Thoroughly testing video game software by hand is difficult. AI agents that can automatically explore different game functionalities are a promising alternative.
Legislation regulating AI safety and transparency is needed, say researchers, so British industry and education can put resources into AI development with confidence.
In this episode, Ben chats to Sarah Brin about art and AI, including curatorial practice for AI art, unionising creative art workers, collaborative artwork, and more.
Find out more about shielding, a popular Safe Reinforcement Learning (Safe RL) technique that aims to keep an agent safe whilst finding an optimal policy.