[2201.00345] Robust Algorithmic Collusion
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
[2201.00345] Robust Algorithmic Collusion Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Economics > General Economics arXiv:2201.00345 (econ) [Submitted on 2 Jan 2022 ( v1 ), last revised 5 Jan 2022 (this version, v2)] Title: Robust Algorithmic Collusion Authors: Nicolas Eschenbaum , Filip Mellgren , Philipp Zahn View a PDF of the paper titled Robust Algorithmic Collusion, by Nicolas Eschenbaum and 2 other authors View PDF Abstract: This paper develops a formal framework to assess policies of learn
Explore this link on the map →related reading
- Algorithmic Game Theory (CS364A), Fall 2013timroughgarden.org
- Reinforcement Learning in Newcomblike Problemsproceedings.neurips.cc
- Evolution as Backstop for Reinforcement Learning · Gwern.netgwern.net
- [2312.08484] Self-Play Q-learners Can Provably Collude in the Iterated Prisoner's Dilemmaarxiv.org
- Game theory - Wikipediaen.wikipedia.org
- Part 2: Kinds of RL Algorithms - Spinning Up documentationspinningup.openai.com
- Robust Cooperation in the Prisoner's Dilemma — LessWronglesswrong.com
- [2211.14468] Similarity-based cooperative equilibriumarxiv.org
- [1912.01683] Optimal Policies Tend to Seek Powerarxiv.org
- Towards a scale-free theory of intelligent agency — AI Alignment Forumalignmentforum.org
- Reevaluating Policy Gradient Methods for Imperfect-Information Gamesarxiv.org
- [AN #70]: Agents that help humans who are still learning about their own preferences — LessWronglesswrong.com