Learning through human feedback

Learning through human feedback  #DeepLearning #AI #ArtificialIntelligence

  • That is why DeepMind co-founded initiatives like the Partnership on AI to Benefit People and Society and why we have a team dedicated to technical AI Safety.
  • Research in this field needs to be open and collaborative to ensure that best practices are adopted as widely as possible, which is why we are also collaborating with OpenAI on research in technical AI Safety.
  • One of the central questions in this field is how we allow humans to tell a system what we want it to do and – importantly – what we don’t want it to do.
  • This is increasingly important as the problems we tackle with machine learning grow more complex and are applied in the real world.
  • The first results from our collaboration demonstrate one method to address this, by allowing humans with no technical experience to teach a reinforcement learning (RL) system – an AI that learns by trial and error – a complex goal.

A central question in technical AI safety is how to tell an algorithm what we want it to do. Working with OpenAI, we demonstrate a novel system that allows a human with no technical experience to teach an AI how to perform a complex task, such as manipulating a simulated robotic arm.
Continue reading “Learning through human feedback”

Researchers Have Created an AI That Is Naturally Curious

Researchers Have Created an #AI That Is Naturally Curious 

 #fintech @futurism

  • Researchers have successfully given AI a curiosity implant, which motivated it to explore a virtual environment.
  • This could be the bridge between AI and real world application

    Researchers at the University of California (UC), Berkeley, have produced an artificial intelligence (AI) that is naturally curious.

  • While the AI that was not equipped with the curiosity ‘upgrade’ banged into walls repeatedly, the curious AI explored its environment in order to learn more.
  • This is a useful and effective strategy for teaching AI to complete specific tasks — as shown by the AI who beat the AlphaGo world number one — but less useful when you want a machine to be autonomous and operate outside of direct commands.
  • This is crucial step to integrating AI into the real world and having it solve real world problems because, as Agrawal says, “rewards in the real world are very sparse.”

Researchers have successfully given AI a curiosity implant, which motivated it to explore a virtual environment.
Continue reading “Researchers Have Created an AI That Is Naturally Curious”