Repeated Games

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 12

All topics

Mitigating Retaliatory Algorithmic Collusion in Repeated Games
Sep 17, 2026Karthik Sivachandran, Rohan PalejaGame-Playing Agents Repeated Games
Department of Computer Science Purdue University
Symmetric solution of the Bellman optimality equation for repeated harmony game
Sep 14, 2026Hisato KomatsuGame-Playing Agents Game Theory
Department of Physics, Kindai University, 577-8502, Higashi-Osaka, Osaka, Japan · Data Science and AI Innovation Research Promotion Center, Shiga University, 522-8522, Hikone, Shiga, Japan
Cheap Talk Stabilizes Strategic Interaction in LLM Agents
Sep 14, 2026Nunzio Lorè, Hongan Zhu, Babak HeydariRepeated Games LLM Agents
Multi-Agent Intelligent Complex Systems (MAGICS) Lab, Northeastern University, Boston, MA, USA
Equilibrium stability as a driver of cooperation among Q-learners
Jul 15, 2026Janusz M. Meylahn, Maximilian SchäferGame-Playing Agents Repeated Games
University of Twente, Department of Applied Mathematics, Drienerloolaan 5, 7522 NB Enschede, The Netherlands. · Institut Mines-Télécom Business School, Department of Data Analytics, Economics, and Finance. 9 Rue Charles Fourier, 91000 Evry, France.
When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games
Jul 6, 2026Jerick Shi, Terry Jingcheng Zhang, Bernhard Schölkopf +2Multi-Agent LLM Systems Game-Playing Agents
Carnegie Mellon University, Pittsburgh, USA · Jinesis AI Lab, Vector Institute and University of Toronto, Toronto, Canada · EuroSafeAI +1
Congestion-Based Slot Pricing in a Railway Auction Game
Jul 2, 2026Bill Roungas, Sebastiaan MeijerMechanism Design Game-Playing Agents
Panteion University, Athens, Greece · Institute of Communication and Computer Systems, Athens, Greece · KTH Royal Institute of Technology, Stockholm, Sweden
Aligned but Not Partner-Specific: How Multimodal LLM Agents Succeed in Reference Games Without Forming Conceptual Pacts
Jun 6, 2026Po-Ya Angela Wang, Chinmaya Mishra, Aslı Özyürek +2Repeated Games LLM Agent Evaluation
Co-Intelligence Humanities AI Future Lab and Graduate Institute of Linguistics, National Taiwan University · Multimodal Language Department, Max Planck Institute for Psycholinguistics · Donders Institute for Brain, Cognition and Behaviour, Radboud University +1
Regret Minimization with Adaptive Opponents in Repeated Games
Jun 4, 2026Mingyang Liu, Asuman Ozdaglar, Tiancheng Yu +1Game-Playing Agents Game Theory
Massachusetts Institute of Technology · OpenAI · University of Maryland, College Park
DNQ: Deep Nash Q-Network for Partially Observable n-Player Games
Jun 4, 2026Qintong Xie, Edward Koh, Xavier Cadet +1Nash Equilibrium Reinforcement Learning
Multi-Agent Strategic Games with LLMs
May 5, 2026Maxim ChupilkinGame Theory Repeated Games
University of Oxford, Department of Politics and International Relations
Trust, Lies, and Long Memories: Emergent Social Dynamics and Reputation in Multi-Round Avalon with LLM Agents
Apr 22, 2026Suveen EllawelaMulti-Agent LLM Systems Game-Playing Agents
National University of Singapore
Unbeatable imitation of a friend
Jul 22, 2025Masahiko UedaGame-Playing Agents Game Theory
Graduate School of Sciences and Technology for Innovation, Yamaguchi University, 1677-1, Yoshida, Yamaguchi, 753-8511, Japan.

Sep 17, 2026, cs.LGJ/K move · Enter open · S save

Mitigating Retaliatory Algorithmic Collusion in Repeated Games

Karthik Sivachandran, Rohan Paleja

Department of Computer Science Purdue University

Game-Playing Agents Repeated Games Q-Learning Algorithmic Collusion Reward Design for RL Multi-Agent Reinforcement Learning

Open paper AskPDF arXiv

Reinforcement learning agents trained to maximize their own reward in repeated interactions can converge to supra-competitive outcomes resembling explicit collusion, without communication or shared design. Existing mitigation approaches are largely tied to specific economic settings, like two-sided platforms and auctions, leaving open how to design interventions for general repeated games. We address this gap by formalizing the connection between empirical observations from prior work on Q-learning collusion and classical theory of Simple Penal Codes (SPCs). We show any non-trivial SPC induces a quantifiable conditional dependence in agents' policies, detectable via the total variation distance between an agent's action distributions across cooperation and defection histories. Building on this connection, we propose CURB (Collusion Unwinding via Reward shaping and Belief injection), a reward-shaping framework that penalizes this Total Variation (TV) distance signal during Q-learning and is guaranteed to convert any SPC fixed point of the dynamics into a trivial one, thus precluding collusive equilibria sustained by punishment threats. Empirically, CURB substantially reduces collusion by Q-learning agents in both Bertrand and Cournot Competition Repeated Games. We further demonstrate that CURB extends to deep Q-network agents in Bertrand competition, suggesting the mechanism generalizes beyond tabular Q-learning.

Momentum

Related topics

Latest papers 12