Optimality of Reinforcement Learning Algorithms with Linear Function Approximation

نویسنده

  • Ralf Schoknecht
چکیده

There are several reinforcement learning algorithms that yield approximate solutions for the problem of policy evaluation when the value function is represented with a linear function approximator. In this paper we show that each of the solutions is optimal with respect to a specific objective function. Moreover, we characterise the different solutions as images of the optimal exact value function under different projection operations. The results presented here will be useful for comparing the algorithms in terms of the error they achieve relative to the error of the optimal approximate solution.

برای دانلود رایگان 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

Low-Area/Low-Power CMOS Op-Amps Design Based on Total Optimality Index Using Reinforcement Learning Approach

This paper presents the application of reinforcement learning in automatic analog IC design. In this work, the Multi-Objective approach by Learning Automata is evaluated for accommodating required functionalities and performance specifications considering optimal minimizing of MOSFETs area and power consumption for two famous CMOS op-amps. The results show the ability of the proposed method to ...

متن کامل

A Function Approximation Method for Model-based High-Dimensional Inverse Reinforcement Learning

This works handles the inverse reinforcement learning problem in high-dimensional state spaces, which relies on an efficient solution of model-based high-dimensional reinforcement learning problems. To solve the computationally expensive reinforcement learning problems, we propose a function approximation method to ensure that the Bellman Optimality Equation always holds, and then estimate a fu...

متن کامل

Iteratively Extending Time Horizon Reinforcement Learning

Reinforcement learning aims to determine an (infinite time horizon) optimal control policy from interaction with a system. It can be solved by approximating the so-called Q-function from a sample of four-tuples (xt, ut, rt, xt+1) where xt denotes the system state at time t, ut the control action taken, rt the instantaneous reward obtained and xt+1 the successor state of the system, and by deter...

متن کامل

Reinforcement Learning with Linear Function Approximation and LQ control Converges

Reinforcement learning is commonly used with function approximation. However, very few positive results are known about the convergence of function approximation based RL control algorithms. In this paper we show that TD(0) and Sarsa(0) with linear function approximation is convergent for a simple class of problems, where the system is linear and the costs are quadratic (the LQ control problem)...

متن کامل

Residual Algorithms: Reinforcement Learning with Function Approximation

A number of reinforcement learning algorithms have been developed that are guaranteed to converge to the optimal solution when used with lookup tables. It is shown, however, that these algorithms can easily become unstable when implemented directly with a general function-approximation system, such as a sigmoidal multilayer perceptron, a radial-basisfunction system, a memory-based learning syst...

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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2002