English
Related papers

Related papers: Model-Free Opponent Shaping

200 papers

We introduce a Noise-based prior Learning (NoL) approach for training neural networks that are intrinsically robust to adversarial attacks. We find that the implicit generative modeling of random noise with the same loss function used…

Machine Learning · Computer Science 2019-06-04 Priyadarshini Panda , Kaushik Roy

Optimal stopping is a fundamental problem in optimization with applications in risk management, finance, robotics, and machine learning. We extend the standard framework to a multi-agent setting, named multi-agent optimal stopping (MAOS),…

Optimization and Control · Mathematics 2025-06-10 Lorenzo Magnino , Yuchen Zhu , Mathieu Laurière

Recently, model-based agents have achieved better performance than model-free ones using the same computational budget and training time in single-agent environments. However, due to the complexity of multi-agent systems, it is tough to…

Multiagent Systems · Computer Science 2022-12-08 Zhiwei Xu , Dapeng Li , Bin Zhang , Yuan Zhan , Yunpeng Bai , Guoliang Fan

The vulnerability of deep neural networks to adversarial examples has motivated an increasing number of defense strategies for promoting model robustness. However, the progress is usually hampered by insufficient robustness evaluations. As…

Machine Learning · Computer Science 2021-10-19 Xiao Yang , Yinpeng Dong , Wenzhao Xiang , Tianyu Pang , Hang Su , Jun Zhu

Reinforcement Learning has been able to solve many complicated robotics tasks without any need for feature engineering in an end-to-end fashion. However, learning the optimal policy directly from the sensory inputs, i.e the observations,…

DL-based automatic modulation classification (AMC) models are highly susceptible to adversarial attacks, where even minimal input perturbations can cause severe misclassifications. While adversarially training an AMC model based on an…

Machine Learning · Computer Science 2025-01-06 Amirmohammad Bamdad , Ali Owfi , Fatemeh Afghah

A growing body of computational studies shows that simple machine learning agents converge to cooperative behaviors in social dilemmas, such as collusive price-setting in oligopoly markets, raising questions about what drives this outcome.…

Computer Science and Game Theory · Computer Science 2025-12-23 Quentin Bertrand , Juan Duque , Emilio Calvano , Gauthier Gidel

Deep learning models, even the-state-of-the-art ones, are highly vulnerable to adversarial examples. Adversarial training is one of the most efficient methods to improve the model's robustness. The key factor for the success of adversarial…

Machine Learning · Computer Science 2023-06-05 Anh Bui , Trung Le , He Zhao , Quan Tran , Paul Montague , Dinh Phung

Recent work has revealed a new class of "zero-determinant" (ZD) strategies for iterated, two-player games. ZD strategies allow a player to unilaterally enforce a linear relationship between her score and her opponent's score, and thus…

Populations and Evolution · Quantitative Biology 2013-12-30 Alexander J. Stewart , Joshua B. Plotkin

In meta-reinforcement learning, an agent is trained in multiple different environments and attempts to learn a meta-policy that can efficiently adapt to a new environment. This paper presents RAMP, a Reinforcement learning Agent using Model…

Machine Learning · Computer Science 2022-10-28 Gabriel Hartmann , Amos Azaria

Multi-agent systems exhibit complex behaviors that emanate from the interactions of multiple agents in a shared environment. In this work, we are interested in controlling one agent in a multi-agent system and successfully learn to interact…

Machine Learning · Computer Science 2020-01-30 Georgios Papoudakis , Stefano V. Albrecht

Adversary emulation is an offensive exercise that provides a comprehensive assessment of a system's resilience against cyber attacks. However, adversary emulation is typically a manual process, making it costly and hard to deploy in…

Machine Learning · Computer Science 2020-11-10 Arnab Bhattacharya , Thiagarajan Ramachandran , Sandeep Banik , Chase P. Dowling , Shaunak D. Bopardikar

Reward-based alignment methods for large language models (LLMs) face two key limitations: vulnerability to reward hacking, where models exploit flaws in the reward signal; and reliance on brittle, labor-intensive prompt engineering when…

Computation and Language · Computer Science 2025-05-20 Zae Myung Kim , Chanwoo Park , Vipul Raheja , Suin Kim , Dongyeop Kang

We consider online reinforcement learning in Mean-Field Games (MFGs). Unlike traditional approaches, we alleviate the need for a mean-field oracle by developing an algorithm that approximates the Mean-Field Equilibrium (MFE) using the…

Machine Learning · Computer Science 2023-04-12 Muhammad Aneeq uz Zaman , Alec Koppel , Sujay Bhatt , Tamer Başar

A self-learning adaptive system (SLAS) uses machine learning to enable and enhance its adaptability. Such systems are expected to perform well in dynamic situations. For learning high-performance adaptation policy, some assumptions must be…

Software Engineering · Computer Science 2021-05-12 Mingyue Zhang , Jialong Li , Haiyan Zhao , Kenji Tei , Shinichi Honiden , Zhi Jin

Sample efficiency remains a key challenge in multi-agent reinforcement learning (MARL). A promising approach is to learn a meaningful latent representation space through auxiliary learning objectives alongside the MARL objective to aid in…

Multiagent Systems · Computer Science 2024-06-06 Dom Huh , Prasant Mohapatra

Path planning plays an essential role in many areas of robotics. Various planning techniques have been presented, either focusing on learning a specific task from demonstrations or retrieving trajectories by optimizing for hand-crafted cost…

Robotics · Computer Science 2018-09-26 Salvatore Virga , Christian Rupprecht , Nassir Navab , Christoph Hennersperger

Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can…

Machine Learning · Computer Science 2025-10-08 Zizhao Wang , Dingcheng Li , Vaishakh Keshava , Phillip Wallis , Ananth Balashankar , Peter Stone , Lukas Rutishauser

The increasing adaptation of vision models across domains, such as satellite imagery and medical scans, has raised an emerging privacy risk: models may inadvertently retain and leak sensitive source-domain specific information in the target…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Arnav Devalapally , Poornima Jain , Kartik Srinivas , Vineeth N. Balasubramanian

Data-Free Meta-Learning (DFML) aims to extract knowledge from a collection of pre-trained models without requiring the original data, presenting practical benefits in contexts constrained by data privacy concerns. Current DFML methods…

Machine Learning · Computer Science 2024-12-10 Yongxian Wei , Zixuan Hu , Zhenyi Wang , Li Shen , Chun Yuan , Dacheng Tao