Cover Image

When Can You Poison Rewards? A Tight Characterization of Reward Poisoning in Linear MDPs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Escamilla, Jose Efraim Aguilar, Hong, Haoyang, Li, Jiawei, Zhao, Haoyu, Zhang, Xuezhou, Hong, Sanghyun, Wang, Huazheng
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Hard Work Does Not Always Pay Off: Poisoning Attacks on Neural Architecture Search
by: Coalson, Zachary, et al.
Published: (2024)

Reinforcement Learning for Infinite-Horizon Average-Reward Linear MDPs via Approximation by Discounted-Reward MDPs
by: Hong, Kihyuk, et al.
Published: (2024)

Can In-Context Reinforcement Learning Recover From Reward Poisoning Attacks?
by: Sasnauskas, Paulius, et al.
Published: (2025)

A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs
by: Hong, Kihyuk, et al.
Published: (2025)

Efficient Reinforcement Learning in Probabilistic Reward Machines
by: Lin, Xiaofeng, et al.
Published: (2024)

Preference Poisoning Attacks on Reward Model Learning
by: Wu, Junlin, et al.
Published: (2024)

Learning Infinite-Horizon Average-Reward Linear Mixture MDPs of Bounded Span
by: Chae, Woojin, et al.
Published: (2024)

Certified Robustness to Clean-Label Poisoning Using Diffusion Denoising
by: Hong, Sanghyun, et al.
Published: (2024)

BadReward: Clean-Label Poisoning of Reward Models in Text-to-Image RLHF
by: Duan, Kaiwen, et al.
Published: (2025)

Robust Thompson Sampling Algorithms Against Reward Poisoning Attacks
by: Xu, Yinglun, et al.
Published: (2024)

RA-PbRL: Provably Efficient Risk-Aware Preference-Based Reinforcement Learning
by: Zhao, Yujie, et al.
Published: (2024)

Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPs
by: Zhang, Junkai, et al.
Published: (2023)

Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
by: Wen, Yuxin, et al.
Published: (2024)

Towards Poisoning Fair Representations
by: Liu, Tianci, et al.
Published: (2023)

What Can You Do When You Have Zero Rewards During RL?
by: Prakash, Jatin, et al.
Published: (2025)

Universal Black-Box Reward Poisoning Attack against Offline Reinforcement Learning
by: Xu, Yinglun, et al.
Published: (2024)

When Distance Distracts: Representation Distance Bias in BT-Loss for Reward Models
by: Xie, Tong, et al.
Published: (2025)

Beyond Static Bias: Adaptive Multi-Fidelity Bandits with Improving Proxies
by: Lu, Muyun, et al.
Published: (2026)

Have You Poisoned My Data? Defending Neural Networks against Data Poisoning
by: De Gaspari, Fabio, et al.
Published: (2024)

On Robustness of Linear Classifiers to Targeted Data Poisoning
by: Gupta, Nakshatra, et al.
Published: (2025)

When Do "More Contexts" Help with Sarcasm Recognition?
by: Nimase, Ojas, et al.
Published: (2024)

Near-Optimal Sample Complexity Bounds for Constrained Average-Reward MDPs
by: Wei, Yukuan, et al.
Published: (2025)

Beyond Scalar Rewards: An Axiomatic Framework for Lexicographic MDPs
by: Shakerinava, Mehran, et al.
Published: (2025)

Achieving Tractable Minimax Optimal Regret in Average Reward MDPs
by: Boone, Victor, et al.
Published: (2024)

A Linear Approach to Data Poisoning
by: Flynn, Donald, et al.
Published: (2025)

Design-Based Bandits Under Network Interference: Trade-Off Between Regret and Statistical Inference
by: Wang, Zichen, et al.
Published: (2025)

Regret Analysis of Unichain Average Reward Constrained MDPs with General Parameterization
by: Satheesh, Anirudh, et al.
Published: (2026)

Two-Timescale Critic-Actor for Average Reward MDPs with Function Approximation
by: Panda, Prashansa, et al.
Published: (2024)

Solving Non-Rectangular Reward-Robust MDPs via Frequency Regularization
by: Gadot, Uri, et al.
Published: (2023)

Why Policy Gradient Algorithms Work for Undiscounted Total-Reward MDPs
by: Lee, Jongmin, et al.
Published: (2025)

Confundo: Learning to Generate Robust Poison for Practical RAG Systems
by: Hu, Haoyang, et al.
Published: (2026)

Sample Complexity Characterization for Linear Contextual MDPs
by: Deng, Junze, et al.
Published: (2024)

A Primal-Dual Algorithm for Offline Constrained Reinforcement Learning with Linear MDPs
by: Hong, Kihyuk, et al.
Published: (2024)

Regret Analysis of Average-Reward Unichain MDPs via an Actor-Critic Approach
by: Ganesh, Swetha, et al.
Published: (2025)

Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples
by: Souly, Alexandra, et al.
Published: (2025)

FuncPoison: Poisoning Function Library to Hijack Multi-agent Autonomous Driving Systems
by: Long, Yuzhen, et al.
Published: (2025)

Span-Based Optimal Sample Complexity for Average Reward MDPs
by: Zurek, Matthew, et al.
Published: (2023)

Focal Reward: Balanced Reinforcement Learning under Rubric-Based Rewards
by: Huang, Yu, et al.
Published: (2026)

Poisoned-MRAG: Knowledge Poisoning Attacks to Multimodal Retrieval Augmented Generation
by: Liu, Yinuo, et al.
Published: (2025)

Associative Poisoning to Generative Machine Learning
by: Mohus, Mathias Lundteigen, et al.
Published: (2025)