Dota 2 represents a significant step up in complexity from board games. It is played in continuous space and time, features hidden information, and requires team coordination. In 2019, OpenAI Five defeated the world champions, Team OG.

The Scale of Training

OpenAI Five was trained entirely through self-play, accumulating 45,000 years of Dota gameplay over 10 months. It experienced 80% of the game's theoretical state space, allowing it to develop entirely new meta-strategies.

The most profound emergent behavior was selfless play. The agents learned to sacrifice themselves for the team objective, something humans struggle with due to ego.

MetricHuman BaselineOpenAI Five
Reaction Time~250msConstrained to ~250ms
Experience10-20,000 hours45,000 years
StrategyDefined roles (Carry, Support)Fluid, context-dependent roles

FAQ: OpenAI Five

Did it cheat with perfect API information?
No, its vision was restricted to what a human player would see (accounting for the fog of war).