Reinforcement Learning in Newcomblike Problems

N/A

# link_g0l4g6azxs.pdf ## Metadata - PDFFormatVersion=1.4 - IsLinearized=false - IsAcroFormPresent=false - IsXFAPresent=false - IsCollectionPresent=false - IsSignaturesPresent=false - Title=Reinforcement Learning in Newcomblike Problems - Producer=macOS Version 10.15 (Build 19A603) Quartz PDFContext - Author=Caspar Oesterheld - Creator=Preview - CreationDate=D:20220124163056Z00'00' - ModDate=D:20220124163056Z00'00' ## Contents ### Page 1 Reinforcement Learning in Newcomblike Environments James BellThe Alan Turing Institute London, UKjbell@posteo.comLinda LinseforsIndependent Researcherlinda.

saved by

• Lydia Nottingham
• Yudhister Joel Kumar
• Bhagyesh Kumar

related reading

• Approval-directed agency and the decision theory of Newcomb-like problemslink.springer.com
• A (Long) Peek into Reinforcement Learning | Lil'Loglilianweng.github.io
• Exploration for the Efficient Deployment of Reinforcement Learning Agentsopenreview.net
• RLAlgsInMDPs.pdfsites.ualberta.ca
• c21f4ce780c5c9d774f79841b81fdc6d-Paper.pdfproceedings.neurips.cc
• [1709.06560] Deep Reinforcement Learning that Mattersarxiv.org
• RL_Notes__final_.pdfjubayer-ibn-hamid.github.io
• [2005.01643] Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemsar5iv.labs.arxiv.org
• rltheorybook_ABJKS.pdfrltheorybook.github.io
• [2211.05311] When is Realizability Sufficient for Off-Policy Reinforcement Learning?ar5iv.labs.arxiv.org
• [2602.11399] Can We Really Learn One Representation to Optimize All Rewards?arxiv.org
• Deep Reinforcement Learning from Human Preferencesproceedings.neurips.cc