Mastering Complex Control In MOBA Games With Deep Reinforcement Learning

Abstract

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyye2019mastering

Related papers

• Towards Playing Full MOBA Games With Deep Reinforcement Learning (2020)0.00
• Hierarchical Reinforcement Learning For Multi-agent MOBA Game (2019)0.00
• Hierarchical Macro Strategy Model For MOBA Game AI (2018)12.02
• Simplified Action Decoder For Deep Multi-agent Reinforcement Learning (2019)4.03
• Hierarchical Multi-agent Reinforcement Learning For Air Combat Maneuvering (2023)8.82
• Multi-agent Actor-critic For Mixed Cooperative-competitive Environments (2017)0.00
• A Comprehensive Review Of Multi-agent Reinforcement Learning In Video Games (2025)5.24
• Episodic Exploration For Deep Deterministic Policies: An Application To Starcraft Micromanagement Tasks (2016)0.00