Redirigiendo al acceso original de articulo en 15 segundos...
ARTÍCULO
TITULO

Explaining Exploration?Exploitation in Humans

Antonio Candelieri    
Andrea Ponti and Francesco Archetti    

Resumen

Human as well as algorithmic searches are performed to balance exploration and exploitation. The search task in this paper is the global optimization of a 2D multimodal function, unknown to the searcher. Thus, the task presents the following features: (i) uncertainty (i.e., information about the function can be acquired only through function observations), (ii) sequentiality (i.e., the choice of the next point to observe depends on the previous ones), and (iii) limited budget (i.e., a maximum number of sequential choices allowed to the players). The data about human behavior are gathered through a gaming app whose screen represents all the possible locations the player can click on. The associated value of the unknown function is shown to the player. Experimental data are gathered from 39 subjects playing 10 different tasks each. Decisions are analyzed in a Pareto optimality setting?improvement vs. uncertainty. The experimental results show that the most significant deviations from the Pareto rationality are associated with a behavior named ?exasperated exploration?, close to random search. This behavior shows a statistically significant association with stressful situations occurring when, according to their current belief, the human feels there are no chances to improve over the best value observed so far, while the remaining budget is running out. To classify between Pareto and Not-Pareto decisions, an explainable/interpretable Machine Learning model based on Decision Tree learning is developed. The resulting model is used to implement a synthetic human searcher/optimizer successively compared against Bayesian Optimization. On half of the test problems, the synthetic human results as more effective and efficient.

 Artículos similares

       
 
Sheng Sheng, Qihui Chen, Jingjing Li and Hua Chen    
Climate change and human activities significantly impact the hydrological cycle, particularly in regions with numerous large-scale reservoirs. Recognizing the limitations of the reservoir module in the original SWAT model, this study presents an improved... ver más
Revista: Water

 
Gaoqiang Zhang, Yutong Cheng, Haodong Liu, Chunlei Xiao, Hongfeng Nie, Zhenzhou Zhu, Dan Zhao and Yourang Zan    
Water resources in arid and semi-arid areas are limiting factors for ecosystem health and economic development. Therefore, an accurate and reasonable assessment of ecological water demand is crucial for efficient water resource utilization. In this study... ver más
Revista: Water

 
Christos Tzimopoulos, Nikiforos Samarinas, Basil Papadopoulos and Christos Evangelides    
The process of how soil moisture profiles evolve into the soil and reach the root zone could be estimated by solving the appropriate strong nonlinear Richards? equation. The nonlinearity of the equation occurs because diffusivity D is generally an expone... ver más
Revista: Hydrology

 
Patricia Bu?kulic, Jelena Parlov, Zoran Kovac and Zoran Nakic    
This study demonstrates an approach to estimate the background value of nitrate as a basis for better groundwater management and protection in areas under long-term human impact. The aim was to determine the ambient background value (ABV) of nitrate in t... ver más
Revista: Hydrology

 
Gemma Di Federico and Andrea Burattin    
Process mining analyzes events that are logged during the execution of a process, with the aim of gathering useful information and knowledge. Process discovery algorithms derive process models that represent these processes. The level of abstraction at w... ver más
Revista: Future Internet