DeepMind’s new system could be a step towards general AI, but there’s a way to go

One of the key challenges of deep reinforcement learning models—the kind of AI systems that have mastered Go, StarCraft 2, and other games—is their inability to generalize their capabilities beyond their training domain. This limit makes it very hard to apply these systems to real-world settings, where situations are much more complicated and unpredictable than the environments where AI models are trained. But scientists at AI research lab DeepMind claim to have taken the “first steps to train an agent capable of playing many different games without needing human interaction data,” according to a blog post about their new “open-ended…

This story continues at The Next Web

Related Articles

Building A Conversational N.L.P Enabled Chatbot Using Google’s Dialogflow

The 2019 Capgemini research institute’s report published after a research on the use of chat assistants showed a drastic 76% increase in customer satisfaction from organizations where chat assistants where built and incorporated into their services. But how does Dialogflow, a product from Google’s ecosystem, aid developers in building chat assistants and contribute to this quota?

Responses

Your email address will not be published. Required fields are marked *

Receive the latest news

Subscribe To Our Weekly Newsletter

Get notified about chronicles from TreatMyBrand (TMB.) directly in your inbox