Research Article

Human-level performance in 3D multiplayer games with population-based reinforcement learning

See allHide authors and affiliations

Science  31 May 2019:
Vol. 364, Issue 6443, pp. 859-865
DOI: 10.1126/science.aau6249

eLetters is an online forum for ongoing peer review. Submission of eLetters are open to all. eLetters are not edited, proofread, or indexed.  Please read our Terms of Service before submitting your own eLetter.

Compose eLetter

Plain text

  • Plain text
    No HTML tags allowed.
  • Web page addresses and e-mail addresses turn into links automatically.
  • Lines and paragraphs break automatically.
Author Information
First or given name, e.g. 'Peter'.
Your last, or family, name, e.g. 'MacMoody'.
Your email address, e.g.
Your role and/or occupation, e.g. 'Orthopedic Surgeon'.
Your organization or institution (if applicable), e.g. 'Royal Free Hospital'.
Statement of Competing Interests

This question is for testing whether or not you are a human visitor and to prevent automated spam submissions.

Vertical Tabs

  • RE:

    As shown in Jaderberg et al. (2019), multiagent reinforcement learning is a promising avenue for artificial intelligence research, as agents have been documented to collaborate at human-level performance in the three-dimensional multiplayer game Quake III Arena in Capture the Flag mode. While it is impressive that multiagent collaboration at human-level performance is now possible, it also raises the inevitable question if we, as human-beings, have the skill and will to collaborate with AI agents in the future? As the findings arguably allude to, a failure to do so could erode our historical competitive advantage of collaboration in the race against the machines. Consequently, we need to find our appropriate coopetition strategy, i.e. The optimal combination of collaboration and competition, if we are to co-exist with AI agents in the future. Or to paraphrase the famous Danish scientist and artist Piet Hein: It is a question of “co-existence or no existence”.

    Competing Interests: None declared.

Stay Connected to Science

Navigate This Article