相关论文: COOL-MC: Verifying and Explaining RL Policies for …

We present the first model-free Reinforcement Learning (RL) algorithm to synthesise policies for an unknown Markov Decision Process (MDP), such that a linear time property is satisfied. The given temporal property is converted into a Limit…

Inspection and maintenance (I&M) planning involves sequential decision making under uncertainties and incomplete information, and can be modeled as a partially observable Markov decision process (POMDP). While single-agent deep…

We consider the reinforcement learning problem for partially observed Markov decision processes (POMDPs) with large or even countably infinite state spaces, where the controller has access to only noisy observations of the underlying…

Residential and commercial buildings, equipped with systems such as heat pumps (HPs), hot water tanks, or stationary energy storage, have a large potential to offer their consumption flexibility as grid services. In this work, we leverage…

Last-Level Cache (LLC) represents the bulk of a modern CPU processor's transistor budget and is essential for application performance as LLC enables fast access to data in contrast to much slower main memory. However, applications with…

Batch reinforcement learning (RL) aims at leveraging pre-collected data to find an optimal policy that maximizes the expected total rewards in a dynamic environment. The existing methods require absolutely continuous assumption (e.g., there…

Cooperative multi-agent reinforcement learning (MARL) is typically framed as a decentralised partially observable Markov decision process (Dec-POMDP), a setting whose hardness stems from two key challenges: partial observability and…

A general control policy framework based on deep reinforcement learning (DRL) is introduced for closed-loop decision making in subsurface flow settings. Traditional closed-loop modeling workflows in this context involve the repeated…

Strategic mining attacks, such as selfish mining, exploit blockchain consensus protocols by deviating from honest behavior to maximize rewards. Markov Decision Process (MDP) analysis faces scalability challenges in modern digital economics,…

Advanced control strategies like Model Predictive Control (MPC) offer significant energy savings for HVAC systems but often require substantial engineering effort, limiting scalability. Reinforcement Learning (RL) promises greater…

Industrial Vending Machines (IVMs) automate the dispensing of a variety of supplies like safety equipment and tools at customer sites, providing 24/7 access while tracking inventory in real-time. Industrial distribution companies typically…

The application of Deep Reinforcement Learning (DRL) to inventory management is an emerging field. However, traditional DRL algorithms, originally developed for diverse domains such as game-playing and robotics, may not be well-suited for…

We study the problem of learning safe control policies that are also effective; i.e., maximizing the probability of satisfying a linear temporal logic (LTL) specification of a task, and the discounted reward capturing the (classic) control…

Consider a discrete-time system in which a centralized controller (CC) is tasked with assigning at each time interval (or slot) K resources (or servers) to K out of M>=K nodes. When assigned a server, a node can execute a task. The tasks…

In this work, we study how to efficiently apply reinforcement learning (RL) for solving large-scale stochastic optimization problems by leveraging intervention models. The key of the proposed methodology is to better explore the solution…

Reinforcement learning (RL) is a key paradigm for post-training large language models (LLMs), but the widely used Group Relative Policy Optimization (GRPO) often suffers from entropy collapse: exploration quickly disappears, policies…

In this paper, a complete industrial validation of a recently published scheme for on-line adaptation of the control updating period in Model Predictive Control is proposed. The industrial process that serves in the validation is a…

Large Language Models (LLMs) increasingly rely on reinforcement learning with verifiable rewards (RLVR) to elicit reliable chain-of-thought reasoning. However, the training process remains bottlenecked by the computationally expensive…

High Performance Computing (HPC) systems are used across a wide range of disciplines for both large and complex computations. HPC systems often receive many thousands of computational tasks at a time, colloquially referred to as jobs. These…

We propose and analyze a model-based bootstrap for transition kernels in finite controlled Markov chains (CMCs) with possibly nonstationary or history-dependent control policies, a setting that arises naturally in offline reinforcement…