Towards Modern Card Games with Large-Scale Action Spaces Through Action Representation

TL;DR

This paper introduces a hybrid reinforcement learning framework that leverages action representations to efficiently handle large-scale action spaces in complex card games like Axie Infinity, improving sample efficiency and winning rates.

Contribution

The paper presents a novel hybrid RL approach that uses action representations to manage large action spaces, outperforming baseline methods in efficiency and effectiveness.

Findings

Achieves the highest winning rate among tested methods.

Demonstrates superior sample efficiency.

Effectively handles large action spaces in complex games.

Abstract

Axie infinity is a complicated card game with a huge-scale action space. This makes it difficult to solve this challenge using generic Reinforcement Learning (RL) algorithms. We propose a hybrid RL framework to learn action representations and game strategies. To avoid evaluating every action in the large feasible action set, our method evaluates actions in a fixed-size set which is determined using action representations. We compare the performance of our method with the other two baseline methods in terms of their sample efficiency and the winning rates of the trained models. We empirically show that our method achieves an overall best winning rate and the best sample efficiency among the three methods.