decisions reliably within the therapeutic range based on individual patient conditions. A batch-constrained policy was implemented to minimize out-of-distribution errors in an offline RL environment and effectively integrate RL with existing clinician policies. The policy's effectiveness was evaluated using weighted importance sampling, an off-policy evaluation method, and the relationship between state representations and Q-values was explored using t-SNE. Both quantitative and qualitative analyses were conducted using the Medical Information Mart for Intensive Care III (MIMIC-III) database, demonstrating the efficacy of the proposed RL-based medication policy. Leveraging advanced machine learning techniques and extensive clinical data, this research enhances heparin administration practices and establishes a precedent for the development of sophisticated decision-support tools in medicine.

The emergence of indoor aerial robots holds significant potential for enhancing construction site workers' productivity by autonomously performing inspection and mapping tasks. The key challenge to this application is ensuring navigation safety with human workers. While navigation in static environments has been extensively studied, navigating dynamic environments remains open due to challenges in perception and planning. Payload limitations of unmanned aerial vehicles limit them to using cameras with limited fields of view, resulting in unreliable perception and tracking during collision avoidance. Moreover, the unpredictable nature of the dynamic environments can quickly make the generated optimal trajectory outdated. To address these challenges, this paper presents a comprehensive navigation framework that incorporates both perception and planning, introducing the concept of dynamic obstacle intent prediction. Our perception module detects and tracks dynamic obstacles efficiently and handles tracking loss and occlusion during collision avoidance. The proposed intent prediction module employs a Markov Decision Process (MDP) to forecast potential actions of dynamic obstacles with the possible future trajectories. Finally, a novel intent-based planning algorithm, leveraging model predictive control (MPC), is applied to generate safe navigation trajectories. Simulation and physical experiments demonstrate that our method enables safe navigation in dynamic environments and achieves the fewest collisions compared to benchmarks.

The traditional approach to POMDPs is to convert them into fully observed MDPs by considering a belief state as an information state. However, a belief-state based approach requires perfect knowledge of the system dynamics and is therefore not applicable in the learning setting where the system model is unknown. Various approaches to circumvent this limitation have been proposed in the literature. We present a unified treatment of some of these approaches by viewing them as models where the agent maintains a local recursively updateable agent state and chooses actions based on the agent state. We highlight the different classes of agent-state based policies and the various approaches that have been proposed in the literature to find good policies within each class. These include the designer's approach to find optimal non-stationary agent-state based policies, policy search approaches to find a locally optimal stationary agent-state based policies, and the approximate information state to find approximately optimal stationary agent-state based policies. We then present how ideas from the approximate information state approach have been used to improve Q-learning and actor-critic algorithms for learning in POMDPs.