Policy Gradient Algorithms Implicitly Optimize by Continuation
This offers a theoretical justification for existing policy-gradient methods, which is incremental but clarifies their underlying mechanisms.
The paper provides a new theoretical interpretation of policy-gradient algorithms in reinforcement learning by framing them within the optimization by continuation framework, showing that optimizing affine Gaussian policies with entropy regularization can be interpreted as implicitly optimizing deterministic policies through continuation.
Direct policy optimization in reinforcement learning is usually solved with policy-gradient algorithms, which optimize policy parameters via stochastic gradient ascent. This paper provides a new theoretical interpretation and justification of these algorithms. First, we formulate direct policy optimization in the optimization by continuation framework. The latter is a framework for optimizing nonconvex functions where a sequence of surrogate objective functions, called continuations, are locally optimized. Second, we show that optimizing affine Gaussian policies and performing entropy regularization can be interpreted as implicitly optimizing deterministic policies by continuation. Based on these theoretical results, we argue that exploration in policy-gradient algorithms consists in computing a continuation of the return of the policy at hand, and that the variance of policies should be history-dependent functions adapted to avoid local extrema rather than to maximize the return of the policy.