Dota 2 with Large Scale Deep Reinforcement Learning

by   OpenAI, et al.

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.


page 36

page 37

page 39

page 41


Towards Playing Full MOBA Games with Deep Reinforcement Learning

MOBA games, e.g., Honor of Kings, League of Legends, and Dota 2, pose gr...

Building a 3-Player Mahjong AI using Deep Reinforcement Learning

Mahjong is a popular multi-player imperfect-information game developed i...

ScrofaZero: Mastering Trick-taking Poker Game Gongzhu by Deep Reinforcement Learning

People have made remarkable progress in game AIs, especially in domain o...

Playing 2048 With Reinforcement Learning

The game of 2048 is a highly addictive game. It is easy to learn the gam...

Winning at Any Cost – Infringing the Cartel Prohibition With Reinforcement Learning

Pricing decisions are increasingly made by AI. Thanks to their ability t...

DouZero+: Improving DouDizhu AI by Opponent Modeling and Coach-guided Learning

Recent years have witnessed the great breakthrough of deep reinforcement...

Modular Architecture for StarCraft II with Deep Reinforcement Learning

We present a novel modular architecture for StarCraft II AI. The archite...

Code Repositories