Learning-based decision-making has the potential to enable generalizable Autonomous Driving (AD) policies, reducing the engineering overhead of rule-based approaches. Imitation Learning (IL) remains the dominant paradigm, benefiting from large-scale human demonstration datasets, but it suffers from inherent limitations such as distribution shift and imitation gaps. Reinforcement Learning (RL) presents a promising alternative, yet its adoption in AD remains limited due to the lack of standardized and efficient research frameworks. To this end, we introduce V-Max, an open research framework providing all the necessary tools to make RL practical for AD. V-Max is built on Waymax, a hardware-accelerated AD simulator designed for large-scale experimentation. We extend it using ScenarioNet's approach, enabling the fast simulation of diverse AD datasets. V-Max integrates a set of observation and reward functions, transformer-based encoders, and training pipelines. Additionally, it includes adversarial evaluation settings and an extensive set of evaluation metrics. Through a large-scale benchmark, we analyze how network architectures, observation functions, training data, and reward shaping impact RL performance.

Aligning robot navigation with human preferences is essential for ensuring comfortable and predictable robot movement in shared spaces, facilitating seamless human-robot coexistence. While preference-based learning methods, such as reinforcement learning from human feedback (RLHF), enable this alignment, the choice of the preference collection interface may influence the process. Traditional 2D interfaces provide structured views but lack spatial depth, whereas immersive VR offers richer perception, potentially affecting preference articulation. This study systematically examines how the interface modality impacts human preference collection and navigation policy alignment. We introduce a novel dataset of 2,325 human preference queries collected through both VR and 2D interfaces, revealing significant differences in user experience, preference consistency, and policy outcomes. Our findings highlight the trade-offs between immersion, perception, and preference reliability, emphasizing the importance of interface selection in preference-based robot learning. The dataset will be publicly released to support future research.

Managing equal charge levels in active cell balancing while charging a Li-ion battery is challenging. An imbalance in charge levels affects the state of health of the battery, along with the concerns of thermal runaway and fire hazards. Traditional methods focus on safety assurance as a trade-off between safety and charging time. Others deal with battery-specific conditions to ensure safety, therefore losing on the generalization of the control strategies over various configurations of batteries. In this work, we propose a method to learn safe battery charging actions by using a safety-layer as an add-on over a Deep Reinforcement Learning (RL) agent. The safety layer perturbs the agent's action to prevent the battery from encountering unsafe or dangerous states. Further, our Deep RL framework focuses on learning a generalized policy that can be effectively employed with varying configurations of batteries. Our experimental results demonstrate that the safety-layer based action perturbation incurs fewer safety violations by avoiding unsafe states along with learning a robust policy for several battery configurations.

Autonomous vehicles (AVs) are transforming modern transportation, but their reliability and safety are significantly challenged by harsh weather conditions such as heavy rain, fog, and snow. These environmental factors impair the performance of cameras, LiDAR, and radar, leading to reduced situational awareness and increased accident risks. Conventional cloud-based AI systems introduce communication delays, making them unsuitable for the rapid decision-making required in real-time autonomous navigation. This paper presents a novel Edge AI-driven real-time decision-making framework designed to enhance AV responsiveness under adverse weather conditions. The proposed approach integrates convolutional neural networks (CNNs) and recurrent neural networks (RNNs) for improved perception, alongside reinforcement learning (RL)-based strategies to optimize vehicle control in uncertain environments. By processing data at the network edge, this system significantly reduces decision latency while improving AV adaptability. The framework is evaluated using simulated driving scenarios in CARLA and real-world data from the Waymo Open Dataset, covering diverse weather conditions. Experimental results indicate that the proposed model achieves a 40% reduction in processing time and a 25% enhancement in perception accuracy compared to conventional cloud-based systems.

Quadrupeds have gained rapid advancement in their capability of traversing across complex terrains. The adoption of deep Reinforcement Learning (RL), transformers and various knowledge transfer techniques can greatly reduce the sim-to-real gap. However, the classical teacher-student framework commonly used in existing locomotion policies requires a pre-trained teacher and leverages the privilege information to guide the student policy. With the implementation of large-scale models in robotics controllers, especially transformers-based ones, this knowledge distillation technique starts to show its weakness in efficiency, due to the requirement of multiple supervised stages. In this paper, we propose Unified Locomotion Transformer (ULT), a new transformer-based framework to unify the processes of knowledge transfer and policy optimization in a single network while still taking advantage of privilege information. The policies are optimized with reinforcement learning, next state-action prediction, and action imitation, all in just one training stage, to achieve zero-shot deployment. Evaluation results demonstrate that with ULT, optimal teacher and student policies can be obtained at the same time, greatly easing the difficulty in knowledge transfer, even with complex transformer-based models.

Sixth generation (6G) wireless technology is anticipated to introduce Integrated Sensing and Communication (ISAC) as a transformative paradigm. ISAC unifies wireless communication and RADAR or other forms of sensing to optimize spectral and hardware resources. This paper presents a pioneering framework that leverages ISAC sensing data to enhance beam selection processes in complex indoor environments. By integrating multi-modal transformer models with a multi-agent contextual bandit algorithm, our approach utilizes ISAC sensing data to improve communication performance and achieves high spectral efficiency (SE). Specifically, the multi-modal transformer can capture inter-modal relationships, enhancing model generalization across diverse scenarios. Experimental evaluations on the DeepSense 6G dataset demonstrate that our model outperforms traditional deep reinforcement learning (DRL) methods, achieving superior beam prediction accuracy and adaptability. In the single-user scenario, we achieve an average SE regret improvement of 49.6% as compared to DRL. Furthermore, we employ transfer reinforcement learning to reduce training time and improve model performance in multi-user environments. In the multi-user scenario, this approach enhances the average SE regret, which is a measure to demonstrate how far the learned policy is from the optimal SE policy, by 19.7% compared to training from scratch, even when the latter is trained 100 times longer.

We integrate a meta-reinforcement learning algorithm with the DreamerV3 architecture to improve load balancing in operating systems. This approach enables rapid adaptation to dynamic workloads with minimal retraining, outperforming the Advantage Actor-Critic (A2C) algorithm in standard and adaptive trials. It demonstrates robust resilience to catastrophic forgetting, maintaining high performance under varying workload distributions and sizes. These findings have important implications for optimizing resource management and performance in modern operating systems. By addressing the challenges posed by dynamic and heterogeneous workloads, our approach advances the adaptability and efficiency of reinforcement learning in real-world system management tasks.

Reinforcement Learning (RL) has demonstrated remarkable success in solving sequential decision-making problems. However, in real-world scenarios, RL agents often struggle to generalize when faced with unseen actions that were not encountered during training. Some previous works on zero-shot action generalization rely on large datasets of action observations to capture the behaviors of new actions, making them impractical for real-world applications. In this paper, we introduce a novel zero-shot framework, Action Generalization from Limited Observations (AGLO). Our framework has two main components: an action representation learning module and a policy learning module. The action representation learning module extracts discriminative embeddings of actions from limited observations, while the policy learning module leverages the learned action representations, along with augmented synthetic action representations, to learn a policy capable of handling tasks with unseen actions. The experimental results demonstrate that our framework significantly outperforms state-of-the-art methods for zero-shot action generalization across multiple benchmark tasks, showcasing its effectiveness in generalizing to new actions with minimal action observations.

Efficient probabilistic inference by variable elimination in graphical models requires an optimal elimination order. However, finding an optimal order is a challenging combinatorial optimisation problem for models with a large number of random variables. Most recently, a reinforcement learning approach has been proposed to find efficient contraction orders in tensor networks. Due to the duality between graphical models and tensor networks, we adapt this approach to probabilistic inference in graphical models. Furthermore, we incorporate structure exploitation into the process of finding an optimal order. Currently, the agent's cost function is formulated in terms of intermediate result sizes which are exponential in the number of indices (i.e., random variables). We show that leveraging specific structures during inference allows for introducing compact encodings of intermediate results which can be significantly smaller. By considering the compact encoding sizes for the cost function instead, we enable the agent to explore more efficient contraction orders. The structure we consider in this work is the presence of local symmetries (i.e., symmetries within a model's factors).

Training visual reinforcement learning (RL) in practical scenarios presents a significant challenge, $\textit{i.e.,}$ RL agents suffer from low sample efficiency in environments with variations. While various approaches have attempted to alleviate this issue by disentanglement representation learning, these methods usually start learning from scratch without prior knowledge of the world. This paper, in contrast, tries to learn and understand underlying semantic variations from distracting videos via offline-to-online latent distillation and flexible disentanglement constraints. To enable effective cross-domain semantic knowledge transfer, we introduce an interpretable model-based RL framework, dubbed Disentangled World Models (DisWM). Specifically, we pretrain the action-free video prediction model offline with disentanglement regularization to extract semantic knowledge from distracting videos. The disentanglement capability of the pretrained model is then transferred to the world model through latent distillation. For finetuning in the online environment, we exploit the knowledge from the pretrained model and introduce a disentanglement constraint to the world model. During the adaptation phase, the incorporation of actions and rewards from online environment interactions enriches the diversity of the data, which in turn strengthens the disentangled representation learning. Experimental results validate the superiority of our approach on various benchmarks.