English
Related papers

Related papers: Core Safety Values for Provably Corrigible Agents

200 papers

Machine learning has made remarkable advancements, but confidently utilising learning-enabled components in safety-critical domains still poses challenges. Among the challenges, it is known that a rigorous, yet practical, way of achieving…

Machine Learning · Computer Science 2024-09-21 Saddek Bensalem , Chih-Hong Cheng , Wei Huang , Xiaowei Huang , Changshun Wu , Xingyu Zhao

When a game involves many agents or when communication between agents is not possible, it is useful to resort to distributed learning where each agent acts in complete autonomy without any information on the other agents' situations.…

Optimization and Control · Mathematics 2025-09-24 Jérôme Taupin , Xavier Leturc , Christophe J. Le Martret

Real-life agents seldom have unlimited reasoning power. In this paper, we propose and study a new formal notion of computationally bounded strategic ability in multi-agent systems. The notion characterizes the ability of a set of agents to…

Multiagent Systems · Computer Science 2023-10-27 Catalin Dima , Wojciech Jamroga

Ensuring robust decision-making in multi-agent systems is challenging when agents have distinct, possibly conflicting objectives and lack full knowledge of each other's strategies. This is apparent in safety-critical applications such as…

Systems and Control · Electrical Eng. & Systems 2025-10-20 Francesco Bianchin , Robert Lefringhausen , Elisa Gaetan , Samuel Tesfazgi , Sandra Hirche

We present five results in the theory of structural governance for cognitive workflow systems. Three are mechanized in Coq 8.19 using the Interaction Trees library with parameterized coinduction; two are proved on paper with explicit…

Artificial Intelligence · Computer Science 2026-05-27 Alan L. McCann

We investigate methods to provide safety assurances for autonomous agents that incorporate predictions of other, uncontrolled agents' behavior into their own trajectory planning. Given a learning-based forecasting model that predicts…

Systems and Control · Electrical Eng. & Systems 2023-12-14 Anish Muthali , Haotian Shen , Sampada Deglurkar , Michael H. Lim , Rebecca Roelofs , Aleksandra Faust , Claire Tomlin

The deployment of autonomous robots in safety-critical applications requires safety guarantees. Provably safe reinforcement learning is an active field of research that aims to provide such guarantees using safeguards. These safeguards…

Machine Learning · Computer Science 2026-05-08 Tim Walter , Hannah Markgraf , Jonathan Külz , Matthias Althoff

This paper proposes a novel decision-making framework for autonomous vehicles (AVs), called predictor-corrector potential game (PCPG), composed of a Predictor and a Corrector. To enable human-like reasoning and characterize agent…

Systems and Control · Electrical Eng. & Systems 2023-11-13 Mushuang Liu , H. Eric Tseng , Dimitar Filev , Anouck Girard , Ilya Kolmanovsky

Model checking of strategic abilities is a notoriously hard problem, even more so in the realistic case of agents with imperfect information, acting in a stochastic environment. Assume-guarantee reasoning can be of great help here,…

Multiagent Systems · Computer Science 2025-11-17 Wojciech Jamroga , Damian Kurpiewski , Łukasz Mikulski

Safety assurance is a critical yet challenging aspect when developing self-driving technologies. Hamilton-Jacobi backward-reachability analysis is a formal verification tool for verifying the safety of dynamic systems in the presence of…

Robotics · Computer Science 2021-06-08 Ran Tian , Anjian Li , Masayoshi Tomizuka , Liting Sun

Undoing computations of a concurrent system is beneficial in many situations, e.g., in reversible debugging of multi-threaded programs and in recovery from errors due to optimistic execution in parallel discrete event simulation. A number…

Logic in Computer Science · Computer Science 2024-02-13 Ivan Lanese , Iain Phillips , Irek Ulidowski

Most learning algorithms with formal regret guarantees essentially rely on trying all possible behaviors, which is problematic when some errors cannot be recovered from. Instead, we allow the learning agent to ask for help from a mentor and…

Machine Learning · Computer Science 2025-09-17 Benjamin Plaut , Juan Liévano-Karim , Hanlin Zhu , Stuart Russell

In this paper a distribution-free methodology is presented for providing robustness guarantees for Nash equilibria (NE) of multi-agent games. Leveraging recent a posteriori developments of the so called scenario approach (Campi et al.,…

Optimization and Control · Mathematics 2020-03-26 George Pantazis , Filiberto Fele , Kostas Margellos

Safety is the priority concern when applying reinforcement learning (RL) algorithms to real-world control problems. While policy iteration provides a fundamental algorithm for standard RL, an analogous theoretical algorithm for safe RL…

Machine Learning · Computer Science 2025-03-14 Yujie Yang , Zhilong Zheng , Shengbo Eben Li , Wei Xu , Jingjing Liu , Xianyuan Zhan , Ya-Qin Zhang

As AI systems grow more capable and autonomous, ensuring their safety and reliability requires not only model-level alignment but also strategic oversight of the humans and institutions involved in their development and deployment. Existing…

Artificial Intelligence · Computer Science 2026-02-10 Cheol Woo Kim , Davin Choo , Tzeh Yuan Neoh , Milind Tambe

We develop a data-driven approach to the computation of a-posteriori feasibility certificates to the solution sets of variational inequalities affected by uncertainty. Specifically, we focus on instances of variational inequalities with a…

Optimization and Control · Mathematics 2022-02-17 Filippo Fabiani , Kostas Margellos , Paul J. Goulart

To provide safety guarantees for learning-based control systems, recent work has developed formal verification methods to apply after training ends. However, if the trained policy does not meet the specifications, or there is conservatism…

Systems and Control · Electrical Eng. & Systems 2025-04-24 Puja Chaudhury , Alexander Estornell , Michael Everett

We present a formal proof in Lean of probably approximately correct (PAC) learnability of the concept class of decision stumps. This classic result in machine learning theory derives a bound on error probabilities for a simple type of…

Machine Learning · Computer Science 2021-01-11 Joseph Tassarotti , Koundinya Vajjha , Anindya Banerjee , Jean-Baptiste Tristan

Auctions in which agents' payoffs are random variables have received increased attention in recent years. In particular, recent work in algorithmic mechanism design has produced mechanisms employing internal randomization, partly in…

Computer Science and Game Theory · Computer Science 2012-06-15 Shaddin Dughmi , Yuval Peres

Multi-hop QA benchmarks frequently reward Large Language Models (LLMs) for spurious correctness, masking ungrounded or flawed reasoning steps. To shift toward rigorous reasoning, we propose SAFE, a dynamic benchmarking framework that…

Computation and Language · Computer Science 2026-04-03 Daeyong Kwon , Soyoung Yoon , Seung-won Hwang