Decision Making in Monopoly using a Hybrid Deep Reinforcement Learning Approach

TL;DR

This paper introduces a hybrid deep reinforcement learning approach for Monopoly, combining RL with fixed policies to improve decision-making and outperform standard RL agents in winning games.

Contribution

The paper presents novel state and action representations, an improved reward function, and a hybrid RL-fixed policy method to enhance Monopoly gameplay strategies.

Findings

Hybrid agent outperforms standard RL agent by 30% in wins.

Proposed approach effectively handles skewed action distributions.

Demonstrates improved decision-making in complex, dynamic environments.

Abstract

Learning to adapt and make real-time informed decisions in a dynamic and complex environment is a challenging problem. Monopoly is a popular strategic board game that requires players to make multiple decisions during the game. Decision-making in Monopoly involves many real-world elements such as strategizing, luck, and modeling of opponent's policies. In this paper, we present novel representations for the state and action space for the full version of Monopoly and define an improved reward function. Using these, we show that our deep reinforcement learning agent can learn winning strategies for Monopoly against different fixed-policy agents. In Monopoly, players can take multiple actions even if it is not their turn to roll the dice. Some of these actions occur more frequently than others, resulting in a skewed distribution that adversely affects the performance of the learning agent. To tackle the non-uniform distribution of actions, we propose a hybrid approach that combines deep reinforcement learning (for frequent but complex decisions) with a fixed policy approach (for infrequent but straightforward decisions). Experimental results show that our hybrid agent outperforms a standard deep reinforcement learning agent by 30% in the number of games won against fixed-policy agents.