Riemannian Proximal Policy Optimization
نویسندگان
چکیده
منابع مشابه
Proximal Policy Optimization Algorithms
We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a “surrogate” objective function using stochastic gradient ascent. Whereas standard policy gradient methods perform one gradient update per data sample, we propose a novel objective function that enables multiple epochs of ...
متن کاملOptimization Techniques on Riemannian Manifolds
The techniques and analysis presented in this paper provide new methods to solve optimization problems posed on Riemannian manifolds. A new point of view is offered for the solution of constrained optimization problems. Some classical optimization techniques on Euclidean space are generalized to Riemannian manifolds. Several algorithms are presented and their convergence properties are analyzed...
متن کاملRiemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds
We study optimization of finite sums of geodesically smooth functions on Riemannian manifolds. Although variance reduction techniques for optimizing finite-sums have witnessed tremendous attention in the recent years, existing work is limited to vector space problems. We introduce Riemannian SVRG (RSVRG), a new variance reduced Riemannian optimization method. We analyze RSVRG for both geodesica...
متن کاملScalable Nuclear-norm Minimization by Subspace Pursuit Proximal Riemannian Gradient
Trace-norm regularization plays a vital role in many learning tasks, such as low-rank matrix recovery (MR), and low-rank representation (LRR). Solving this problem directly can be computationally expensive due to the unknown rank of variables or large-rank singular value decompositions (SVDs). To address this, we propose a proximal Riemannian gradient (PRG) scheme which can efficiently solve tr...
متن کاملProximal Point Methods with Bregman Function on Riemannian Manifolds
We study the proximal point algorithm with Bregman type distance to minimize the problem , , . ) ( min S x to s x f ∈ where S is an open convex subset of a complete simply connected Riemannian manifold M of non positive sectional curvature and f is a convex function in this manifold. Introducing a strong assumption on the geodesic triangle on this manifold we obtain the convergence of the seque...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Computer and Information Science
سال: 2020
ISSN: 1913-8997,1913-8989
DOI: 10.5539/cis.v13n3p93