Subjects: Computer Science >> Other Disciplines of Computer Science Subjects: Psychology >> Other Disciplines of Psychology submitted time 2021-12-21
Abstract: " Game map is an important human-computer interactive content-bearing platform in major games. With the application of cellular automata(CA) and Procedural Content Generation (PCG)in map generation, the spatial scale and data volume of current game maps are increasing greatly, while in game map test procedure, automatic methods such as interactive test script are inadequate both in depth and application breadth, especially in the lack of game map evaluation from player experience perspective. This research proposes an automatic game map test method based on agent reinforcement learning. By establishing agents’ interactive action models standing for different types of players’ behaviors in the map, universal evaluation of the map environment is enhanced through agent actions, which can optimize game map design from the perspective of player experience with quantitative value of inferiority. Finally, our campus scenes in Minecraft were used as the experimental environments to verify the effectiveness of the method.
Peer Review Status:Awaiting Review
Subjects: Psychology >> Physiological Psychology Subjects: Computer Science >> Other Disciplines of Computer Science submitted time 2020-08-07
Abstract: Neuroscience have great inspiration for artificial intelligence. By drawing on the research results of these disciplines, we designed a new artificial neural network to simulate the amygdala in human brain. The neural network consists of two parts, a long-term memory network and a activation network. The memory network records the neurons sending and receiving signals and the weight between them, while the activation network records the neurons sending and receiving signals and the time point when the signals were sent. The activation network retains only a short time memory of the event and modifies the weights in the long-term memory network according to the set rules. Using this approach, we have successfully endows the agent the ability of fear emotion learning and classical conditioning learning, which is very similar to the ability of amygdala".
Peer Review Status:Awaiting Review
Subjects: Psychology >> Medical Psychology Subjects: Computer Science >> Other Disciplines of Computer Science submitted time 2019-09-28
Abstract: Machine learning is a promising approach for mental disorders. In recent years, machine learning based on T1 weighted imaging and Diffusion Tensor Imaging (DTI) data has been used to investigate the psychopathology and underlying mechanisms of schizophrenia patients and high-risk population. The findings from the previous literature suggest that structural features of frontal lobe and temporal lobe can improve classification performance. In addition, the combination of behavioural performances and the features of brain structure is superior to the single-modality structural images on classification accuracy. However, the existing empirical studies classifying schizophrenia patients or high-risk population from controls are limited in sample size and generalization ability. " "