All about Iterated Prisoner's Dilemma. Python code and jupyter notebooks. See how to build new strategies and evaluate them.

Prisoner's Dilemma research environment.

Reinforcement learning approach to the prisoner's dilemma, based on Q learning

This is the repository for my 20 credit project during my final year at cardiff university. The project involves researching the best responses to strategies in the Iterated Prisoners Dilemma.

Prisoner's dilemma simulator including genetic algorithms for strategy evolution and a spatial variant of the iterated prisoner's dilemma game

A prisoner's dilemma game simulation in Clojure

This is a model plugin for Evoplex. It implements the spatial prisoner's dilemma game proposed by Nowak, M. A., & May, R. M. (1992). Evolutionary games and spatial chaos. Nature, 359(6398), 826.

A prisoner's dilemma agent based model simulation for investigating effects of differing strategies on emergent behaviours and spatial patterns with configurable environments.

Run Prisoner's Dilemma competitions in Python.

This Python program simulates the Prisoner's Dilemma, allowing players to choose from various strategies (Cooperator, Defector, Revenger, Tit-for-Tat, Random, and Detective). Players can specify the number of rounds, with an optional delay to observe each round’s interactions.

Presentations n Papers

Finds optimal strategies for sequential symmetric games using a genetic algorithm

Recreation of the prisoner's dilemma model from Axelrod's "Evolution of Cooperation" in Python

🎮 A web simulator for the Iterated Prisoner's Dilemma, inspired by Robert Axelrod🧠

A tool to analyze strategies for the Iterated Prisoner's Dilemma

Lacan's Prisoner's Dilemma Done VIsually and Linearly

Published research codebase: multi-agent N-person IPD simulation + analysis (game theory / MARL).

A NetLogo Agent Based Model extending Smaldino's (2013) Spatial Prisoner's Dilemma by incorporating reciprocating agents.

Agentic Game Lab is a modular research framework for studying LLM-based AI agents in stochastic, multi-player games such as the Iterated Prisoner’s Dilemma. It integrates configurable simulators, structured logging, and analysis pipelines to evaluate emergent strategic behavior under noise, payoff drift, and dynamic rules.

This program simulates and quantifies outcomes of parameterized prisoner’s dilemma simulation in various MAS networks. This is the third lab in the series of 3 lab projects designed to introduce Multi-Agent Systems (MAS) as a base for Machine Learning.