Search Results for author:
Found 1 papers, 0 papers with code
On the Second-Order Convergence of Biased Policy Gradient Algorithms
Since the objective functions of reinforcement learning problems are typically highly nonconvex, it is desirable that policy gradient, the most popular algorithm, escapes saddle points and arrives at second-order stationary points.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
