Mastering Complex Control in MOBA Games with Deep Reinforcement Learning

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, the trained AI agents can defeat top professional human players in full 1v1 games. Introduction Deep reinforcement learning (DRL) has been widely used for building agents to learn complex control in competitive environments. In the competitive setting, a considerable amount of existing DRL research adopt two-agent games as the testbed, i.e., one agent versus another (1v1). Among them, Atari series and board games have been widely studied. For example, a human-level agent for playing Atari games is trained with deep Q-networks (Mnih et al. 2015). The incorporation of supervised learning and self-play into the training brings the agent to the level of beating human professionals in the game of Go (Silver et al. 2016).