# Mastering Complex Control in MOBA Games with Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/1912.09729 · HTML: https://mlsanity.com/paper/1912.09729/

## Key facts

- Cited by 161 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Dec 2019.

## Built on by (most cited first, 30 of 161)

- [Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2106.03400/) (2021)
- [Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning](https://mlsanity.com/paper/2508.09726/) (2025)
- [DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning](https://mlsanity.com/paper/2106.06135/) (2021)
- [MiniCPM4: Ultra-Efficient LLMs on End Devices](https://mlsanity.com/paper/2506.07900/) (2025)
- [A Survey on Transformers in Reinforcement Learning](https://mlsanity.com/paper/2301.03044/) (2023)
- [DCPO: Dynamic Clipping Policy Optimization](https://mlsanity.com/paper/2509.02333/) (2025)
- [Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR](https://mlsanity.com/paper/2507.15778/) (2025)
- [Block-Attention for Efficient Prefilling](https://mlsanity.com/paper/2409.15355/) (2024)
- [JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2112.04907/) (2021)
- [Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement Learning](https://mlsanity.com/paper/2209.08483/) (2022)
- [A Survey on Self-play Methods in Reinforcement Learning](https://mlsanity.com/paper/2408.01072/) (2024)
- [FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization](https://mlsanity.com/paper/2603.19835/) (2026)
- [Order Matters: Agent-by-agent Policy Optimization](https://mlsanity.com/paper/2302.06205/) (2023)
- [Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting](https://mlsanity.com/paper/2509.11452/) (2025)
- [Introducing LongCat-Flash-Thinking: A Technical Report](https://mlsanity.com/paper/2509.18883/) (2025)
- [POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding](https://mlsanity.com/paper/2407.14931/) (2024)
- [When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL](https://mlsanity.com/paper/2510.06062/) (2025)
- [You May Not Need Ratio Clipping in PPO](https://mlsanity.com/paper/2202.00079/) (2022)
- [Excluding the Irrelevant: Focusing Reinforcement Learning through Continuous Action Masking](https://mlsanity.com/paper/2406.03704/) (2024)
- [Towards Applicable Reinforcement Learning: Improving the Generalization and Sample Efficiency with Policy Ensemble](https://mlsanity.com/paper/2205.09284/) (2022)
- [Pretraining in Deep Reinforcement Learning: A Survey](https://mlsanity.com/paper/2211.03959/) (2022)
- [Model-based Multi-agent Reinforcement Learning: Recent Progress and Prospects](https://mlsanity.com/paper/2203.10603/) (2022)
- [PPO-Clip Attains Global Optimality: Towards Deeper Understandings of Clipping](https://mlsanity.com/paper/2312.12065/) (2023)
- [Coordinated Proximal Policy Optimization](https://mlsanity.com/paper/2111.04051/) (2021)
- [Visual Imitation Learning with Patch Rewards](https://mlsanity.com/paper/2302.00965/) (2023)
- [Benchmarking End-to-End Behavioural Cloning on Video Games](https://mlsanity.com/paper/2004.00981/) (2020)
- [PerfectDou: Dominating DouDizhu with Perfect Information Distillation](https://mlsanity.com/paper/2203.16406/) (2022)
- [Spike Calibration: Fast and Accurate Conversion of Spiking Neural Network for Object Detection and Segmentation](https://mlsanity.com/paper/2207.02702/) (2022)
- [Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization](https://mlsanity.com/paper/2209.00347/) (2022)
- [DQ-GAT: Towards Safe and Efficient Autonomous Driving with Deep Q-Learning and Graph Attention Networks](https://mlsanity.com/paper/2108.05030/) (2021)

## Abstract (arXiv)

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.