Towards Modern Card Games with Large-Scale Action Spaces Through Action Representation
This addresses the problem of applying RL to games with huge action spaces for game AI developers, but it is incremental as it builds on existing RL techniques.
The paper tackled the challenge of solving Axie Infinity, a complex card game with a large action space, by proposing a hybrid RL framework that uses action representations to evaluate actions in a fixed-size set, achieving the best winning rate and sample efficiency compared to baseline methods.
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.