Deep Learning Approach Towards T-Rex Game
DOI:
https://doi.org/10.26438/ijcse/v8i9.2427Keywords:
Deep reinforcement, Sensory inputAbstract
In this project, we enforce both feature-extraction based totally algorithms and an end-to-cease deep reinforcement mastering technique to discover ways to control Chrome offline dinosaur recreation directly from high- dimensional sport display input. Results display that as compared with the pixel function based totally algorithms, deep reinforcement learning is more effective and effective. It leverages the high-dimensional sensory input immediately and avoids capability errors in characteristic extraction. Finally, we recommend special schooling strategies to address class imbalance issues due to the boom in game velocity. A simple and smooth GUI is supplied for smooth gameplay. The gameplay layout is so simple that user won’t discover it tough to use and understand. Different images are used within the development of this easy recreation project, the gaming environment is similar to the authentic T-Rex Dino Run sport. In order to run the project, you need to have set up python and pygame in your PC. This might be a new word for many however each and every one of us has learned to stroll the usage of the idea of Reinforcement Learning (RL) and this is how our brain still works. A reward gadget is a foundation for any RL algorithm.
References
[1]https://thenextweb.com/dd/2018/09/07/4-years-later-google finally-explains-the-origins-ofits-chrome-dinosaur-game/
[2]V. Mnih, K. Kavukcuoglu, D. Silver, A. Graves, IAntonoglou, D. Riedmiller. Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602, 2013.
[3] V. Mnih, K. Kavukcuoglu, D. Silver, A. A. Rusu, J. Veness, M. G. Bellemare, A. Graves, M.Riedmiller, A. K. Fidjeland, G. Ostrovski, et al. Human-level control through deep reinforcementlearning. Nature, 518(7540):529–533, 2015.
[4] G. Tesauro. Temporal difference learning and td-gammon. Communications of the ACM,38(3):58–68, 1995.
[5] G. Bradski et al. The opencv library. Doctor Dobb Journal, 25(11):120–126, 2000.
[6] Koray Kayabol, Member, IEEE ”Histogram-Based Contextual Classification of SAR Images”, IEEE geoscience and remote sensing letters, vol. 12, no. 1, January 2015.
[7] Xin Su, Chu He, Member, IEEE, Qian Feng, Xinping Deng, and Hong Sun, Member, IEEE "A Supervised Classification Method Based on Conditional Random Fields With Multiscale Region Connection Calculus Model for SAR Image",IEEE geoscience and remote sensing letters, vol. 8, no. 3, May 2011.
[8] Mery Picco and Gabriela Palacio "Unsupervised Classification of SAR Images Using Markov Random Fields and G0 I Model",IEEE geoscience and remote sensing letters, vol. 8, no. 2, March 2011.
[9] A. Sharma, P.K. Misra, “Aspects of enhancing security in software development life cycle,” Advances in Computational Sciences and Technology, Vol. 10, Issue. 2, pp. 203-210.
[10] Jr. Padal, C.M. Salado, L. Mary Jean May, N.P. Sobejana, “SPAMAST Smart Garbage Bin Monitoring System Using Wireless Sensor Network,” Journal of Engineering Research and Reports, pp. 1-16, 2019.
[11] D. Goel, R. Upadhyay, “Effectiveness of use of Animation in Advertising: A Literature Review,” International Journal of Scientific Research in Network Security and Communication, Vol.5, Issue. 3, pp. 146-159, 2017.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
