Poster
in
Affinity Workshop: 4th MusIML workshop at ICML’25
Making progress in Trustworthy AI using DeepMind’s AI Safety Gridworlds
Ahmed Ghoor · Jonathan Shock
Abstract:
DeepMind's AI Safety Gridworlds are a suite of environments aimed at facilitating the research and development of safe artificial intelligence by encapsulating simplified, yet meaningful, representations of safety challenges that real-world AI systems might encounter. This paper looks at DeepMind's accompanying paper and surveys several solutions that have been proposed for the environments.
Chat is not available.