A Parametric Class of Approximate Gradient Updates for Policy Optimization

Saurabh Kumar
Junfeng Wen
Dale Schuurmans


Approaches to policy optimization have been motivated from diverse principles, based on how the parametric model is interpreted or how the learning objective is formulated, yet they share a common goal of maximizing expected return. To better capture the commonalities and identify the key differences between alternative policy optimization methods, we develop a unified perspective that re-expresses the underlying update rules in terms of a limited choice of gradient form and a scaling function. In particular, we identify a unified space of approximate gradient updates for policy optimization that is highly structured, yet covers both classical and recent examples, including PPO. The primary benefit is that the framework also reveals novel but still well motivated updates that generalize existing algorithms in a way that can deliver benefits both in terms of convergence speed and final result quality. An experimental investigation demonstrates that the additional degrees of freedom identified in the unification can be leveraged to obtain non-trivial improvements both in synthetic domains and on popular deep RL benchmarks.