Related papers: Speculative Policy Orchestration: A Latency-Resili…

Leveraging planning during learning and decision-making is central to the long-term development of intelligent agents. Recent works have successfully combined tree-based search methods and self-play learning mechanisms to this end. However,…

We present a lightweight and interpretable decision framework for dynamic edge server selection in latency-critical applications that explicitly accounts for tail risk and switching stability. Each candidate server is characterised by…

Combinatorial optimization assumes that all parameters of the optimization problem, e.g. the weights in the objective function is fixed. Often, these weights are mere estimates and increasingly machine learning techniques are used to for…

In this paper, we examine cloud-edge-terminal IoT networks, where edges undertake a range of typical dynamic scheduling tasks. In these IoT networks, a central policy for each task can be constructed at a cloud server. The central policy…

Existing methods for vision-language task planning excel in short-horizon tasks but often fall short in complex, long-horizon planning within dynamic environments. These challenges primarily arise from the difficulty of effectively training…

Many real-world analytics problems involve two significant challenges: prediction and optimization. Due to the typically complex nature of each challenge, the standard paradigm is predict-then-optimize. By and large, machine learning tools…

Ubiquitous mobile devices have catalyzed the development of vehicle crowd sensing (VCS). In particular, vehicle sensing systems show great potential in the flexible acquisition of spatio-temporal urban data through built-in sensors under…

Modern edge AI applications increasingly rely on microservice architectures that integrate both AI services and conventional microservices into complex request chains with stringent latency requirements. Effectively orchestrating these…

Data-driven approaches to predict-then-optimize decision-making problems seek to mitigate the risk of uncertainty region misspecification in safety-critical settings. Current approaches, however, suffer from considering overly conservative…

We study reinforcement learning in hybrid discrete-continuous action spaces, such as settings where the discrete component selects a regime (or index) and the continuous component optimizes within it -- a structure common in robotics,…

Reinforcement learning (RL) plays an increasingly important role in enhancing the reasoning capabilities of large language models (LLMs), yet stable and performant policy optimization remains challenging. Token-level importance ratios often…

Recently significant progress has been made in vehicle prediction and planning algorithms for autonomous driving. However, it remains quite challenging for an autonomous vehicle to plan its trajectory in complex scenarios when it is…

Safety-critical learning requires policies that improve performance without leaving the safe operating regime. We study constrained policy learning where model parameters must satisfy rollout-based safety constraints that can be evaluated…

Expressive generative models have advanced robotic manipulation by capturing complex, multi-modal action distributions over temporally extended trajectories. However, fine-tuning these policies via RL remains challenging due to instability…

The predict-then-optimize (PTO) framework is indispensable for addressing practical stochastic decision-making tasks. It consists of two crucial steps: initially predicting unknown parameters of an optimization model and subsequently…

Model-based algorithms, which learn a dynamics model from logged experience and perform some sort of pessimistic planning under the learned model, have emerged as a promising paradigm for offline reinforcement learning (offline RL).…

Reinforcement Learning (RL) algorithms have shown tremendous success in simulation environments, but their application to real-world problems faces significant challenges, with safety being a major concern. In particular, enforcing…

The paradigm of robot-assisted surgery is shifting toward data-driven autonomy, where policies learned via Reinforcement Learning (RL) or Imitation Learning (IL) enable the execution of complex tasks. However, these ``black-box" policies…

Deep reinforcement learning algorithms can perform poorly in real-world tasks due to the discrepancy between source and target environments. This discrepancy is commonly viewed as the disturbance in transition dynamics. Many existing…

Enhancing the reasoning capabilities of large language models effectively using reinforcement learning (RL) remains a crucial challenge. Existing approaches primarily adopt two contrasting advantage estimation granularities: token-level…