Reward tampering problems and solutions in reinforcement learning: a causal influence diagram perspective

DOI10.1007/s11229-021-03141-4zbMath1529.68309arXiv1908.04734OpenAlexW3165436200MaRDI QIDQ6182771

Marcus Hutter, Victoria Krakovna, Tom Everitt, Ramana Kumar

Publication date: 26 January 2024

Published in: Synthese (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1908.04734

zbMATH Keywords

decision theoryBayesian learningcausalityreinforcement learningAGI safetycausal influence diagrams

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) General considerations in statistical decision theory (62C05) Agent technology and artificial intelligence (68T42) Causal inference from observational studies (62D20)

Related Items (1)

On Imperfect Recall in Multi-Agent Influence Diagrams

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Planning and acting in partially observable stochastic domains
• General time consistent discounting
• Multi-agent influence diagrams for representing and solving games.
• Representing and Solving Decision Problems with Limited Information
• A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

This page was built for publication: Reward tampering problems and solutions in reinforcement learning: a causal influence diagram perspective