--Traffic congestion remains a major challenge for modern urban transportation, diminishing both efficiency and quality of life. While autonomous driving technologies and reinforcement learning (RL) have shown promise for improving traffic control, most prior work has focused on small-scale networks or isolated intersections. Large-scale mixed traffic control, involving both human-driven and robotic vehicles, remains underexplored. In this study, we propose a decentralized multi-agent reinforcement learning framework for managing large-scale mixed traffic networks, where intersections are controlled either by traditional traffic signals or by robotic vehicles. We evaluate our approach on a real-world network of 14 intersections in Colorado Springs, Colorado, USA, using average vehicle waiting time as the primary measure of traffic efficiency. We are exploring a problem that has not been sufficiently addressed: Is large-scale Multi-Agent Traffic Control (MTC) still feasible when facing time-varying Origin-Destination (OD) patterns?

The performance of Offline reinforcement learning is significantly impacted by the issue of state distributional shift, and out-of-distribution (OOD) state correction is a popular approach to address this problem. In this paper, we propose a novel method named Density-Aware Safety Perception (DASP) for OOD state correction. Specifically, our method encourages the agent to prioritize actions that lead to outcomes with higher data density, thereby promoting its operation within or the return to in-distribution (safe) regions. To achieve this, we optimize the objective within a variational framework that concurrently considers both the potential outcomes of decision-making and their density, thus providing crucial contextual information for safe decision-making. Finally, we validate the effectiveness and feasibility of our proposed method through extensive experimental evaluations on the offline MuJoCo and AntMaze suites.

Monte-Carlo tree search (MCTS) has driven many recent breakthroughs in deep reinforcement learning (RL). However, scaling MCTS to parallel compute has proven challenging in practice which has motivated alternative planners like sequential Monte-Carlo (SMC). Many of these SMC methods adopt particle filters for smoothing through a reformulation of RL as a policy inference problem. Yet, persisting design choices of these particle filters often conflict with the aim of online planning in RL, which is to obtain a policy improvement at the start of planning. Drawing inspiration from MCTS, we tailor SMC planners specifically for RL by improving data generation within the planner through constrained action sampling and explicit terminal state handling, as well as improving policy and value target estimation. This leads to our Trust-Region Twisted SMC (TRT-SMC), which shows improved runtime and sample-efficiency over baseline MCTS and SMC methods in both discrete and continuous domains.

Perching on structures such as trees, beams, and ledges is essential for extending the endurance of aerial robots by enabling energy conservation in standby or observation modes. A tethered tensile perching mechanism offers a simple, adaptable solution that can be retrofitted to existing robots and accommodates a variety of structure sizes and shapes. However, tethered tensile perching introduces significant modelling challenges which require precise management of aerial robot dynamics, including the cases of tether slack & tension, and momentum transfer. Achieving smooth wrapping and secure anchoring by targeting a specific tether segment adds further complexity. In this work, we present a novel trajectory framework for tethered tensile perching, utilizing reinforcement learning (RL) through the Soft Actor-Critic from Demonstrations (SACfD) algorithm. By incorporating both optimal and suboptimal demonstrations, our approach enhances training efficiency and responsiveness, achieving precise control over position and velocity. This framework enables the aerial robot to accurately target specific tether segments, facilitating reliable wrapping and secure anchoring. We validate our framework through extensive simulation and real-world experiments, and demonstrate effectiveness in achieving agile and reliable trajectory generation for tensile perching.

Deploying reinforcement learning (RL) policies in real-world involves significant challenges, including distribution shifts, safety concerns, and the impracticality of direct interactions during policy refinement. Existing methods, such as domain randomization (DR) and off-dynamics RL, enhance policy robustness by direct interaction with the target domain, an inherently unsafe practice. We propose Uncertainty-Aware RL (UARL), a novel framework that prioritizes safety during training by addressing Out-Of-Distribution (OOD) detection and policy adaptation without requiring direct interactions in target domain. UARL employs an ensemble of critics to quantify policy uncertainty and incorporates progressive environmental randomization to prepare the policy for diverse real-world conditions. By iteratively refining over high-uncertainty regions of the state space in simulated environments, UARL enhances robust generalization to the target domain without explicitly training on it. We evaluate UARL on MuJoCo benchmarks and a quadrupedal robot, demonstrating its effectiveness in reliable OOD detection, improved performance, and enhanced sample efficiency compared to baselines.

Underwater Acoustic Networks (UANs) have gained significant attention from both industry and academia due to their indisputable advantages in improving link reliability, increasing system capacity, expanding transmission range and so on. Acoustic communication is most widely used underwater communication as sound wave is not absorbed by water so easily like electromagnetic wave and optical wave [1]. UANs typically consist of acoustic-linked seabed sensors, autonomous underwater vehicles, and ground stations that provide links to onshore control centers. Due to the battery-powered network nodes, shallow water acoustic channel characteristics, such as low available bandwidth and highly varying multi-path, maximizing throughput while minimizing consumption has become a very challenging task [2]. Recent studies have discussed the challenges and opportunities of underwater cognitive communication [3], proposed cooperative automatic repeat request protocols for higher channel quality [4], and analyzed the impact of low transmission rates and long preambles on medium access control protocols [5]. Artificial intelligence (AI) has experienced significant growth in popularity in recent years, and many industries and research fields have explored its potential applications, including information theory, game theory, biological systems, and so on [6-9].

With the emergence of compute-intensive and delay-sensitive applications in vehicular networks, unmanned aerial vehicles (UAVs) have emerged as a promising complement for vehicular edge computing due to the high mobility and flexible deployment. However, the existing UAV-assisted offloading strategies are insufficient in coordinating heterogeneous computing resources and adapting to dynamic network conditions. Hence, this paper proposes a dual-layer UAV-assisted edge computing architecture based on partial offloading, composed of the relay capability of high-altitude UAVs and the computing support of low-altitude UAVs. The proposed architecture enables efficient integration and coordination of heterogeneous resources. A joint optimization problem is formulated to minimize the system delay and energy consumption while ensuring the task completion rate. To solve the high-dimensional decision problem, we reformulate the problem as a Markov decision process and propose a hierarchical offloading scheme based on the soft actor-critic algorithm. The method decouples global and local decisions, where the global decisions integrate offloading ratios and trajectory planning into continuous actions, while the local scheduling is handled via designing a priority-based mechanism. Simulations are conducted and demonstrate that the proposed approach outperforms several baselines in task completion rate, system efficiency, and convergence speed, showing strong robustness and applicability in dynamic vehicular environments.

Recently, there has been a surge of vision-based GUI agents designed to automate everyday mobile and web tasks. These agents interpret raw GUI screenshots and autonomously decide where to click, scroll, or type, which bypasses handcrafted rules and app-specific APIs. However, most existing methods trained GUI agent in the offline environment using pre-collected trajectories. This approach limits scalability, causes overfitting to specific UI templates, and leads to brittle policies when faced with unseen environment. We present MobileGUI-RL, a scalable framework that trains GUI agent in online environment. MobileGUI-RL contains two key components. It (i) synthesizes a curriculum of learnable tasks through self-exploration and filtering, and (ii) adapts GRPO to GUI navigation with trajectory-aware advantages and composite rewards that balance task success and execution efficiency. Experiments on three online mobile-agent benchmarks show consistent gains, validating the effectiveness of our approach.

In many reinforcement learning (RL) applications, augmenting the task rewards with heuristic rewards that encode human priors about how a task should be solved is crucial for achieving desirable performance. However, because such heuristics are usually not optimal, much human effort and computational resources are wasted in carefully balancing tasks and heuristic rewards. Theoretically rigorous ways of incorporating heuristics rely on the idea of \textit{policy invariance}, which guarantees that the performance of a policy obtained by maximizing heuristic rewards is the same as the optimal policy with respect to the task reward. However, in practice, policy invariance doesn't result in policy improvement, and such methods are known to empirically perform poorly. We propose a new paradigm to mitigate reward hacking and effectively use heuristics based on the practical goal of maximizing policy improvement instead of policy improvement. Our framework, Heuristic Enhanced Policy Optimization (HEPO), effectively leverages heuristics while avoiding the pitfall of prior methods for mitigating reward hacking. HEPO achieves superior performance on standard benchmarks with well-engineered reward functions. More surprisingly, HEPO allows policy optimization to achieve good performance even when heuristics are not well-engineered and designed by non-expert humans, showcasing HEPO's ability to reduce human effort in reward design. % HEPO is a plug-and-play optimization method for leveraging heuristics in reinforcement learning. Code is available at https://github.com/Improbable-AI/hepo.

ObjectRL is an open-source Python codebase for deep reinforcement learning (RL), designed for research-oriented prototyping with minimal programming effort. Unlike existing codebases, ObjectRL is built on Object-Oriented Programming (OOP) principles, providing a clear structure that simplifies the implementation, modification, and evaluation of new algorithms. ObjectRL lowers the entry barrier for deep RL research by organizing best practices into explicit, clearly separated components, making them easier to understand and adapt. Each algorithmic component is a class with attributes that describe key RL concepts and methods that intuitively reflect their interactions. The class hierarchy closely follows common ontological relationships, enabling data encapsulation, inheritance, and polymorphism, which are core features of OOP. We demonstrate the efficiency of ObjectRL's design through representative use cases that highlight its flexibility and suitability for rapid prototyping. The documentation and source code are available at https://objectrl.readthedocs.io and https://github.com/adinlab/objectrl .