Journal ArticleDOI
Reinforcement learning versus evolutionary computation: A survey on hybrid algorithms
Reads0
Chats0
TLDR
This overview considers the entire spectrum of algorithmic aspects and proposes a novel methodology that analyses the technical resemblances and differences in ECRL.Abstract:
A variety of Reinforcement Learning (RL) techniques blends with one or more techniques from Evolutionary Computation (EC) resulting in hybrid methods classified according to their goal, new focus, and their component methodologies. We denote this class of hybrid algorithmic techniques as the evolutionary computation versus reinforcement learning (ECRL) paradigm. This overview considers the entire spectrum of algorithmic aspects and proposes a novel methodology that analyses the technical resemblances and differences in ECRL. Our design analyses the motivation for each ECRL paradigm, the underlying natural models, the sub-component algorithmic techniques, as well as the properties of their ensemble.read more
Citations
More filters
Journal ArticleDOI
Bio-inspired computation: Where we stand and what's next
Javier Del Ser,Javier Del Ser,Eneko Osaba,Daniel Molina,Xin-She Yang,Sancho Salcedo-Sanz,David Camacho,Swagatam Das,Ponnuthurai Nagaratnam Suganthan,Carlos A. Coello Coello,Francisco Herrera +10 more
TL;DR: The main purpose of this paper is to outline the state of the art and to identify open challenges concerning the most relevant areas within bio-inspired optimization, thereby highlighting the need for reaching a consensus and joining forces towards achieving valuable insights into the understanding of this family of optimization techniques.
Journal ArticleDOI
Artificial intelligence for sustainability: Challenges, opportunities, and a research agenda
TL;DR: It is argued that AI can support the derivation of culturally appropriate organizational processes and individual practices to reduce the natural resource and energy intensity of human activities and facilitate and fosters environmental governance.
Proceedings Article
Evolution-Guided Policy Gradient in Reinforcement Learning
Shauharda Khadka,Kagan Tumer +1 more
TL;DR: Evolutionary Reinforcement Learning (ERL), a hybrid algorithm that leverages the population of an EA to provide diversified data to train an RL agent, and reinserts the RL agent into theEA population periodically to inject gradient information into the EA.
Journal ArticleDOI
Parameters identification of photovoltaic cell models using enhanced exploratory salp chains-based approach
Abdelkader Abbassi,Abdelkader Abbassi,Rabeh Abbassi,Rabeh Abbassi,Ali Asghar Heidari,Ali Asghar Heidari,Diego Oliva,Huiling Chen,Arslan Habib,Mohamed Jemli,Mingjing Wang +10 more
TL;DR: This paper proposes an Opposition-based Learning Modified Salp Swarm Algorithm (OLMSSA) for accurate identification of the two-diode model parameters of the electrical equivalent circuit of the PV cell/module and demonstrates that OLMSSA is highly competitive and even significantly better than the reported results of the majority of recently-developed parameter identification methods.
Journal ArticleDOI
Differential evolution based on reinforcement learning with fitness ranking for solving multimodal multiobjective problems
TL;DR: A novel Differential Evolution algorithm based on Reinforcement Learning with Fitness Ranking (DE-RLFR), which could quickly and effectively find multiple PSs in the decision space, and approach PF in the global sense.
References
More filters
Journal ArticleDOI
Deep learning
TL;DR: Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.
Book
Deep Learning
TL;DR: Deep learning as mentioned in this paper is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts, and it is used in many applications such as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames.
Book
Reinforcement Learning: An Introduction
TL;DR: This book provides a clear and simple account of the key ideas and algorithms of reinforcement learning, which ranges from the history of the field's intellectual foundations to the most recent developments and applications.
Journal ArticleDOI
A fast and elitist multiobjective genetic algorithm: NSGA-II
TL;DR: This paper suggests a non-dominated sorting-based MOEA, called NSGA-II (Non-dominated Sorting Genetic Algorithm II), which alleviates all of the above three difficulties, and modify the definition of dominance in order to solve constrained multi-objective problems efficiently.
Book
Adaptation in natural and artificial systems
TL;DR: Names of founding work in the area of Adaptation and modiication, which aims to mimic biological optimization, and some (Non-GA) branches of AI.