Hokoff: Real Game Dataset From Honor Of Kings And Its Offline Reinforcement Learning Benchmarks

Abstract

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 co

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyqu2024hokoff

Related papers

• Off-the-grid MARL: Datasets With Baselines For Offline Multi-agent Reinforcement Learning (2023)2.26
• D4RL: Datasets For Deep Data-driven Reinforcement Learning (2020)0.00
• Offline Fictitious Self-play For Competitive Games (2024)0.00
• AD4RL: Autonomous Driving Benchmarks For Offline Reinforcement Learning With Value-based Dataset (2024)7.16
• RL Unplugged: A Suite Of Benchmarks For Offline Reinforcement Learning (2020)0.00
• Neorl-2: Near Real-world Benchmarks For Offline Reinforcement Learning With Extended Realistic Scenarios (2025)0.00
• Fewer May Be Better: Enhancing Offline Reinforcement Learning With Reduced Dataset (2025)0.00
• Mini Honor Of Kings: A Lightweight Environment For Multi-agent Reinforcement Learning (2024)3.42