[1401.5577] Robust Cooperation in the Prisoner's Dilemma: Program Equilibrium via Provability Logic

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status Get status notifications via email or slack

[1401.5577] Robust Cooperation in the Prisoner's Dilemma: Program Equilibrium via Provability Logic Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Computer Science and Game Theory arXiv:1401.5577 (cs) [Submitted on 22 Jan 2014 ( v1 ), last revised 5 Apr 2021 (this version, v2)] Title: Robust Cooperation in the Prisoner's Dilemma: Program Equilibrium via Provability Logic Authors: Mihaly Barasz , Paul Christiano , Benja Fallenstein , Marcello Herreshoff , Patrick LaVictoire , Eliez

related reading

• Robust Cooperation in the Prisoner's Dilemma — LessWronglesswrong.com
• [2211.05057] A Note on the Compatibility of Different Robust Program Equilibria of the Prisoner's Dilemmaarxiv.org
• [2401.05566] Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Trainingarxiv.org
• [2211.14468] Similarity-based cooperative equilibriumarxiv.org
• [2201.00345] Robust Algorithmic Collusionarxiv.org
• [2312.08484] Self-Play Q-learners Can Provably Collude in the Iterated Prisoner's Dilemmaarxiv.org
• [2512.18552] Toward Training Superintelligent Software Agents through Self-Play SWE-RLarxiv.org
• [2410.22540] A Demonic Outcome Logic for Randomized Nondeterminismarxiv.org
• Cooperative and uncooperative institution designs: Surprises and problems in open-source game theoryarxiv.org
• [2311.07815] Cooperative AI via Decentralized Commitment Devicesarxiv.org
• [2304.03279] Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmarkarxiv.org
• [1711.02456] Self-referential basis of undecidable dynamics: from The Liar Paradox and The Halting Problem to The Edge of Chaosarxiv.org