paper-with-me

홈 › Papers

Operator Splitting Value Iteration

2022-11-25 · Amin Rakhsha, Andrew Wang, Mohammad Ghavamzadeh, Amir-Massoud Farahmand

We introduce new planning and reinforcement learning algorithms for discounted MDPs that utilize an approximate model of the environment to accelerate the convergence of the value function. Inspired by the splitting approach in numerical linear algebra, we introduce Operator Splitting Value Iteration (OS-VI) for both Policy Evaluation and Control problems. OS-VI achieves a much faster convergence rate when the model is accurate enough. We also introduce a sample-based version of the algorithm called OS-Dyna. Unlike the traditional Dyna architecture, OS-Dyna still converges to the correct value function in presence of model approximation error.

📄 PDF Abstract BibTeX arXiv:2211.13937

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Single-Forward-Step Projective Splitting: Exploiting Cocoercivity

2019-02-24 · Patrick R. Johnstone, Jonathan Eckstein

This work describes a new variant of projective splitting for solving maximal monotone inclusions and complicated convex optimization problems. In the new version, cocoercive operators can be processed with a single forw…

GSOS: Gauss-Seidel Operator Splitting Algorithm for Multi-Term Nonsmooth Convex Composite Optimization

2017-08-01 · ICML 2017 8 · Li Shen, Wei Liu, Ganzhao Yuan, Shiqian Ma

In this paper, we propose a fast Gauss-Seidel Operator Splitting (GSOS) algorithm for addressing multi-term nonsmooth convex composite optimization, which has wide applications in machine learning, signal processing…

Toward Designing Convergent Deep Operator Splitting Methods for Task-specific Nonconvex Optimization

2018-04-28 · Risheng Liu, Shichao Cheng, Yi He, Xin Fan 외

Operator splitting methods have been successfully used in computational sciences, statistics, learning and vision areas to reduce complex problems into a series of simpler subproblems. However, prevalent splitting scheme…

Deblurring

Halpern-Type Accelerated and Splitting Algorithms For Monotone Inclusions

2021-10-15 · Quoc Tran-Dinh, Yang Luo

In this paper, we develop a new type of accelerated algorithms to solve some classes of maximally monotone equations as well as monotone inclusions. Instead of using Nesterov's accelerating approach, our methods rely on …

Vocal Bursts Type Prediction

Adaptive Three Operator Splitting

2018-04-06 · ICML 2018 7 · Fabian Pedregosa, Gauthier Gidel

We propose and analyze an adaptive step-size variant of the Davis-Yin three operator splitting. This method can solve optimization problems composed by a sum of a smooth term for which we have access to its gradient and …