← authors · overview

• Policy Poisoning in Batch Reinforcement Learning and Control
  2019 · 43 citations
• Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning
  2020 · 37 citations
• Adaptive Reward-Poisoning Attacks against Reinforcement Learning
  2020 · 34 citations
• Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments
  2021 · 16 citations
• Robust Policy Gradient against Strong Data Corruption
  2021 · 10 citations
• Policy Teaching in Reinforcement Learning via Environment Poisoning Attacks
  2020 · 8 citations
• Provable Defense against Backdoor Policies in Reinforcement Learning
  2022 · 7 citations
• Using Machine Teaching to Investigate Human Assumptions when Teaching Reinforcement Learners
  2020 · 6 citations
• Byzantine-Robust Online and Offline Distributed Reinforcement Learning
  2022 · 2 citations
• The Sample Complexity of Teaching-by-Reinforcement on Q-Learning