Towards Controllable Agent in MOBA Games with Generative Modeling

TL;DR

This paper introduces a generative modeling approach to develop controllable MOBA game agents that mimic human behavior and align with human players, utilizing deep latent alignment networks and attention mechanisms.

Contribution

It presents a novel deep latent alignment neural network model and sampling algorithms for action control in MOBA games, including deterministic and stochastic attention variants.

Findings

Effective in simulated Honor of Kings gameplay

Demonstrates improved human-like behavior and control

Validated through online experiments

Abstract

We propose novel methods to develop action controllable agent that behaves like a human and has the ability to align with human players in Multiplayer Online Battle Arena (MOBA) games. By modeling the control problem as an action generation process, we devise a deep latent alignment neural network model for training agent, and a corresponding sampling algorithm for controlling an agent's action. Particularly, we propose deterministic and stochastic attention implementations of the core latent alignment model. Both simulated and online experiments in the game Honor of Kings demonstrate the efficacy of the proposed methods.