AI People Wiki

Builders & open source

Christopher Berner

Research engineer, OpenAI

Christopher Berner is listed as the first named author on OpenAI's 2019 paper "Dota 2 with Large Scale Deep Reinforcement Learning," documenting OpenAI Five's defeat of world champions Team OG. Author-contribution notes credit him among early Dota work including the 1v1 training system, Dota 2 gym interface, first Dota agent, and early batch-size scaling.123

At a glance

Current role
None confirmed in the sources
Company
OpenAI
Sources cited
3
Profile reviewed

Accomplishments

  • First author, Dota 2 large-scale deep RL technical report.1
  • Early OpenAI Five 1v1 systems and batch scaling.2

OpenAI Five

The OpenAI Five system used large-scale PPO self-play to defeat Dota 2 world champions in April 2019. Berner is first author on the technical report and is credited in contribution notes with early 1v1 systems and scaling experiments that preceded the full 5v5 agent.12

Timeline

  1. OpenAI Five defeats Team OG.3
  2. Dota 2 large-scale RL paper released.1

Documented roles

The sources do not confirm a current role; these are the roles they document.

  • Research engineer (Dota / OpenAI Five), OpenAI1

Where they work

Open roles at OpenAI (808)

See all 808 open jobs at OpenAI →

Suggest a correction or removal

Profiles cover public professional work only, and each statement cites a source. If something is out of date, missing or wrong, tell us and link a source. People can also ask for their profile to be corrected or removed.

References

3 sources · profile reviewed Oct 24, 2026 · data updated Oct 24, 2026

  1. Dota 2 with Large Scale Deep Reinforcement LearningarXiv · Paper · published Dec 13, 2019 · accessed Oct 24, 2026
  2. Dota 2 with Large Scale Deep RL (PDF)OpenAI · Paper · accessed Oct 24, 2026
  3. OpenAI Five defeats Dota 2 world championsOpenAI · Announcement · accessed Oct 24, 2026