Tag : Ai Explainability

• @deepmindsafetyresearch
• causality
• ai explainability
• ai safety

8 min read 2021-03-06 03:59:34

What mechanisms drive agent behaviour?

By the Safety Analysis Team: Grégoire Déletang, Jordi Grau-Moya, Miljan Martic, Tim Genewein, Tom McGrath, Vladimir Mikulik, Markus Kunesch, Shane

• @deepmindsafetyresearch
• causality
• ai explainability
• ai safety

8 min read 2021-03-06 03:59:34

What mechanisms drive agent behaviour?

By the Safety Analysis Team: Grégoire Déletang, Jordi Grau-Moya, Miljan Martic, Tim Genewein, Tom McGrath, Vladimir Mikulik, Markus Kunesch, Shane