Subvolts take Explore how AI can learn to cooperate, a key to solving complex global challenges. Feb 1, 2022 - Developers
- Understand how to design AI agents that can collaborate effectively with other agents and humans.
- Business
- Learn how cooperative AI can lead to more robust solutions for complex problems that require teamwork.
This episode features researchers from a leading AI lab discussing foundational work on cooperative AI, offering valuable insights into future AI development.
Better together
Audio streams from Hannah Fry. Your place is remembered on this device.
From Subvolts
Summary and analysis by Subvolts editorial, AI-assisted.
Google DeepMind's podcast episode "Better Together" features host Hannah Fry discussing cooperative AI with researchers Thore Graepel, Kevin McKee, Doina Precup, and Laura Weidinger. They explore how cooperation underpins societal achievements and influences AI development, drawing parallels from BF Skinner's work to strategic games like Diplomacy. The conversation delves into the research behind creating AI systems that can collaborate effectively.
This podcast explores how AI can learn to work together, like people do. Researchers discuss how cooperation helps us build big things and how AI can be designed to collaborate for better results.
This episode offers insight into the foundational research at Google DeepMind concerning cooperative AI. It's for anyone interested in how AI can be designed to work with humans and other AI systems, moving beyond purely competitive models. The discussion on cooperation connects directly to current frontier lab efforts in multi-agent systems and building more collaborative AI, relevant for developing AI that can solve complex, real-world problems.
- HostHannah Fry
- GuestThore GraepelDeepMind
- GuestKevin MckeeDeepMind
- GuestDoina PrecupDeepMind
- GuestLaura WeidingerDeepMind
- Episode Title: Better together
- Show: Google DeepMind: The Podcast
- Length: 35 minutes
- Interviewees: Thore Graepel, Kevin Mckee, Doina Precup & Laura Weidinger
- Influences Mentioned: BF Skinner, Diplomacy
Cooperation is at the heart of our society. Inventing the railway, giving birth to the Renaissance, and creating the Covid-19 vaccine all required people to combine efforts. But cooperation is so much more. It governs our education systems, healthcare, and food production. In this episode, Hannah meets the researchers working on cooperative AI, and hears about their work and influences from the famous American psychologist - and pigeon trainer - BF Skinner to the strategic board game Diplomacy.
For questions or feedback on the series, message us on Twitter @DeepMind or email podcast@deepmind.com
Interviewees: DeepMind’s Thore Graepel, Kevin Mckee, Doina Precup & Laura Weidinger
Credits
Presenter: Hannah Fry
Series Producer: Dan Hardoon
Production support: Jill Achineku
Sounds design: Emma Barnaby
Music composition: Eleni Shaw
Sound Engineer: Nigel Appleton
Editor: David Prest
Commissioned by DeepMind
Thank you to everyone who made this season possible!
Further reading:
Machines must learn to find common ground, Nature: https://www.nature.com/articles/d41586-021-01170-0
Introduction to Reinforcement Learning, DeepMind: https://www.youtube.com/watch?v=2pWv7GOvuf0
B.F. Skinner, Wikipedia: https://en.wikipedia.org/wiki/B._F._Skinner
The Tragedy of the Commons, Wikipedia: https://en.wikipedia.org/wiki/Tragedy_of_the_commons
Staving Off The Ultimate Tragedy Of The Commons, Forbes: https://www.forbes.com/sites/georgebradt/2021/11/02/staving-off-the-ultimate-tragedy-of-the-commons-by-making-better-complex-decisions-cooperatively-in-glasgow/
Understanding Agent Cooperation, DeepMind: https://deepmind.com/blog/article/understanding-agent-cooperation
The emergence of complex cooperative agents, DeepMind: https://deepmind.com/blog/article/capture-the-flag-science
Please leave us a review on Spotify or Apple Podcasts if you enjoyed this episode. We always want to hear from our audience whether that's in the form of feedback, new idea or a guest recommendation!
Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.
- cooperative AI
- DeepMind researchers
- AI that works well with people or other AI.
- BF Skinner
- Psychologist
- A famous psychologist known for studying behavior and learning.
44 minCan AI help us better predict the weather?
WithPeter Battaglia
45 minThe mathematics of AI uncertainty
WithZoubin Ghahramani
53 minSame guests, other shows
54 min10 Years of AlphaGo: The Turning Point for AI | Thore Graepel & Pushmeet Kohli
WithThore Graepel, Pushmeet Kohli
33 minFair for all
WithSasha Brown, William Isaac, Shakir Mohamed, Kevin Mckee
33 minThe road to AGI
WithShane Legg, Doina Precup, Dave Silver, Jackson Broshear
34 minLet's get physical
WithRaia Hadsell, Viorica Patraucean, Jan Humplik, Akhil Raju
Questions people ask
- What is cooperative AI?
- Cooperative AI involves designing artificial intelligence systems that can effectively work together with humans and other AI agents to achieve common goals.
- What influences the research on cooperative AI?
- The research draws inspiration from societal cooperation, the work of psychologist BF Skinner, and strategic board games like Diplomacy.
Page generated Oct 19, 2026. Summaries are Subvolts' own; the audio, artwork and notes belong to Hannah Fry.