Scalable Bilinear π Learning Using State and Action Features

Computer Science

• Linear Programming 100%
• Parameter Space 50%
• Primal-Dual 50%
• Reinforcement Learning 50%
• Markov Decision Process 50%
• Memory Footprint 50%
• Dual Formulation 50%
• Runtime Complexity 50%

Keyphrases

• Approximate Linear Programming 100%

Chemical Engineering

• Reinforcement Learning 100%