# Reinforcement Learning Produces Dominant Strategies for the Iterated Prisoner's Dilemma

arXiv: https://arxiv.org/abs/1707.06307 · HTML: https://mlsanity.com/paper/1707.06307/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2017.

## Built on by (most cited first, 8 of 8)

- [Model-Free Opponent Shaping](https://mlsanity.com/paper/2205.01447/) (2022)
- [COLA: Consistent Learning with Opponent-Learning Awareness](https://mlsanity.com/paper/2203.04098/) (2022)
- [Scaling Opponent Shaping to High Dimensional Games](https://mlsanity.com/paper/2312.12568/) (2023)
- [Modeling Moral Choices in Social Dilemmas with Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2301.08491/) (2023)
- [Opponent Shaping in LLM Agents](https://mlsanity.com/paper/2510.08255/) (2025)
- [Mathematics of multi-agent learning systems at the interface of game theory and artificial intelligence](https://mlsanity.com/paper/2403.07017/) (2024)
- [Constant-Memory Strategies in Stochastic Games: Best Responses and Equilibria](https://mlsanity.com/paper/2505.07008/) (2025)
- [Preference-based opponent shaping in differentiable games](https://mlsanity.com/paper/2412.03072/) (2024)

## Abstract (arXiv)

We present tournament results and several powerful strategies for the Iterated Prisoner's Dilemma created using reinforcement learning techniques (evolutionary and particle swarm algorithms). These strategies are trained to perform well against a corpus of over 170 distinct opponents, including many well-known and classic strategies. All the trained strategies win standard tournaments against the total collection of other opponents. The trained strategies and one particular human made designed strategy are the top performers in noisy tournaments also.