William Vorhies's Blog Posts Tagged 'RL' (3)

Can Reinforcement Learning Break Through in 2020

Summary: Reinforcement Learning (RL) is going to be critical to achieving our AI/ML technology goals but it has several barriers to overcome. While reliability and a reduction in training data may be achievable within a year, the nature of RL as a ‘black box’ solution will bring scrutiny for its lack of transparency.

…

Continue

Added by William Vorhies on December 30, 2019 at 11:18am — No Comments

Reimagining Reinforcement Learning – Upside Down

Summary: For all the hype around winning game play and self-driving cars, traditional Reinforcement Learning (RL) has yet to deliver as a reliable tool for ML applications. Here we explore the main drawbacks as well as an innovative approach to RL that dramatically reduces the training compute requirement and time to train.

…

Continue

Added by William Vorhies on December 23, 2019 at 7:30am — No Comments

Things that Aren’t Working in Deep Learning

Summary: This may be the golden age of deep learning but a lot can be learned by looking at where deep neural nets aren’t working yet. This can be a guide to calming the hype. It can also be a roadmap to future opportunities once these barriers are behind us.

We are living in the golden age of deep…