Can In-Context Reinforcement Learning Recover From Reward Poisoning Attacks?

Documenti analoghi

• Independent Learning in Performative Markov Potential Games
  di: Sahitaj, Rilind, et al.
  Pubblicazione: (2025)
• Distributionally Robust Reinforcement Learning with Human Feedback
  di: Mandal, Debmalya, et al.
  Pubblicazione: (2025)
• Universal Black-Box Reward Poisoning Attack against Offline Reinforcement Learning
  di: Xu, Yinglun, et al.
  Pubblicazione: (2024)
• Local Environment Poisoning Attacks on Federated Reinforcement Learning
  di: Ma, Evelyn, et al.
  Pubblicazione: (2023)
• SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents
  di: Rathbun, Ethan, et al.
  Pubblicazione: (2024)