Dota 2 With Large Scale Deep Reinforcement Learning

Abstract

On April 13th, 2019, OpenAI Five became the first AI system to defeat the world champions at an esports game. The game of Dota 2 presents novel challenges for AI systems such as long time horizons, imperfect information, and complex, continuous state-action spaces, all challenges which will become increasingly central to more capable AI systems. OpenAI Five leveraged existing reinforcement learning techniques, scaled to learn from batches of approximately 2 million frames every 2 seconds. We developed a distributed training system and tools for continual training which allowed us to train OpenAI Five for 10 months. By defeating the Dota 2 world champion (Team OG), OpenAI Five demonstrates that self-play reinforcement learning can achieve superhuman performance on a difficult task.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyopenai2019dota

Related papers

• Towards Playing Full MOBA Games With Deep Reinforcement Learning (2020)0.00
• Tikick: Towards Playing Multi-agent Football Full Games From Single-agent Demonstrations (2021)0.00
• Mastering Complex Control In MOBA Games With Deep Reinforcement Learning (2019)0.00
• Tleague: A Framework For Competitive Self-play Based Distributed Multi-agent Reinforcement Learning (2020)0.00
• A Comprehensive Review Of Multi-agent Reinforcement Learning In Video Games (2025)5.24
• Douzero: Mastering Doudizhu With Self-play Deep Reinforcement Learning (2021)0.00
• A Survey Of Deep Reinforcement Learning In Video Games (2019)0.00
• Applying Supervised And Reinforcement Learning Methods To Create Neural-network-based Agents For Playing Starcraft II (2021)0.00