Real-time neuroevolution in the NERO video game

By Kenneth O. Stanley, Bobby D. Bryant, Risto Miikkulainen. IEEE Transactions on Evolutionary Computation, 2005

426 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/3a01bdcd4bb19151d326bff1c84561ea0b6c757e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Biasing Coevolutionary Search for Optimal Multiagent Behaviors (2006, background): “Some research applies a single learner to improve the performance of an entire team of agents (for example, [5]–[7]).”
Compositional pattern producing networks: A novel abstraction of development (2007, methodology): “See Stanley et al. [ 72 ], Stanley and Miikkulainen”
Autonomous Evolution of Topographic Regularities in Artificial Neural Networks (2010, methodology): “This section reviews the NEAT method (for a full description see Stanley & Miikkulainen, 2002b, 2004; Stanley, Bryant, & Miikkulainen, 2005b).”
Regularized Evolution for Image Classifier Architecture Search (2018, methodology): “Real-time algorithms address this issue, e.g . rtNEAT [40] and tournament selection [19].”
Evolution of Plastic Learning in Spiking Networks via Memristive Connections (2012, methodology): “This method has been shown to be amenable to realtime evolution [53].”
Evolving plastic neural networks with novelty search (2010, methodology): “…was originally developed to evolve ANNs to solve difficult control and sequential decision tasks and has proven successful in a wide diversity of domains (Aaltonen et al., 2009; Stanley et al., 2003, 2005; Stanley & Miikkulainen, 2002; Taylor, Whiteson, & Stone, 2006; Whiteson & Stone, 2006).”
A unified approach to evolving plasticity and neural geometry (2012, neutral): “One methodology that has shown promise in autonomously generating ANNs for complex control problems is neuroevolution , i.e. evolving ANNs through evolutionary algorithms (EAs) [12] [20] [31] [35].”
Quo vadis artificial intelligence? (2022, background): “From a domain-specific perspective, ANI tools have been or are being developed for education, medication, transportation, marketing, and game production [72–76].”
Evolving Spiking Networks with Variable Resistive Memories (2014, methodology): “This method has been shown to be amenable to real-time evolution (Stanley et al., 2005).”
Exploiting Open-Endedness to Solve Problems Through the Search for Novelty (2008, methodology): “This paper’s experiments utilize NEAT, which has been proven in many control tasks [27, 29], including maze navigation [26], the domain of the experiments in this paper.”
Coevolution of neural networks using a layered pareto archive (2006, background): “the evolution of neural networks, which are a promising approach to constructing agents for complex games [ 15 ].”
A novel generative encoding for exploiting neural network sensor and output geometry (2007, methodology): “Parameter settings are based on standard SharpNEAT defaults and prior reported settings for NEAT [18, 20, 17].”
The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities (2018, positive): “Why Walk Around the Wall When You Can Walk Over It? The NeuroEvolving Robotic Operatives (NERO) video game applied digital evolution to enable non-player characters to evolve in real time while the game is being played [85].”
Generative NeuroEvolution for Deep Learning (2013, background): “…(NEAT) algorithm [17] is a popular neuroevolutionary approach that has been proven in a variety of challenging tasks, including particle physics [18, 19], simulated car racing [20], RoboCup Keep-away [21], function approximation [22], and real-time agent evolution [23], among others [17].”