Investigating the Treacherous Turn in Deep Reinforcement Learning

Documenti analoghi

• Backdoors in DRL: Four Environments Focusing on In-distribution Triggers
  di: Ashcraft, Chace, et al.
  Pubblicazione: (2025)
• Causality-Driven Audits of Model Robustness
  di: Drenkow, Nathan, et al.
  Pubblicazione: (2024)
• Trusted Weights, Treacherous Optimizations? Optimization-Triggered Backdoor Attacks on LLMs
  di: Wang, Yifei, et al.
  Pubblicazione: (2026)
• POLO: Preference-Guided Multi-Turn Reinforcement Learning for Lead Optimization
  di: Wang, Ziqing, et al.
  Pubblicazione: (2025)
• Deep Dive into Model-free Reinforcement Learning for Biological and Robotic Systems: Theory and Practice
  di: Jiao, Yusheng, et al.
  Pubblicazione: (2024)