Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2408.10556 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909399506747392 |
|---|---|
| author | 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 |
| author_facet | 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 |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_10556 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks 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 Artificial Intelligence Machine Learning 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. |
| title | Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2408.10556 |