Table 3 presents the details of datasets in HoK1v1 task. Spells set to frenzy . Generally, a level of "1" is used for datasets with the "norm" prefix, while a level This distinction indicates varying levels of difficulty. In the Generalization category, "norm_general" and "hard_general," have their corresponding datasets. For example, to sample the "norm_general" dataset, we let the level-1 model fight with level-0, level-542 For example, in the "norm_hero_general" experiment, we directly use the model trained on "norm_medium" dataset only contains the fixed default hero "luban."

We also introduce a novel baseline algorithm tailored for the inherent hierarchical action space of the game.

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.