| Autor: |
Qu, Yun, Wang, Boyuan, Shao, Jianzhun, Jiang, Yuhang, Chen, Chen, Ye, Zhenbin, Liu, Lin, Yang, Junfeng, Lai, Lin, Qin, Hongyang, Deng, Minwen, Zhuo, Juchao, Ye, Deheng, Fu, Qiang, Yang, Wei, Yang, Guang, Huang, Lanxiao, Ji, Xiangyang |
| Rok vydání: |
2024 |
| Předmět: |
|
| Druh dokumentu: |
Working Paper |
| Popis: |
The advancement of Offline Reinforcement Learning (RL) and Offline Multi-Agent Reinforcement Learning (MARL) critically depends on the availability of high-quality, pre-collected offline datasets that represent real-world complexities and practical applications. However, existing datasets often fall short in their simplicity and lack of realism. To address this gap, we propose Hokoff, a comprehensive set of pre-collected datasets that covers both offline RL and offline MARL, accompanied by a robust framework, to facilitate further research. This data is derived from Honor of Kings, a recognized Multiplayer Online Battle Arena (MOBA) game known for its intricate nature, closely resembling real-life situations. Utilizing this framework, we benchmark a variety of offline RL and offline MARL algorithms. We also introduce a novel baseline algorithm tailored for the inherent hierarchical action space of the game. We reveal the incompetency of current offline RL approaches in handling task complexity, generalization and multi-task learning. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
