Reinforcement Learning Agents in Colonel Blotto

TL;DR

This paper explores the effectiveness of reinforcement learning agents in the Colonel Blotto game, demonstrating their strong performance against random opponents and analyzing their strategic behaviors in multi-opponent scenarios.

Contribution

It introduces the application of RL agents to Colonel Blotto, showing their competitive performance and revealing how strategies differ between single and multiple opponents.

Findings

RL agents outperform random opponents

Performance remains strong with multiple opponents

Optimal strategies vary significantly between single and multiple opponents

Abstract

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.