Genetic Programming as Policy Search in Markov Decision Processes

نویسنده

  • Chris Gearhart
چکیده

In this paper, we examine genetic programming as a policy search technique for planning problems representable as Markov Decision Processes. The planning task under consideration is derived from a real-time strategy war game. This problem presents unique challenges for standard genetic programming approaches; despite this, we show that genetic programming produces results competitive with standard techniques, albeit with certain

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

A Genetic Search In Policy Space For Solving Markov Decision Processes

Markov Decision Processes (MDPs) have been studied extensively in the context of decision making under uncertainty. This paper presents a new methodology for solving MDPs, based on genetic algorithms. In particular, the importance of discounting in the new framework is dealt with and applied to a model problem. Comparison with the policy iteration algorithm from dynamic programming reveals the ...

متن کامل

On the Performance Bounds of some Policy Search Dynamic Programming Algorithms

We consider the infinite-horizon discounted optimal control problem formalized by Markov Decision Processes. We focus on Policy Search algorithms, that compute an approximately optimal policy by following the standard Policy Iteration (PI) scheme via an -approximate greedy operator (Kakade and Langford, 2002; Lazaric et al., 2010). We describe existing and a few new performance bounds for Direc...

متن کامل

On Partially Observable Markov Decision Processes Using Genetic Algorithm Based Q-Learning

As powerful probabilistic models for optimal policy search, partially observable Markov decision processes (POMDPs) still suffer from the problems such as hidden state and uncertainty in action effects. In this paper, a novel approximate algorithm Genetic algorithm based Q-Learning (GAQ-Learning), is proposed to solve the POMDP problems. In the proposed methodology, genetic algorithms maintain ...

متن کامل

Integrating value functions and policy search for continuous Markov Decision Processes

Value function approaches for Markov decision processes have been used successfully to find optimal policies for a large number of problems. Recent findings have demonstrated that policy search can be used effectively in reinforcement learning when standard value function techniques become overwhelmed by the size and dimensionality of the state space. We demonstrate that substantial benefits ca...

متن کامل

Utilizing Generalized Learning Automata for Finding Optimal Policies in MMDPs

Multi agent Markov decision processes (MMDPs), as the generalization of Markov decision processes to the multi agent case, have long been used for modeling multi agent system and are used as a suitable framework for Multi agent Reinforcement Learning. In this paper, a generalized learning automata based algorithm for finding optimal policies in MMDP is proposed. In the proposed algorithm, MMDP ...

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 2003