OpenAI Five

📰 OpenAI News

OpenAI Five, a team of five neural networks, defeats amateur human teams at Dota 2 using self-play and reinforcement learning

advanced Published 25 Jun 2018
Action Steps
  1. Train a neural network using self-play and reinforcement learning
  2. Use a scaled-up version of Proximal Policy Optimization running on multiple GPUs and CPU cores
  3. Implement a separate LSTM for each hero to learn recognizable strategies
  4. Benchmark progress by hosting matches against top players
Who Needs to Know This

AI engineers and researchers benefit from understanding the application of reinforcement learning and self-play in complex games like Dota 2, while product managers and entrepreneurs can learn from the potential of AI in esports

Key Insight

💡 Reinforcement learning can yield long-term planning with large but achievable scale without fundamental advances

Share This
🤖 OpenAI Five defeats amateur human teams at Dota 2 using self-play and reinforcement learning! 💻
Read full article → ← Back to News