Related papers: Towards Runtime Adaptation of Actor Systems

This paper proposes a highly robust autonomous agent framework based on the ReAct paradigm, designed to solve complex tasks through adaptive decision making and multi-agent collaboration. Unlike traditional frameworks that rely on fixed…

Reinforcement learning in multi-agent scenarios is important for real-world applications but presents challenges beyond those seen in single-agent settings. We present an actor-critic algorithm that trains decentralized policies in…

Stream processing applications are deployed as continuous queries that run from the time of their submission until their cancellation. This deployment mode limits developers who need their applications to perform runtime adaptation, such as…

Actor-Critic based approaches were among the first to address reinforcement learning in a general setting. Recently, these algorithms have gained renewed interest due to their generality, good convergence properties, and possible biological…

Adapting models to dynamic, real-world environments characterized by shifting data distributions and unseen test scenarios is a critical challenge in deep learning. In this paper, we consider a realistic and challenging Test-Time Adaptation…

In this paper, a continuous-time adaptive actor-critic reinforcement learning (RL) controller is developed for drift-free nonlinear systems. Practical examples of such systems are image-based visual servoing (IBVS) and wheeled mobile robots…

LLM agents are rapidly evolving from coding assistants into autonomous software engineering systems. However, existing evaluation methodologies remain largely centered on static, isolated, and short-horizon benchmarks that fail to capture…

Static analysis tools come in many forms andconfigurations, allowing them to handle various tasks in a (secure) development process: code style linting, bug/vulnerability detection, verification, etc., and adapt to the specific requirements…

Test-Time Learning (TTL) enables language agents to iteratively refine their performance through repeated interactions with the environment at inference time. At the core of TTL is an adaptation policy that updates the actor policy based on…

Pre-trained Vision-Language-Action (VLA) models represent a major leap towards general-purpose robots, yet efficiently adapting them to novel, specific tasks in-situ remains a significant hurdle. While reinforcement learning (RL) is a…

In this paper, we present a distributed estimation setup where local agents estimate their states from relative measurements received from their neighbours. In the case of heterogeneous multi-agent systems, where only relative measurements…

Robot learning methods have recently made great strides, but generalization and robustness challenges still hinder their widespread deployment. Failing to detect and address potential failures renders state-of-the-art learning systems not…

Continual Test-time adaptation (CTTA) continuously adapts the deployed model on every incoming batch of data. While achieving optimal accuracy, existing CTTA approaches present poor real-world applicability on resource-constrained edge…

Modern software applications demand efficient and reliable testing methodologies to ensure robust user interface functionality. This paper introduces an autonomous reinforcement learning (RL) agent integrated within a Behavior-Driven…

Synchronization among autonomous agents via local interactions is one of the benchmark problems in multi-agent control. Whereas synchronization algorithms for identical agents have been thoroughly studied, synchronization of heterogeneous…

Established recurrent neural networks are well-suited to solve a wide variety of prediction tasks involving discrete sequences. However, they do not perform as well in the task of dynamical system identification, when dealing with…

In this paper, an adaptive observer is proposed for multi-input multi-output (MIMO) discrete-time linear time-invariant (LTI) systems. Unlike existing MIMO adaptive observer designs, the proposed approach is applicable to LTI systems in…

Test-Time Adaptation (TTA) enables pre-trained models to adjust to distribution shift by learning from unlabeled test-time streams. However, existing methods typically treat these streams as independent samples, overlooking the supervisory…

Achieving optimal steady-state performance in real-time is an increasingly necessary requirement of many critical infrastructure systems. In pursuit of this goal, this paper builds a systematic design framework of feedback controllers for…

Temporal action localization aims to identify the boundaries and categories of actions in videos, such as scoring a goal in a football match. Single-frame supervision has emerged as a labor-efficient way to train action localizers as it…