How can we reconcile the ease of specifying tasks through natural language-based approaches with the performance improvements of goal-conditioned learning?
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.
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.
As generative AI settles into the mainstream, growing numbers of courses and certifications are promising entry into the “hot job” of prompt engineering.