Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement LearningDownload PDF

Published: 17 Sept 2022, Last Modified: 22 Oct 2023NeurIPS 2022 Datasets and Benchmarks Readers: Everyone
Keywords: Reinforcement learning, competitive reinforcement learning
Abstract: This paper introduces Honor of Kings Arena, a reinforcement learning (RL) environment based on the Honor of Kings, one of the world’s most popular games at present. Compared to other environments studied in most previous work, ours presents new generalization challenges for competitive reinforcement learning. It is a multi-agent problem with one agent competing against its opponent; and it requires the generalization ability as it has diverse targets to control and diverse opponents to compete with. We describe the observation, action, and reward specifications for the Honor of Kings domain and provide an open-source Python-based interface for communicating with the game engine. We provide twenty target heroes with a variety of tasks in Honor of Kings Arena and present initial baseline results for RL-based methods with feasible computing resources. Finally, we showcase the generalization challenges imposed by Honor of Kings Arena and possible remedies to the challenges. All of the software, including the environment-class, are publicly available.
Author Statement: Yes
Supplementary Material: pdf
URL: https://github.com/tencent-ailab/hok_env
License: Apache License 2.0 for `hok_env` Tencent's Hornor of Kings AI And Machine Learning License for the game engine: https://github.com/tencent-ailab/hok_env/blob/master/GAMECORE.LICENSE
Contribution Process Agreement: Yes
In Person Attendance: Yes
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/arxiv:2209.08483/code)
7 Replies