Posted on by Rafael Scapin

Reinforcement learning frustrates humans in teamplay, MIT study finds

Artificial intelligence has proven that complicated board and video games are no longer the exclusive domain of the human mind. From chess to Go to StarCraft, AI systems that use reinforcement learning algorithms have outperformed human world champions in recent years. But despite the high individual performance of RL agents, they can become frustrating teammates when paired with human players, according to a study by AI researchers at MIT Lincoln Laboratory.

https://bdtechtalks.com/2021/11/01/reinforcement-learning-hanabi/

Related Posts:

  1. Artificial Intelligence will match humans intelligence by 2062
  2. Presentation of the Week: The power of artificial intelligence vs the power of human intelligence
  3. The MIT Press and the MIT Media Lab Launch the Knowledge Futures Group
  4. Artificial Intelligence: What’s The Difference Between Deep Learning And Reinforcement Learning?
  5. Online Learning is Just as Effective as Traditional Education, According to a New MIT Study