Lauro Langosco
Publications by Year
Research Areas
Blockchain Technology Applications and Security, Reinforcement Learning in Robotics, Ethics and Social Impacts of AI, Neuroethics, Human Enhancement, Biomedical Innovations, Topic Modeling
Most-Cited Works
- → Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback(2023)89 cited
- → Harms from Increasingly Agentic Algorithmic Systems(2023)87 cited
- → Goal Misgeneralization in Deep Reinforcement Learning(2021)22 cited
- → Foundational Challenges in Assuring Alignment and Safety of Large Language Models(2024)14 cited
- Objective Robustness in Deep Reinforcement Learning.(2021)
- → Unifying Grokking and Double Descent(2023)2 cited