Deep RL for bin packing

Karim Beguir (InstaDeep)

11:05–11:45 Thursday, 17 October 2019

Location: Westminster Suite

Average rating:

(4.75, 4 ratings)

Karim Beguir discusses a system in which an agent that learns to pack boxes efficiently in containers while respecting multiple physical constraints. The agent is trained using reinforcement learning to minimize the wasted space. Without any human knowledge, the agent achieves superhuman performance and outperforms commercial optimization software.

Karim Beguir

InstaDeep

Karim Beguir helps companies get a grip on the latest AI advances and deploy them in practice. A graduate of France’s École Polytechnique and former program fellow at NYU’s Courant Institute, Karim has a passion for teaching and using applied mathematics. This encouraged him to cofound InstaDeep (named one of the 20 global tech startups to watch in 2017 by PCMag). Karim is one of fewer than 100 Google Certified Machine Learning Developer Experts worldwide and serves on the steering committee of Indaba, Africa’s most important AI event series. Karim is now on a mission to democratize AI and make it accessible to a wider audience.