Evolutionary Algorithms for Reinforcement Learning

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.

Cited by in corpus (14)

• ES-MAML: Simple Hessian-Free Meta Learning
• Derivative-Free Reinforcement Learning: A Review
• Reinforcement Learning Driven Heuristic Optimization
• Training Agents using Upside-Down Reinforcement Learning
• Zeroth-Order Algorithms for Nonconvex Minimax Problems with Improved Complexities
• Genetic Algorithms in Wireless Networking: Techniques, Applications, and Issues
• A survey of air combat behavior modeling using machine learning
• Surrogate-assisted distributed swarm optimisation for computationally expensive geoscientific models
• Counter-Factual Reinforcement Learning: How to Model Decision-Makers That Anticipate The Future
• Momentum Accelerates Evolutionary Dynamics
• Reusability and Transferability of Macro Actions for Reinforcement Learning
• Deep Reinforcement Learning using Genetic Algorithm for Parameter Optimization
• A Novel Update Mechanism for Q-Networks Based On Extreme Learning Machines
• Selection in Scale-Free Small World