Stuart Russell

Credited works

1. Algorithms for Inverse Reinforcement Learning author, byline position 2
2. An Open Letter Asks AI Researchers To Reconsider Responsibilities contributor, byline position 2
3. Cooperative Inverse Reinforcement Learning author, byline position 4
4. Policy invariance under reward transformations: Theory and application to reward shaping author, byline position 3
5. Provably Optimal Learning Algorithms for Assistance Games author, byline position 4
6. Research Priorities for Robust and Beneficial Artificial Intelligence author, byline position 1
7. Safe Learning Under Irreversible Dynamics via Asking for Help author, byline position 4
8. Should Robots be Obedient? author, byline position 4
9. The Off-Switch Game author, byline position 4

Related Parallax entries

• 2015 beneficial-AI open letter event
• 2023 pause letter on giant AI experiments event
• AI Alignment concept
• Algorithms for Inverse Reinforcement Learning paper
• Cooperative Inverse Reinforcement Learning paper
• Corrigibility concept
• Corrigibility paper
• Corrigible Assistance in One Round: Pragmatic-Pedagogic Best Response paper
• Distributional Shift concept
• From objectives to accountable control note
• Human Model Misspecification concept
• Key Papers: A Reading Guide note
• Meaningful Human Control concept
• Origins of Alignment: Problems Before the Name note
• Policy invariance under reward transformations: Theory and application to reward shaping paper
• Provably Optimal Learning Algorithms for Assistance Games paper
• Research Priorities for Robust and Beneficial Artificial Intelligence paper
• Safe Learning Under Irreversible Dynamics via Asking for Help paper
• Safely Interruptible Agents paper
• Safety Case concept
• Should Robots be Obedient? paper
• Stuart Russell person
• The Off-Switch Game paper