# Foolproof Cooperative Learning

arXiv: https://arxiv.org/abs/1906.09831 · HTML: https://mlsanity.com/paper/1906.09831/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jun 2019.

## Built on by (most cited first, 3 of 3)

- [A Review of Cooperation in Multi-agent Learning](https://mlsanity.com/paper/2312.05162/) (2023)
- [Balancing Adaptability and Non-exploitability in Repeated Games](https://mlsanity.com/paper/2112.10314/) (2021)
- [Learning Collective Action under Risk Diversity](https://mlsanity.com/paper/2201.12891/) (2022)

## Abstract (arXiv)

This paper extends the notion of learning equilibrium in game theory from matrix games to stochastic games. We introduce Foolproof Cooperative Learning (FCL), an algorithm that converges to a Tit-for-Tat behavior. It allows cooperative strategies when played against itself while being not exploitable by selfish players. We prove that in repeated symmetric games, this algorithm is a learning equilibrium. We illustrate the behavior of FCL on symmetric matrix and grid games, and its robustness to selfish learners.