paper-with-me

홈 › Papers

Policy Search: Any Local Optimum Enjoys a Global Performance Guarantee

2013-06-06 · Bruno Scherrer, Matthieu Geist

Local Policy Search is a popular reinforcement learning approach for handling large state spaces. Formally, it searches locally in a paramet erized policy space in order to maximize the associated value function averaged over some predefined distribution. It is probably commonly b elieved that the best one can hope in general from such an approach is to get a local optimum of this criterion. In this article, we show th e following surprising result: \emph{any} (approximate) \emph{local optimum} enjoys a \emph{global performance guarantee}. We compare this g uarantee with the one that is satisfied by Direct Policy Iteration, an approximate dynamic programming algorithm that does some form of Poli cy Search: if the approximation error of Local Policy Search may generally be bigger (because local search requires to consider a space of s tochastic policies), we argue that the concentrability coefficient that appears in the performance bound is much nicer. Finally, we discuss several practical and theoretical consequences of our analysis.

📄 PDF Abstract BibTeX arXiv:1306.1520

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Variance-Reduced Conservative Policy Iteration

2022-12-12 · Naman Agarwal, Brian Bullins, Karan Singh

We study the sample complexity of reducing reinforcement learning to a sequence of empirical risk minimization problems over the policy space. Such reductions-based algorithms exhibit local convergence in the function sp…

reinforcement-learningReinforcement Learning (RL)

Global optimization of expensive black-box models based on asynchronous hybrid-criterion with interval reduction

2018-11-29 · Chunlin Gong, Xu Li, Hua Su, Jinlei Guo 외

In this paper, a new sequential surrogate-based optimization (SSBO) algorithm is developed, which aims to improve the global search ability and local search efficiency for the global optimization of expensive black-box m…

global-optimization

Can We Find Nash Equilibria at a Linear Rate in Markov Games?

2023-03-03 · Zhuoqing Song, Jason D. Lee, Zhuoran Yang

We study decentralized learning in two-player zero-sum discounted Markov games where the goal is to design a policy optimization algorithm for either agent satisfying two properties. First, the player does not need to kn…

Probabilistic Saliency Estimation

2016-09-13 · Caglar Aytekin, Alexandros Iosifidis, Moncef Gabbouj

In this paper, we model the salient object detection problem under a probabilistic framework encoding the boundary connectivity saliency cue and smoothness constraints in an optimization problem. We show that this proble…

Objectobject-detectionObject DetectionOne-Class Classification+3

High-dimensional Bayesian Optimization via Covariance Matrix Adaptation Strategy

2024-02-05 · Lam Ngo, Huong Ha, Jeffrey Chan, Vu Nguyen 외

Bayesian Optimization (BO) is an effective method for finding the global optimum of expensive black-box functions. However, it is well known that applying BO to high-dimensional optimization problems is challenging. To a…

Bayesian Optimization