Evolutionary Algorithms for Reinforcement Learning

Citations Over TimeTop 10% of 1999 papers

Abstract

There are two distinct approaches to solving reinforcement learning problems, namely, searching in value function space and searching in policy space. Temporal difference methods and evolutionary algorithms are well-known examples of these approaches. Kaelbling, Littman and Moore recently provided an informative survey of temporal difference methods. This article focuses on the application of evolutionary algorithms to the reinforcement learning problem, emphasizing alternative policy representations, credit assignment methods, and problem-specific genetic operators. Strengths and weaknesses of the evolutionary approach to reinforcement learning are presented, along with a survey of representative applications.

Related Papers

• → Temporal Difference Learning, SARSA, and Q-Learning(2019)14 cited
• → Dual Representations for Dynamic Programming and Reinforcement Learning(2007)30 cited
• → Variants of Bellman equation on reinforcement learning problems(2022)6 cited
• → Reinforcement Learning: Tutorial and Survey(2024)