Call for Paper - March 2023 Edition
IJCA solicits original research papers for the March 2023 Edition. Last date of manuscript submission is February 20, 2023. Read More

Playing Doom with Deep Reinforcement Learning

Print
PDF
IJCA Proceedings on International Conference on Recent Trends in Science, Technology, Management and Social Development
© 2019 by IJCA Journal
ICRTSTMSD 2018 - Number 1
Year of Publication: 2019
Authors:
Manan Kalra
J. C. Patni

Manan Kalra and J C Patni. Article: Playing Doom with Deep Reinforcement Learning. IJCA Proceedings on International Conference on Recent Trends in Science, Technology, Management and Social Development ICRTSTMSD 2018(1):14-20, August 2019. Full text available. BibTeX

@article{key:article,
	author = {Manan Kalra and J. C. Patni},
	title = {Article: Playing Doom with Deep Reinforcement Learning},
	journal = {IJCA Proceedings on International Conference on Recent Trends in Science, Technology, Management and Social Development},
	year = {2019},
	volume = {ICRTSTMSD 2018},
	number = {1},
	pages = {14-20},
	month = {August},
	note = {Full text available}
}

Abstract

In this work, we present a deep learning model based on reinforcement learning that is tied to an AI agent. The agent successfully learns policies to control itself in a virtual game environment directly from high-dimensional sensory inputs. The model is a convolutional neural network, trained with a variant of the Q-learning algorithm, whose input is raw pixels and whose output is a Q-value directly associated with the best possible future action. We apply our method to a first-person shooting game - Doom. We find that it outperforms all previous approaches and also surpasses a human expert.

References

  • Sutton, R. S. & Bartro, A. G. (1998). Introduction to Reinforcement Learning. Cambridge, MA: MIT Press.
  • Bellman, R. E (1957). Dynamic Programming. , Princeton, New Jersey: Princeton University Press.
  • Bellemare M. G. , Naddaf, Y. , Veness, J. & Bowling M. (2013). The arcade learning environment: An evaluation platform for general agents. Journal of Artificial Intelligence Research, 47:253–279.
  • Bellemare, M. G. , Veness, J. & Bowling, M. (2012). Investigating contingency awareness using atari 2600 games. In AAAI.
  • Silver, D. (2016). Deep Reinforcement Learning. DeepMind Technologies.
  • Krizhevsky, A. , Sutskever, I. & Hinton, G. (2012). Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems 25, pages 1106–1114.
  • White, D. J. (1993, November). A Survey of Applications of Markov Decision Processes. The Journal of the Operational Research Society, Vol. 44, No. 11, pp. 1073-1096.