Monopoly Deal: A Benchmark Environment for Bounded One-Sided Response Games

TL;DR

This paper introduces Monopoly Deal as a benchmark environment for studying bounded one-sided response games, providing a platform for evaluating decision-making algorithms in this strategic setting.

Contribution

It presents a modified Monopoly Deal environment to isolate bounded one-sided response dynamics and demonstrates CFR's effectiveness without new algorithmic developments.

Findings

CFR converges to effective strategies in the environment

The platform supports research with a web interface and open-source code

The environment isolates a unique game dynamic for focused study

Abstract

Card games are widely used to study sequential decision-making under uncertainty, with real-world analogues in negotiation, finance, and cybersecurity. These games typically fall into three categories based on the flow of control: strictly sequential (players alternate single actions), deterministic response (some actions trigger a fixed outcome), and unbounded reciprocal response (alternating counterplays are permitted). A less-explored but strategically rich structure is the bounded one-sided response, where a player's action briefly transfers control to the opponent, who must satisfy a fixed condition through one or more moves before the turn resolves. We term games featuring this mechanism Bounded One-Sided Response Games (BORGs). We introduce a modified version of Monopoly Deal as a benchmark environment that isolates this dynamic, where a Rent action forces the opponent to choose payment assets. The gold-standard algorithm, Counterfactual Regret Minimization (CFR), converges on effective strategies without novel algorithmic extensions. A lightweight full-stack research platform unifies the environment, a parallelized CFR runtime, and a human-playable web interface. The trained CFR agent and source code are available at https://monopolydeal.ai.