Mastering Complex Control in MOBA Games with Deep Reinforcement Learning
This addresses the challenge of achieving human-level performance in complex game environments for AI and gaming applications, representing a strong specific gain rather than incremental.
The authors tackled the problem of complex action control in MOBA 1v1 games by developing a deep reinforcement learning framework, resulting in an AI agent that defeats top professional human players in full games.
We study the reinforcement learning problem of complex action control in the Multi-player Online Battle Arena (MOBA) 1v1 games. This problem involves far more complicated state and action spaces than those of traditional 1v1 games, such as Go and Atari series, which makes it very difficult to search any policies with human-level performance. In this paper, we present a deep reinforcement learning framework to tackle this problem from the perspectives of both system and algorithm. Our system is of low coupling and high scalability, which enables efficient explorations at large scale. Our algorithm includes several novel strategies, including control dependency decoupling, action mask, target attention, and dual-clip PPO, with which our proposed actor-critic network can be effectively trained in our system. Tested on the MOBA game Honor of Kings, our AI agent, called Tencent Solo, can defeat top professional human players in full 1v1 games.