Evolving a Team in a First-Person Shooter Game by Using a Genetic Algorithm

Liaw, Chishyan; Tsai, Ching-Tsorng; Ko, Chao-Hui; Hao, Gorden

doi:10.1080/08839514.2013.768883

Cited by 11 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Genetic algorithm has been approved to obtain globally optimal solution of non-linear function and parameter estimation [14][15], genetic algorithm is used to optimize feature weight coefficients in our paper, whose specific step is as following:…”

Section: Optimized Methods Of Feature Weighting Coefficientsmentioning

confidence: 99%

Estimating Key Speaker in Meeting Speech Based on Multiple Features Optimization

Li¹,

Li²,

He³

2015

IJSIP

View full text Add to dashboard Cite

This paper proposes to estimate key speaker in meeting speech based on multiple features optimization. First, each feature is defined and their differences between key speaker and other speakers are analyzed. Then, a decision function of multiple feature weighting is generated for estimating key speaker in meeting speech, and the genetic algorithm is used to optimize these coefficients of feature weighting. The methods are evaluated on three different meeting speech datasets. Experimental results show that the proposed optimization method obtains average accuracy of 93.3% for estimating key speaker, and gains average accuracy improvement by 9.7% and 4.1% compared with the previous method and the feature weighting method without optimization, respectively.

show abstract

Section: Optimized Methods Of Feature Weighting Coefficientsmentioning

confidence: 99%

Estimating Key Speaker in Meeting Speech Based on Multiple Features Optimization

Li¹,

Li²,

He³

2015

IJSIP

View full text Add to dashboard Cite

show abstract

“…Cole et al used GAs to tune game agents for first person shooter games [13]. Liaw et al used GAs to evolve game agents that work as a team [14] . Othman et al discuss using simulations to evolve an AI agent for tactical purposes [15].…”

Section: A Problem Domain and Previous Workmentioning

confidence: 99%

Adaptive Simulation-Based Training of Artificial-Intelligence Decision Makers Using Bayesian Optimization

Israelsen¹,

Ahmed²,

Green³

et al. 2018

Journal of Aerospace Information Systems

View full text Add to dashboard Cite

This work studies how an AI-controlled dog-fighting agent with tunable decisionmaking parameters can learn to optimize performance against an intelligent adversary, as measured by a stochastic objective function evaluated on simulated combat engagements. Gaussian process Bayesian optimization (GPBO) techniques are developed to automatically learn global Gaussian Process (GP) surrogate models, which provide statistical performance predictions in both explored and unexplored areas of the parameter space. This allows a learning engine to sample full-combat simulations at parameter values that are most likely to optimize performance and also provide highly informative data points for improving future predictions. However, standard GPBO methods do not provide a reliable surrogate model for the highly volatile objective functions found in aerial combat, and thus do not reliably identify global maxima.These issues are addressed by novel Repeat Sampling (RS) and Hybrid Repeat/Multipoint Sampling (HRMS) techniques. Simulation studies show that HRMS improves the accuracy of GP surrogate models, allowing AI decision-makers to more accurately predict performance and efficiently tune parameters.

show abstract

“…Referenced in (Choi et al, 2007) as a testbed for a believable agent, built with the help of general-purpose cognitive architecture called ICARUS. Also used in experiments with neural network-based AI by Westra and Dignum (2009), and with genetic algorithm-based AI strategy optimization by Liaw, Wang, Tsai, Ko, & Hao (2013). Since the engine's source code is freely available now under GNU license, some researchers implement new algorithms directly in the code of existing game bots (El Rhalibi & Merabti, 2008).…”

Section: Testbedsmentioning

confidence: 99%

Creating Believable and Effective AI Agents for Games and Simulations

Umarov¹,

Mozgovoy

2014

Advances in Systems Analysis, Software Engineering, and High Performance Computing

View full text Add to dashboard Cite

The rapid development of complex virtual worlds (most notably, in 3D computer and video games) introduces new challenges for the creation of virtual agents, controlled by Artificial Intelligence (AI) systems. Two important sub-problems in this topic area that need to be addressed are (a) believability and (b) effectiveness of agents' behavior (i.e. human-likeness of the characters and high ability to achieving their own goals). In this chapter, the authors study current approaches to believability and effectiveness of AI behavior in virtual worlds. They examine the concepts of believability and effectiveness and analyze several successful attempts to address these challenges. In conclusion, the authors provide a case study that suggests that believable and effective behavior can be achieved through learning behavioral patterns from observation with subsequent automatic selection of effective acting strategies.

show abstract

Evolving a Team in a First-Person Shooter Game by Using a Genetic Algorithm

Cited by 11 publications

References 12 publications

Estimating Key Speaker in Meeting Speech Based on Multiple Features Optimization

Estimating Key Speaker in Meeting Speech Based on Multiple Features Optimization

Adaptive Simulation-Based Training of Artificial-Intelligence Decision Makers Using Bayesian Optimization

Creating Believable and Effective AI Agents for Games and Simulations

Contact Info

Product

Resources

About