Towards Playing Full MOBA Games With Deep Reinforcement Learning

Abstract

MOBA games, e.g., Honor of Kings, League of Legends, and Dota 2, pose grand challenges to AI systems such as multi-agent, enormous state-action space, complex action control, etc. Developing AI for playing MOBA games has raised much attention accordingly. However, existing work falls short in handling the raw game complexity caused by the explosion of agent combinations, i.e., lineups, when expanding the hero pool in case that OpenAI's Dota AI limits the play to a pool of only 17 heroes. As a result, full MOBA games without restrictions are far from being mastered by any existing AI system. In this paper, we propose a MOBA AI learning paradigm that methodologically enables playing full MOBA games with deep reinforcement learning. Specifically, we develop a combination of novel and existing learning techniques, including curriculum self-play learning, policy distillation, off-policy adaption, multi-head value estimation, and Monte-Carlo tree-search, in training and playing a large pool

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyye2020towards

Related papers

• Mastering Complex Control In MOBA Games With Deep Reinforcement Learning (2019)0.00
• Hierarchical Reinforcement Learning For Multi-agent MOBA Game (2019)0.00
• Dota 2 With Large Scale Deep Reinforcement Learning (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
• A Comprehensive Review Of Multi-agent Reinforcement Learning In Video Games (2025)5.24
• Tikick: Towards Playing Multi-agent Football Full Games From Single-agent Demonstrations (2021)0.00
• Tleague: A Framework For Competitive Self-play Based Distributed Multi-agent Reinforcement Learning (2020)0.00