Data to 7 Oct 2026

Deceptive Reinforcement Learning Under Adversarial Manipulations on Cost Signals

arXiv 1906.10571 ↗First posted 24 Jun 2019cs.LG cs.AI math.OCcited by 50

Not on the map. Why?

Abstract (arXiv)

This paper studies reinforcement learning (RL) under malicious falsification on cost signals and introduces a quantitative framework of attack models to understand the vulnerabilities of RL. Focusing on Q-learning, we show that Q-learning algorithms converge under stealthy attacks and bounded falsifications on cost signals. We characterize the relation between the falsified cost and the Q-factors as well as the policy learned by the learning agent which provides fundamental limits for feasible offensive and defensive moves. We propose a robust region in terms of the cost within which the adversary can never achieve the targeted policy. We provide conditions on the falsified cost which can mislead the agent to learn an adversary's favored policy. A numerical case study of water reservoir control is provided to show the potential hazards of RL in learning-based control systems and corroborate the results.

Key facts. Cited by 50 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 13; 2022: 12; 2023: 7; 2024: 9; 2025: 4; 2026: 4.

50 papers.

Sort:

By area:

2021Robust Reinforcement Learning on State Observations with Learned Optimal Adversarycited by 133
2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoningcited by 93
2021Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RLcited by 54
2022Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learningcited by 42
2022Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizabilitycited by 32
2021Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learningcited by 29
2021Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environmentscited by 26
2022COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attackscited by 25
2021Defense Against Reward Poisoning Attacks in Reinforcement Learningcited by 20
2022Reward Poisoning Attacks on Offline Multi-Agent Reinforcement Learningcited by 19
2023Automated Cyber Defence: A Reviewcited by 19
2021Reinforcement Learning for Feedback-Enabled Cyber Resiliencecited by 18

38 more

2023Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influencecited by 16
2021Deceptive Reinforcement Learning for Privacy-Preserving Planningcited by 14
2021Multi-Task Federated Reinforcement Learning with Adversariescited by 13
2022Admissible Policy Teaching through Reward Designcited by 12
2022Illusory Attacks: Information-Theoretic Detectability Matters in Adversarial Attackscited by 12
2023Efficient Adversarial Attacks on Online Multi-agent Reinforcement Learningcited by 9
2021Game Redesign in No-regret Game Playingcited by 8
2024Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policiescited by 8
2022New Challenges in Reinforcement Learning: A Survey of Security and Privacycited by 7
2022Sampling Attacks on Meta Reinforcement Learning: A Minimax Formulation and Complexity Analysiscited by 5
2022Reward Delay Attacks on Deep Reinforcement Learningcited by 5
2024Corruption-Robust Offline Two-Player Zero-Sum Markov Gamescited by 4
2021Improving Robustness of Deep Reinforcement Learning Agents: Environment Attack based on the Critic Networkcited by 3
2021Reward-Free Attacks in Multi-Agent Reinforcement Learningcited by 3
2021Efficient Action Poisoning Attacks on Linear Contextual Banditscited by 3
2023Efficient Action Robust Reinforcement Learning with Probabilistic Policy Execution Uncertaintycited by 2
2023Minimally Modifying a Markov Game to Achieve Any Nash Equilibrium and Valuecited by 2
2024Stealthy Adversarial Attacks on Stochastic Multi-Armed Banditscited by 2
2024Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbationscited by 2
2022Reinforcement Learning for Linear Quadratic Control is Vulnerable Under Cost Manipulationcited by 1
2022Security of Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 1
2023Data Poisoning to Fake a Nash Equilibrium in Markov Gamescited by 1
2023Optimal Cost Constrained Adversarial Attacks For Multiple Agent Systemscited by 1
2024Deceptive Path Planning via Reinforcement Learning with Graph Neural Networkscited by 1
2024Strategizing against Q-learners: A Control-theoretical Approachcited by 1
2024Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learningcited by 1
2024AI Ethics by Design: Implementing Customizable Guardrails for Responsible AI Developmentcited by 1
2020Learn to Exceed: Stereo Inverse Reinforcement Learning with Concurrent Policy Optimizationcited by 0
2021A study of first-passage time minimization via Q-learning in heated gridworldscited by 0
2024Policy Iteration for Two-Player General-Sum Stochastic Stackelberg Gamescited by 0
2025Optimally Installing Strict Equilibriacited by 0
2025Pruning Cannot Hurt Robustness: Certified Trade-offs in Reinforcement Learningcited by 0
2025Provably Invincible Adversarial Attacks on Reinforcement Learning Systems: A Rate-Distortion Information-Theoretic Approachcited by 0
2025Diffusion Guided Adversarial State Perturbations in Reinforcement Learningcited by 0
2026Cyber Deception for Mission Surveillance via Hypergame-Theoretic Deep Reinforcement Learningcited by 0
2026Efficient Preference Poisoning Attack on Offline RLHFcited by 0
2026Repeated Deceptive Path Planning against Learnable Observercited by 0
2026Safe-RULE: Safe Reinforcement UnLEarningcited by 0