scholarly journals Optimal Action-based or User Prediction-based Haptic Guidance: Can You Do Even Better?

Author(s):  
Hee-Seung Moon ◽  
Jiwon Seo
2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Benoît De Courson ◽  
Daniel Nettle

AbstractHumans sometimes cooperate to mutual advantage, and sometimes exploit one another. In industrialised societies, the prevalence of exploitation, in the form of crime, is related to the distribution of economic resources: more unequal societies tend to have higher crime, as well as lower social trust. We created a model of cooperation and exploitation to explore why this should be. Distinctively, our model features a desperation threshold, a level of resources below which it is extremely damaging to fall. Agents do not belong to fixed types, but condition their behaviour on their current resource level and the behaviour in the population around them. We show that the optimal action for individuals who are close to the desperation threshold is to exploit others. This remains true even in the presence of severe and probable punishment for exploitation, since successful exploitation is the quickest route out of desperation, whereas being punished does not make already desperate states much worse. Simulated populations with a sufficiently unequal distribution of resources rapidly evolve an equilibrium of low trust and zero cooperation: desperate individuals try to exploit, and non-desperate individuals avoid interaction altogether. Making the distribution of resources more equal or increasing social mobility is generally effective in producing a high cooperation, high trust equilibrium; increasing punishment severity is not.


Entropy ◽  
2021 ◽  
Vol 23 (6) ◽  
pp. 737
Author(s):  
Fengjie Sun ◽  
Xianchang Wang ◽  
Rui Zhang

An Unmanned Aerial Vehicle (UAV) can greatly reduce manpower in the agricultural plant protection such as watering, sowing, and pesticide spraying. It is essential to develop a Decision-making Support System (DSS) for UAVs to help them choose the correct action in states according to the policy. In an unknown environment, the method of formulating rules for UAVs to help them choose actions is not applicable, and it is a feasible solution to obtain the optimal policy through reinforcement learning. However, experiments show that the existing reinforcement learning algorithms cannot get the optimal policy for a UAV in the agricultural plant protection environment. In this work we propose an improved Q-learning algorithm based on similar state matching, and we prove theoretically that there has a greater probability for UAV choosing the optimal action according to the policy learned by the algorithm we proposed than the classic Q-learning algorithm in the agricultural plant protection environment. This proposed algorithm is implemented and tested on datasets that are evenly distributed based on real UAV parameters and real farm information. The performance evaluation of the algorithm is discussed in detail. Experimental results show that the algorithm we proposed can efficiently learn the optimal policy for UAVs in the agricultural plant protection environment.


PLoS ONE ◽  
2016 ◽  
Vol 11 (7) ◽  
pp. e0158709
Author(s):  
Femke E. van Beek ◽  
Irene A. Kuling ◽  
Eli Brenner ◽  
Wouter M. Bergmann Tiest ◽  
Astrid M. L. Kappers
Keyword(s):  

2021 ◽  
Author(s):  
Mine Sarac ◽  
Duke Loke ◽  
Max Evans ◽  
Olivia Chong ◽  
James Saunders ◽  
...  

2009 ◽  
Vol 103 (3-5) ◽  
pp. 276-285 ◽  
Author(s):  
Edwin H.F. van Asseldonk ◽  
Martijn Wessels ◽  
Arno H.A. Stienen ◽  
Frans C.T. van der Helm ◽  
Herman van der Kooij

Sign in / Sign up

Export Citation Format

Share Document