# Reinforcement Learning Agents in Colonel Blotto

arXiv: https://arxiv.org/abs/2204.02785 · HTML: https://mlsanity.com/paper/2204.02785/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 2 references that are in the map.
- First posted on arXiv 4 Apr 2022.

## Builds on (most cited first, 1 of 1)

- [OpenSpiel: A Framework for Reinforcement Learning in Games](https://mlsanity.com/paper/1908.09453/) (2019)

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

- [When Is Diversity Rewarded in Cooperative Multi-Agent Learning?](https://mlsanity.com/paper/2506.09434/) (2025)
- [Reinforcement Learning for Game-Theoretic Resource Allocation on Graphs](https://mlsanity.com/paper/2505.06319/) (2025)
- [HGFormer: A Hierarchical Graph Transformer Framework for Two-Stage Colonel Blotto Games via Reinforcement Learning](https://mlsanity.com/paper/2506.08580/) (2025)

## Abstract (arXiv)

Models and games are simplified representations of the world. There are many different kinds of models, all differing in complexity and which aspect of the world they allow us to further our understanding of. In this paper we focus on a specific instance of agent-based models, which uses reinforcement learning (RL) to train the agent how to act in its environment. Reinforcement learning agents are usually also Markov processes, which is another type of model that can be used. We test this reinforcement learning agent in a Colonel Blotto environment1, and measure its performance against Random agents as its opponent. We find that the RL agent handily beats a single opponent, and still performs quite well when the number of opponents are increased. We also analyze the RL agent and look at what strategies it has arrived by looking at the actions that it has given the highest and lowest Q-values. Interestingly, the optimal strategy for playing multiple opponents is almost the complete opposite of the optimal strategy for playing a single opponent.