English
Related papers

Related papers: Path-Specific Objectives for Safer Agent Incentive…

200 papers

Modern recommendation systems rely on the wisdom of the crowd to learn the optimal course of action. This induces an inherent mis-alignment of incentives between the system's objective to learn (explore) and the individual users' objective…

Computer Science and Game Theory · Computer Science 2018-07-06 Gal Bahar , Rann Smorodinsky , Moshe Tennenholtz

In an unfamiliar setting, a model-based reinforcement learning agent can be limited by the accuracy of its world model. In this work, we present a novel, training-free approach to improving the performance of such agents separately from…

Machine Learning · Computer Science 2024-02-26 Martin Benfeghoul , Umais Zahid , Qinghai Guo , Zafeirios Fountas

Multi-agent reinforcement learning methods have shown remarkable potential in solving complex multi-agent problems but mostly lack theoretical guarantees. Recently, mean field control and mean field games have been established as a…

Machine Learning · Computer Science 2021-12-20 Kai Cui , Anam Tahir , Mark Sinzger , Heinz Koeppl

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…

Machine Learning · Computer Science 2024-08-20 Manuel Wendl , Lukas Koller , Tobias Ladner , Matthias Althoff

In this work, we investigate a steering problem in a mediator-augmented two-player normal-form game, where the mediator aims to guide players toward a specific action profile through information and incentive design. We first characterize…

Computer Science and Game Theory · Computer Science 2025-09-01 Asrin Efe Yorulmaz , Raj Kiriti Velicheti , Melih Bastopcu , Tamer Başar

While offline reinforcement learning provides reliable policies for real-world deployment, its inherent pessimism severely restricts an agent's ability to explore and collect novel data online. Drawing inspiration from safe reinforcement…

Machine Learning · Computer Science 2026-03-20 Amirhossein Roknilamouki , Arnob Ghosh , Eylem Ekici , Ness B. Shroff

Backdoor attacks on reinforcement learning implant a backdoor in a victim agent's policy. Once the victim observes the trigger signal, it will switch to the abnormal mode and fail its task. Most of the attacks assume the adversary can…

Multiagent Systems · Computer Science 2022-11-22 Shuo Chen , Yue Qiu , Jie Zhang

We consider the problem of incentivising desirable behaviours in multi-agent systems by way of taxation schemes. Our study employs the concurrent games model: in this model, each agent is primarily motivated to seek the satisfaction of a…

Computer Science and Game Theory · Computer Science 2023-07-12 David Hyland , Julian Gutierrez , Michael Wooldridge

Model-based Reinforcement Learning approaches have the promise of being sample efficient. Much of the progress in learning dynamics models in RL has been made by learning models via supervised learning. But traditional model-based…

Machine Learning · Computer Science 2019-06-12 Shagun Sodhani , Anirudh Goyal , Tristan Deleu , Yoshua Bengio , Sergey Levine , Jian Tang

Traditionally, reinforcement learning methods predict the next action based on the current state. However, in many situations, directly applying actions to control systems or robots is dangerous and may lead to unexpected behaviors because…

Robotics · Computer Science 2020-11-03 Nan Lin , Yuxuan Li , Yujun Zhu , Ruolin Wang , Xiayu Zhang , Jianmin Ji , Keke Tang , Xiaoping Chen , Xinming Zhang

Offline reinforcement learning enables learning from a fixed dataset, without further interactions with the environment. The lack of environmental interactions makes the policy training vulnerable to state-action pairs far from the training…

Machine Learning · Statistics 2022-10-11 Shentao Yang , Zhendong Wang , Huangjie Zheng , Yihao Feng , Mingyuan Zhou

How to detect and mitigate deceptive AI systems is an open problem for the field of safe and trustworthy AI. We analyse two algorithms for mitigating deception: The first is based on the path-specific objectives framework where paths in the…

Artificial Intelligence · Computer Science 2023-06-27 Ismail Sahbane , Francis Rhys Ward , C Henrik Åslund

I study whether and which expert incentives can be provided at what cost when the states of the world become non-contractible, but there is some noisy observation about the states that can be contracted upon. A principal hires an agent to…

Theoretical Economics · Economics 2025-11-12 Zizhe Xia

LLM agents emit actions, not just text, and once taken, those actions often cannot be undone. Yet today's agent-safety evaluations run greedy or a few sampled rollouts and report a single safe/unsafe rate -- blind to the long-tail…

Cryptography and Security · Computer Science 2026-05-05 Shuyi Lin , Anshuman Suri , Alina Oprea , Cheng Tan

We consider schemes for obtaining truthful reports on a common but hidden signal from large groups of rational, self-interested agents. One example are online feedback mechanisms, where users provide observations about the quality of a…

Computer Science and Game Theory · Computer Science 2014-01-16 Radu Jurca , Boi Faltings

Reinforcement learning is a powerful learning paradigm in which agents can learn to maximize sparse and delayed reward signals. Although RL has had many impressive successes in complex domains, learning can take hours, days, or even years…

Machine Learning · Computer Science 2020-11-04 Paniz Behboudian , Yash Satsangi , Matthew E. Taylor , Anna Harutyunyan , Michael Bowling

We develop a general problem setting for training and testing the ability of agents to gather information efficiently. Specifically, we present a collection of tasks in which success requires searching through a partially-observed…

Machine Learning · Computer Science 2016-12-09 Philip Bachman , Alessandro Sordoni , Adam Trischler

Reinforcement learning is a proven technique for an agent to learn a task. However, when learning a task using reinforcement learning, the agent cannot distinguish the characteristics of the environment from those of the task. This makes it…

Artificial Intelligence · Computer Science 2017-08-10 Pieter Van Molle , Tim Verbelen , Steven Bohez , Sam Leroux , Pieter Simoens , Bart Dhoedt

Through multi-agent competition and the sparse high-level objective of winning a race, we find that both agile flight (e.g., high-speed motion pushing the platform to its physical limits) and strategy (e.g., overtaking or blocking) emerge…

Robotics · Computer Science 2026-03-05 Vineet Pasumarti , Lorenzo Bianchi , Antonio Loquercio

The main challenge of multiagent reinforcement learning is the difficulty of learning useful policies in the presence of other simultaneously learning agents whose changing behaviors jointly affect the environment's transition and reward…

‹ Prev 1 8 9 10 Next ›