相关论文: Reusable Test Suites for Reinforcement Learning

Reactive synthesis algorithms allow automatic construction of policies to control an environment modeled as a Markov Decision Process (MDP) that are optimal with respect to high-level temporal logic specifications. However, they assume that…

Robust policies enable reinforcement learning agents to effectively adapt to and operate in unpredictable, dynamic, and ever-changing real-world environments. Factored representations, which break down complex state and action spaces into…

The field of reinforcement learning offers a large variety of concepts and methods to tackle sequential decision-making problems. This variety has become so large that choosing an algorithm for a task at hand can be challenging. In this…

We study the problem of training a principal in a multi-agent general-sum game using reinforcement learning (RL). Learning a robust principal policy requires anticipating the worst possible strategic responses of other agents, which is…

This paper describes a purely data-driven solution to a class of sequential decision-making problems with a large number of concurrent online decisions, with applications to computing systems and operations research. We assume that while…

Large Language Model (LLM) agents can increasingly automate complex reasoning through Test-Time Scaling (TTS), iterative refinement guided by reward signals. However, many real-world tasks involve multi-stage pipeline whose final outcomes…

We address the problem of deploying a reinforcement learning (RL) agent on a physical system such as a datacenter cooling unit or robot, where critical constraints must never be violated. We show how to exploit the typically smooth dynamics…

Multi-Agent Reinforcement Learning (MARL) algorithms are widely adopted in tackling complex tasks that require collaboration and competition among agents in dynamic Multi-Agent Systems (MAS). However, learning such tasks from scratch is…

Multi-agent systems have evolved into practical LLM-driven collaborators for many applications, gaining robustness from diversity and cross-checking. However, multi-agent RL (MARL) training is resource-intensive and unstable: co-adapting…

Autonomous UAV navigation using reinforcement learning (RL) is vulnerable to adversarial attacks that manipulate sensor inputs, potentially leading to unsafe behavior and mission failure. Although robust RL methods provide partial…

Reinforcement learning (RL) finetuning is crucial to aligning large language models (LLMs), but the process is notoriously unstable and exhibits high variance across model checkpoints. In practice, selecting the best checkpoint is…

In the vast landscape of internet information, recommender systems (RecSys) have become essential for guiding users through a sea of choices aligned with their preferences. These systems have applications in diverse domains, such as news…

Reinforcement learning (RL) paradigms have demonstrated strong performance on reasoning-intensive tasks such as code generation. However, limited trajectory diversity often leads to diminishing returns, which constrains the achievable…

In many Deep Reinforcement Learning (RL) problems, decisions in a trained policy vary in significance for the expected safety and performance of the policy. Since RL policies are very complex, testing efforts should concentrate on states in…

In the real world, agents often have to operate in situations with incomplete information, limited sensing capabilities, and inherently stochastic environments, making individual observations incomplete and unreliable. Moreover, in many…

Peer selection, the evaluation and selection of agents by their peers, is an important problem in the field of computational social choice; with applications to grading in massively online courses (MOOCs) and academic peer review. Current…

Reinforcement learning often uses neural networks to solve complex control tasks. However, neural networks are sensitive to input perturbations, which makes their deployment in safety-critical environments challenging. This work lifts…

Reinforcement learning (RL) has gained increasing attraction in the academia and tech industry with launches to a variety of impactful applications and products. Although research is being actively conducted on many fronts (e.g., offline…

Mutation testing is a standard technique to evaluate the quality of a test suite. Due to its computationally intensive nature, many approaches have been proposed to make this technique feasible in real case scenarios. Among these…

Static feature exclusion strategies often fail to prevent bias when hidden dependencies influence the model predictions. To address this issue, we explore a reinforcement learning (RL) framework that integrates bias mitigation and automated…