Tag
OpenAI Five became the first AI system to defeat Dota 2 world champions using large-scale deep reinforcement learning with self-play, demonstrating superhuman performance on a complex game with long time horizons and imperfect information.
OpenAI Five becomes the first AI to defeat world-champion esports professionals in Dota 2, winning two back-to-back matches against OG at the OpenAI Five Finals. The breakthrough was achieved through unprecedented scaling of training compute rather than novel algorithms, and the team is retiring OpenAI Five while announcing plans to deploy it for public internet play.
OpenAI Five competed against top professional Dota 2 teams at The International 2018, losing both matches against elite human players while demonstrating competitive gameplay and strategic depth developed through self-taught learning.
OpenAI releases benchmark results for OpenAI Five, their Dota 2 playing system, detailing training methodology across six major revisions with compute requirements ranging from 8 to 35 petaflop/s-days and introducing new network architecture tooling.
OpenAI Five completed a benchmark match against humans in Dota 2, demonstrating improved capabilities including expanded hero pool (18 heroes), Roshan pit mechanics, and wards. The system shows general training flexibility in acquiring complex game skills.
OpenAI Five is a reinforcement learning agent that masters Dota 2 through self-play training with curriculum learning and strategic randomization, progressing from random behavior to executing complex human-level strategies.
OpenAI describes iterative improvements to their Dota 2 bot during The International tournament, combining coaching with self-play to enhance agent performance through rapid training cycles and strategic refinements discovered during professional matches.
OpenAI created a bot that defeats world-class Dota 2 professionals in 1v1 matches using only self-play learning, without imitation learning or tree search. The achievement demonstrates progress toward AI systems that can accomplish complex goals in dynamic, multi-agent environments.