Login

 

Show simple item record

dc.contributor Gordon, V. Scott en_US
dc.contributor.advisor Muyan-Ozcelik, Pinar en_US
dc.contributor.author Shiroor, Shekhar Vikas
dc.date.accessioned 2019-01-11T23:05:49Z
dc.date.available 2019-01-11T23:05:49Z
dc.date.issued 2019-01-11
dc.date.submitted 2018-12-12
dc.identifier.uri http://hdl.handle.net/10211.3/207667
dc.description Project (M.S., Computer Science)--California State University, Sacramento, 2018. en_US
dc.description.abstract This project to implements a generalized neural network agent that plays different video games using reinforcement learning algorithm. This project uses OpenAIs simulated video game environment ‘gym’ for training and testing the proposed reinforcement learning algorithm solution. For training the neural network agent, different neural network models are used like Convolutional Neural Networks, Recurrent Neural Networks and combination of both. Python and TFlearn (Tensorflow backend) are used to implement the project. The results show that the proposed solution works well for an average of two to three games. However, performance of the solution is degraded when neural network is trained on four or more video games. Although using the ‘TopK’ metric (which is added to the proposed solution to increase the efficiency of neural network to play multiple video games) yields a dramatic increase in training and validation accuracy of the neural networks, the networks are still not able to play variety of video games with good degree of precision. To improve the performance, deeper neural network models like VGG-19 can be utilized in the future, given that hardware resources required by such models are available (e.g., a GPU with a larger global memory is needed). en_US
dc.description.sponsorship Computer Science en_US
dc.language.iso en_US en_US
dc.subject Deep learning en_US
dc.subject OpenAI en_US
dc.subject Reinforcement learning en_US
dc.subject Tensorflow en_US
dc.subject TFLearn en_US
dc.subject NumPy en_US
dc.subject LSTM en_US
dc.title Implementation of a neural network agent that plays video games using reinforcement learning en_US
dc.type Project en_US


Files in this item

Icon

This item appears in the following Collection(s)

Show simple item record

Search DSpace


My Account

RSS Feeds