Related papers: Hyperfastrl: Hypernetwork-based reinforcement lear…

Graph Representation Learning (GRL) can be fundamentally modeled as a physical process of seeking an energy equilibrium state for a node system on a latent manifold. However, existing Graph Neural Networks (GNNs) often suffer from…

We develop a machine-learning framework to learn hyperparameter sequences for accelerated first-order methods (e.g., the step size and momentum sequences in accelerated gradient descent) to quickly solve parametric convex optimization…

The goal of many applications in energy and transport sectors is to control turbulent flows. However, because of chaotic dynamics and high dimensionality, the control of turbulent flows is exceedingly difficult. Model-free reinforcement…

This article addresses the pump-scheduling optimization problem to enhance real-time control of real-world water distribution networks (WDNs). Our primary objectives are to adhere to physical operational constraints while reducing energy…

In this paper, we consider the problem of accelerating the numerical simulation of time dependent problems by time domain decomposition. The available algorithms enabling such decompositions present severe efficiency limitations and are an…

Accelerating artificial intelligence by photonics is an active field of study aiming to exploit the unique properties of photons. Reinforcement learning is an important branch of machine learning, and photonic decision-making principles…

High-order tuners are algorithms that show promise in achieving greater efficiency than classic gradient-based algorithms in identifying the parameters of parametric models and/or in facilitating the progress of a control or optimization…

Despite the wealth of research into provably efficient reinforcement learning algorithms, most works focus on tabular representation and thus struggle to handle exponentially or infinitely large state-action spaces. In this paper, we…

Quantum control is concerned with the realisation of desired dynamics in quantum systems, serving as a linchpin for advancing quantum technologies and fundamental research. Analytic approaches and standard optimisation algorithms do not…

Self-paced reinforcement learning (RL) aims to improve the data efficiency of learning by automatically creating sequences, namely curricula, of probability distributions over contexts. However, existing techniques for self-paced RL fail in…

A central challenge in reinforcement learning is that policies trained in controlled environments often fail under distribution shifts at deployment into real-world environments. Distributionally Robust Reinforcement Learning (DRRL)…

This paper investigates the so-called reward-balancing methods, a novel class of algorithms for solving discounted-return reinforcement learning (RL) problems. These methods consist of iteratively adjusting the reward function to transform…

Modern large language model (LLM) training is inherently dynamic: resource fluctuations, RLHF phase shifts, and cluster elasticity continually reshape the optimal parallelism layout, posing a significant challenge to existing training…

This paper considers the problem of real-time control and learning in dynamic systems subjected to parametric uncertainties. We propose a combination of a Reinforcement Learning (RL) based policy in the outer loop suitably chosen to ensure…

Meta-Reinforcement Learning addresses the critical limitations of conventional Reinforcement Learning in multi-task and non-stationary environments by enabling fast policy adaptation and improved generalization. We introduce a novel Meta-RL…

Can reinforcement learning with hard, verifiable rewards teach a compact language model to reason about physics, or does it primarily learn to pattern-match toward correct answers? We study this question by training a 1.5B-parameter…

This paper discusses learning a structured feedback control to obtain sufficient robustness to exogenous inputs for linear dynamic systems with unknown state matrix. The structural constraint on the controller is necessary for many…

Federated learning (FL) enables distributed devices to train a shared machine learning (ML) model collaboratively while protecting their data privacy. However, the resource-limited mobile devices suffer from intensive…

Single-task RL agents are typically trained under a fixed reward function, which limits their robustness to reward misspecification and their ability to adapt to changing preferences. We introduce Reward-Conditioned Reinforcement Learning…

This work investigates transfer learning strategies to accelerate deep reinforcement learning (DRL) for multifidelity control of chaotic fluid flows. Progressive neural networks (PNNs), a modular architecture designed to preserve and reuse…