Least-Squares Temporal Difference Learning

نویسنده

  • Justin A. Boyan
چکیده

Excerpted from: Boyan, Justin. Learning Evaluation Functions for Global Optimization. Ph.D. thesis, Carnegie Mellon University, August 1998. (Available as Technical Report CMU-CS-98-152.) TD( ) is a popular family of algorithms for approximate policy evaluation in large MDPs. TD( ) works by incrementally updating the value function after each observed transition. It has two major drawbacks: it makes inefficient use of data, and it requires the user to manually tune a stepsize schedule for good performance. For the case of linear value function approximations and = 0, the Least-Squares TD (LSTD) algorithm of Bradtke and Barto [5] eliminates all stepsize parameters and improves data efficiency. This paper extends Bradtke and Barto’s work in three significant ways. First, it presents a simpler derivation of the LSTD algorithm. Second, it generalizes from = 0 to arbitrary values of ; at the extreme of = 1, the resulting algorithm is shown to be a practical formulation of supervised linear regression. Third, it presents a novel, intuitive interpretation of LSTD as a model-based reinforcement learning technique.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Locally Weighted Least Squares Temporal Difference Learning

This paper introduces locally weighted temporal difference learning for evaluation of a class of policies whose value function is nonlinear in the state. Least squares temporal difference learning is used for training local models according to a distance metric in state-space. Empirical evaluations are reported demonstrating learning performance on a number of strongly non-linear value function...

متن کامل

Sustainable ℓ2-regularized actor-critic based on recursive least-squares temporal difference learning

Least-squares temporal difference learning (LSTD) has been used mainly for improving the data efficiency of the critic in actor-critic (AC). However, convergence analysis of the resulted algorithms is difficult when policy is changing. In this paper, a new AC method is proposed based on LSTD under discount criterion. The method comprises two components as the contribution: (1) LSTD works in an ...

متن کامل

Ensembles of extreme learning machine networks for value prediction

Value prediction is an important subproblem of several reinforcement learning (RL) algorithms. In a previous work, it has been shown that the combination of least-squares temporal-difference learning with ELM (extreme learning machine) networks is a powerful method for value prediction in continuous-state problems. This work proposes the use of ensembles to improve the approximation capabilitie...

متن کامل

Least-squares temporal difference learning based on extreme learning machine

This paper proposes a least-squares temporal difference (LSTD) algorithm based on extreme learning machine that uses a singlehidden layer feedforward network to approximate the value function. While LSTD is typically combined with local function approximators, the proposed approach uses a global approximator that allows better scalability properties. The results of the experiments carried out o...

متن کامل

Kernel Recursive Least-Squares Temporal Difference Algorithms with Sparsification and Regularization

By combining with sparse kernel methods, least-squares temporal difference (LSTD) algorithms can construct the feature dictionary automatically and obtain a better generalization ability. However, the previous kernel-based LSTD algorithms do not consider regularization and their sparsification processes are batch or offline, which hinder their widespread applications in online learning problems...

متن کامل

Incremental Least-Squares Temporal Difference Learning

Approximate policy evaluation with linear function approximation is a commonly arising problem in reinforcement learning, usually solved using temporal difference (TD) algorithms. In this paper we introduce a new variant of linear TD learning, called incremental least-squares TD learning, or iLSTD. This method is more data efficient than conventional TD algorithms such as TD(0) and is more comp...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1999