English
Related papers

Related papers: Deception in Optimal Control

200 papers

Learning to control an environment without hand-crafted rewards or expert data remains challenging and is at the frontier of reinforcement learning research. We present an unsupervised learning algorithm to train agents to achieve…

Machine Learning · Computer Science 2018-11-29 David Warde-Farley , Tom Van de Wiele , Tejas Kulkarni , Catalin Ionescu , Steven Hansen , Volodymyr Mnih

Can deception exist in differential games? We provide a case study for a Turret-Attacker differential game, where two Attackers seek to score points by reaching a target region while a Turret tries to minimize the score by aligning itself…

Computer Science and Game Theory · Computer Science 2024-05-14 Daigo Shishika , Alexander Von Moll , Dipankar Maity , Michael Dorothy

When deploying artificial agents in real-world environments where they interact with humans, it is crucial that their behavior is aligned with the values, social norms or other requirements of that environment. However, many environments…

Machine Learning · Computer Science 2023-05-05 Mattijs Baert , Pietro Mazzaglia , Sam Leroux , Pieter Simoens

The deferred acceptance algorithm is an elegant solution to the stable matching problem that guarantees optimality and truthfulness for one side of the market. Despite these desirable guarantees, it is susceptible to strategic misreporting…

Computer Science and Game Theory · Computer Science 2020-12-09 Hadi Hosseini , Fatima Umar , Rohit Vaish

An insider is defined as a team member who covertly deviates from the team's optimal collaborative control strategy in pursuit of a private objective, while maintaining an outward appearance of cooperation. Such insider threats can severely…

Optimization and Control · Mathematics 2025-12-04 Gehui Xu , Kaiwen Chen , Thomas Parisini , Andreas A. Malikopoulos

As increasingly capable agents are deployed, a central safety challenge is how to retain meaningful human control without modifying the underlying system. We study a minimal control interface in which an agent chooses whether to act…

Artificial Intelligence · Computer Science 2026-02-23 William Overman , Mohsen Bayati

The intent of control argumentation frameworks is to specifically model strategic scenarios from the perspective of an agent by extending the standard model of argumentation framework in a way that takes unquantified uncertainty regarding…

Artificial Intelligence · Computer Science 2022-10-24 Minal Suresh Patil

We exhibit optimal control strategies for a simple toy problem in which the underlying dynamics depend on a parameter that is initially unknown and must be learned. We consider a cost function posed over a finite time interval, in contrast…

Optimization and Control · Mathematics 2020-02-27 Charles L. Fefferman , Bernat Guillen Pegueroles , Clarence W. Rowley , Melanie Weber

Imitation is widely observed in populations of decision-making agents. Using our recent convergence results for asynchronous imitation dynamics on networks, we consider how such networks can be efficiently driven to a desired equilibrium…

Computer Science and Game Theory · Computer Science 2017-04-17 James Riehl , Pouria Ramazi , Ming Cao

Recent results in the ML community have revealed that learning algorithms used to compute the optimal strategy for the leader to commit to in a Stackelberg game, are susceptible to manipulation by the follower. Such a learning algorithm…

Computer Science and Game Theory · Computer Science 2022-09-12 Georgios Birmpas , Jiarui Gan , Alexandros Hollender , Francisco J. Marmolejo-Cossío , Ninad Rajgopal , Alexandros A. Voudouris

If we could define the set of all bad outcomes, we could hard-code an agent which avoids them; however, in sufficiently complex environments, this is infeasible. We do not know of any general-purpose approaches in the literature to avoiding…

Artificial Intelligence · Computer Science 2020-06-17 Michael K. Cohen , Marcus Hutter

Desensitization addresses safe optimal planning under parametric uncertainties by providing sensitivity function-based risk estimates. This paper expands upon the existing work on desensitization in optimal control to address safe planning…

Systems and Control · Electrical Eng. & Systems 2024-02-08 Vinodhini Comandur , Tulasi Ram Vechalapu , Venkata Ramana Makkapati , Panagiotis Tsiotras , Seth Hutchinson

Adversarial examples can be defined as inputs to a model which induce a mistake - where the model output is different than that of an oracle, perhaps in surprising or malicious ways. Original models of adversarial attacks are primarily…

Machine Learning · Computer Science 2018-11-06 Peter Henderson , Koustuv Sinha , Rosemary Nan Ke , Joelle Pineau

Biological systems often choose actions without an explicit reward signal, a phenomenon known as intrinsic motivation. The computational principles underlying this behavior remain poorly understood. In this study, we investigate an…

Artificial Intelligence · Computer Science 2023-01-05 Stas Tiomkin , Ilya Nemenman , Daniel Polani , Naftali Tishby

This work considers a novel information design problem and studies how the craft of payoff-relevant environmental signals solely can influence the behaviors of intelligent agents. The agents' strategic interactions are captured by a Markov…

Multiagent Systems · Computer Science 2021-06-15 Tao Zhang , Quanyan Zhu

We study a class of two-player competitive concurrent stochastic games on graphs with reachability objectives. Specifically, player 1 aims to reach a subset $F_1$ of game states, and player 2 aims to reach a subset $F_2$ of game states…

Systems and Control · Electrical Eng. & Systems 2023-03-24 Chongyang Shi , Shuo Han , Jie Fu

As the cornerstone of artificial intelligence, machine perception confronts a fundamental threat posed by adversarial illusions. These adversarial attacks manifest in two primary forms: deductive illusion, where specific stimuli are crafted…

Artificial Intelligence · Computer Science 2026-05-01 Ching-Chun Chang , Fan-Yun Chen , Shih-Hong Gu , Kai Gao , Hanrui Wang , Isao Echizen

We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As a victim, we consider RL agents whose objective is to find…

Machine Learning · Computer Science 2020-08-20 Amin Rakhsha , Goran Radanovic , Rati Devidze , Xiaojin Zhu , Adish Singla

We consider a counter-adversarial sequential decision-making problem where an agent computes its private belief (posterior distribution) of the current state of the world, by filtering private information. According to its private belief,…

Systems and Control · Electrical Eng. & Systems 2020-04-09 Inês Lourenço , Robert Mattila , Cristian R. Rojas , Bo Wahlberg

In this paper, we consider an unconstrained distributed optimization problem over a network of agents, in which some agents are adversarial. We solve the problem via gradient-based distributed optimization algorithm and characterize the…

Optimization and Control · Mathematics 2021-03-22 Iyanuoluwa Emiola , Laurent Njilla , Chinwendu Enyioha
‹ Prev 1 4 5 6 7 8 10 Next ›