← authors · overview

• Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
  2023 · 93 citations
• Active Exploration for Inverse Reinforcement Learning
  2022 · 6 citations
• Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning
  2023 · 6 citations
• Learning Safety Constraints from Demonstrations with Unknown Rewards
  2023 · 4 citations
• Humans are not Boltzmann Distributions: Challenges and Opportunities for Modelling Human Feedback and Interaction in Reinforcement Learning
  2022 · 3 citations
• Detecting Spiky Corruption in Markov Decision Processes
  2019 · 1 citations
• Challenges for Using Impact Regularizers to Avoid Negative Side Effects
  2021 · 1 citations
• MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking
  2025
• Information Directed Reward Learning for Reinforcement Learning
  2021
• Mapping out the Space of Human Feedback for Reinforcement Learning: A Conceptual Framework
  2024
• ViSTa Dataset: Do vision-language models understand sequential tasks?
  2024