scientific article; zbMATH DE number 7626725

MaRDI QIDQ5053203zbMATH OpenFDO

Authors Amin Rakhsha, Goran Radanovic, Rati Devidze, Xiaojin Zhu, Adish Singla

Publication date 6 December 2022

Full work available at URL https://arxiv.org/abs/2011.10824, https://jmlr.csail.mit.edu/papers/v22/20-1329.html

zbMATH Keywords

environment poisoningpolicy teachingreinforcement learningsecurity threattraining-time adversarial attacks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites work

• A survey on transfer learning for multiagent reinforcement learning systems
• Adversarial machine learning
• Average reward reinforcement learning: foundations, algorithms, and empirical results
• Data poisoning attacks in contextual bandits
• Deceptive Reinforcement Learning Under Adversarial Manipulations on Cost Signals
• scientific article; zbMATH DE number 5957196 (Why is no real title available?)
• scientific article; zbMATH DE number 1350309 (Why is no real title available?)
• scientific article; zbMATH DE number 700091 (Why is no real title available?)
• scientific article; zbMATH DE number 7626725 (Why is no real title available?)
• Learning in structured MDPs with convex cost functions: improved regret bounds for inventory management
• Model-based average reward reinforcement learning
• Near-optimal regret bounds for reinforcement learning
• On the complexity of teaching
• Online Markov decision processes
• Reinforcement learning. An introduction
• Robust Control of Markov Decision Processes with Uncertain Transition Matrices
• Robust Dynamic Programming
• Stronger data poisoning attacks break data sanitization defenses

Cited in

(2)

• scientific article; zbMATH DE number 7626725 (Why is no real title available?)
• Learning key steps to attack deep reinforcement learning agents

This page was built for publication:

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5053203)