Related papers: Resilient Constrained Learning
Meta-Reinforcement Learning (Meta-RL) aims to acquire meta-knowledge for quick adaptation to diverse tasks. However, applying these policies in real-world environments presents a significant challenge in balancing rapid adaptability with…
We introduce a class of concurrent learning (CL) algorithms designed to solve parameter estimation problems with convergence rates ranging from hyperexponential to prescribed-time while utilizing alternating datasets during the learning…
In many real world applications, reinforcement learning agents have to optimize multiple objectives while following certain rules or satisfying a list of constraints. Classical methods based on reward shaping, i.e. a weighted combination of…
We consider a distributed system, consisting of a heterogeneous set of devices, ranging from low-end to high-end. These devices have different profiles, e.g., different energy budgets, or different hardware specifications, determining their…
Contrastive representation learning has gained much attention due to its superior performance in learning representations from both image and sequential data. However, the learned representations could potentially lead to performance…
Robust reinforcement learning is essential for deploying reinforcement learning algorithms in real-world scenarios where environmental uncertainty predominates. Traditional robust reinforcement learning often depends on rectangularity…
Safety is an essential requirement for reinforcement learning systems. The newly emerging framework of robust constrained Markov decision processes allows learning policies that satisfy long-term constraints while providing guarantees under…
We study the problem of safe offline reinforcement learning (RL), the goal is to learn a policy that maximizes long-term reward while satisfying safety constraints given only offline data, without further interaction with the environment.…
Robust causal discovery from observational data under imperfect prior knowledge remains a significant and largely unresolved challenge. Existing methods typically presuppose perfect priors or can only handle specific, pre-identified error…
In the past years, augmented Lagrangian methods have been successfully applied to several classes of non-convex optimization problems, inspiring new developments in both theory and practice. In this paper we bring most of these recent…
Although federated learning has achieved many breakthroughs recently, the heterogeneous nature of the learning environment greatly limits its performance and hinders its real-world applications. The heterogeneous data, time-varying wireless…
Optimization problems are ubiquitous in our societies and are present in almost every segment of the economy. Most of these optimization problems are NP-hard and computationally demanding, often requiring approximate solutions for…
Reinforcement Learning (RL) serves as a versatile framework for sequential decision-making, finding applications across diverse domains such as robotics, autonomous driving, recommendation systems, supply chain optimization, biology,…
Compared with traditional deep learning techniques, continual learning enables deep neural networks to learn continually and adaptively. Deep neural networks have to learn new tasks and overcome forgetting the knowledge obtained from the…
Modern learning systems increasingly rely on amortized learning - the idea of reusing computation or inductive biases shared across tasks to enable rapid generalization to novel problems. This principle spans a range of approaches,…
The desire to use reinforcement learning in safety-critical settings has inspired a recent interest in formal methods for learning algorithms. Existing formal methods for learning and optimization primarily consider the problem of…
Learning latent representations from complex data is central to modern machine learning, spanning temporal, multimodal, and partially observed systems. In such settings, representations are better understood as latent states capturing…
Reinforcement learning has become a powerful paradigm for improving the capability of intelligent systems, but its practical deployment faces two central challenges. First, reinforcement learning must scale efficiently in distributed…
A novel federated learning training framework for heterogeneous environments is presented, taking into account the diverse network speeds of clients in realistic settings. This framework integrates asynchronous learning algorithms and…
A self-learning adaptive system (SLAS) uses machine learning to enable and enhance its adaptability. Such systems are expected to perform well in dynamic situations. For learning high-performance adaptation policy, some assumptions must be…