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 (26)

• A Survey and Critique of Multiagent Deep Reinforcement Learning
• Noisy Networks for Exploration
• CIXL2: A Crossover Operator for Evolutionary Algorithms Based on Population Features
• Slice as an Evolutionary Service: Genetic Optimization for Inter-Slice Resource Management in 5G Networks
• Fast Damage Recovery in Robotics with the T-Resilience Algorithm
• Deep Hierarchical Reinforcement Learning Algorithm in Partially Observable Markov Decision Processes
• Reinforcement Learning Produces Dominant Strategies for the Iterated Prisoner's Dilemma
• ES-MAML: Simple Hessian-Free Meta Learning
• Derivative-Free Reinforcement Learning: A Review
• Robustness of Quantum-Enhanced Adaptive Phase Estimation
• Reinforcement Learning Driven Heuristic Optimization
• Solving the Rubik's Cube Without Human Knowledge
• Training Agents using Upside-Down Reinforcement Learning
• Zeroth-Order Algorithms for Nonconvex Minimax Problems with Improved Complexities
• Neuron as a reward-modulated combinatorial switch and a model of learning behavior
• Surrogate-assisted distributed swarm optimisation for computationally expensive geoscientific models
• A survey of air combat behavior modeling using machine learning
• Genetic Algorithms in Wireless Networking: Techniques, Applications, and Issues
• Counter-Factual Reinforcement Learning: How to Model Decision-Makers That Anticipate The Future
• Momentum Accelerates Evolutionary Dynamics
• Co-evolutionary multi-task learning for dynamic time series prediction
• 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
• Optimized Look-Ahead Tree Policies: A Bridge Between Look-Ahead Tree Policies and Direct Policy Search