NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:2438
Title:A Geometric Perspective on Optimal Representations for Reinforcement Learning


		
The paper studies representation learning for RL through a notion of adversarial value functions. This provides a new conceptual/theoretical understanding of representation learning for RL that all reviewers felt was interesting. The experimental results are somewhat preliminary, but sufficient.