Summary of Hokoff: Real Game Dataset From Honor Of Kings and Its Offline Reinforcement Learning Benchmarks, by Yun Qu et al.
Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks
by Yun Qu, Boyuan Wang, Jianzhun Shao, Yuhang Jiang, Chen Chen, Zhenbin Ye, Lin Liu, Junfeng Yang, Lin Lai, Hongyang Qin, Minwen Deng, Juchao Zhuo, Deheng Ye, Qiang Fu, Wei Yang, Guang Yang, Lanxiao Huang, Xiangyang Ji
First submitted to arxiv on: 20 Aug 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes Hokoff, a set of pre-collected datasets for Offline Reinforcement Learning (RL) and Offline Multi-Agent Reinforcement Learning (MARL). These datasets are designed to represent real-world complexities and practical applications. The datasets are derived from Honor of Kings, a MOBA game known for its intricate nature. The authors benchmark various offline RL and MARL algorithms using this framework and introduce a novel baseline algorithm tailored for the game’s hierarchical action space. They also highlight the limitations of current offline RL approaches in handling task complexity, generalization, and multi-task learning. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about creating special computer datasets to help machines learn from old games like Honor of Kings. The game is complicated and has many different actions. The researchers want to make it easier for computers to learn from this game by breaking it down into smaller pieces. They created a set of these “pieces” and used them to test how well different algorithms can learn from the game. They found that current ways of learning from old games aren’t very good at handling complicated tasks. |
Keywords
» Artificial intelligence » Generalization » Multi task » Reinforcement learning
