publication . Conference object . Preprint . Other literature type . 2016

ViZDoom: A Doom-based AI research platform for visual reinforcement learning

Kempka, Michal; Wydmuch, Marek; Runc, Grzegorz; Toczek, Jakub; Jaskowski, Wojciech;
Open Access
  • Published: 06 May 2016
  • Publisher: IEEE
Abstract
The recent advances in deep neural networks have led to effective vision-based reinforcement learning methods that have been employed to obtain human-level controllers in Atari 2600 games from pixel data. Atari 2600 games, however, do not resemble real-world tasks since they involve non-realistic 2D environments and the third-person perspective. Here, we propose a novel test-bed platform for reinforcement learning research from raw visual information which employs the first-person perspective in a semi-realistic 3D world. The software, called ViZDoom, is based on the classical first-person shooter video game, Doom. It allows developing bots that play the game us...
Subjects
ACM Computing Classification System: ComputingMilieux_PERSONALCOMPUTING
free text keywords: Reinforcement learning, Machine learning, computer.software_genre, computer, Pixel, Computer science, Artificial intelligence, business.industry, business, Scenario, Visual learning, Software, Screen buffer, Visualization, Artificial neural network, Human–computer interaction, Computer Science - Learning, Computer Science - Artificial Intelligence, Computer Science - Computer Vision and Pattern Recognition
Related Organizations
27 references, page 1 of 2

[1] Zdoom wiki page. http://zdoom.org/wiki/Main Page. Accessed: 2016- 01-30.

[2] Minoru Asada, Shoichi Noda, Sukoya Tawaratsumida, and Koh Hosoda. Purposive behavior acquisition for a real robot by vision-based reinforcement learning. In Recent Advances in Robot Learning, pages 163-187. Springer, 1996.

[3] Minoru Asada, Eiji Uchibe, Shoichi Noda, Sukoya Tawaratsumida, and Koh Hosoda. A vision-based reinforcement learning for coordination of soccer playing behaviors. In Proceedings of AAAI-94 Workshop on AI and A-life and Entertainment, pages 16-21, 1994. [OpenAIRE]

[4] Nicholas Cole, Sushil J Louis, and Chris Miles. Using a genetic algorithm to tune first-person shooter bots. In Evolutionary Computation, 2004. CEC2004. Congress on, volume 1, pages 139-145. IEEE, 2004.

[5] Giuseppe Cuccu, Matthew Luciw, Ju¨rgen Schmidhuber, and Faustino Gomez. Intrinsically motivated neuroevolution for vision-based reinforcement learning. In Development and Learning (ICDL), 2011 IEEE International Conference on, volume 2, pages 1-7. IEEE, 2011.

[6] Mark Dawes and Richard Hall. Towards using first-person shooter computer games as an artificial intelligence testbed. In KnowledgeBased Intelligent Information and Engineering Systems, pages 276-282. Springer, 2005.

[7] Abdennour El Rhalibi and Madjid Merabti. A hybrid fuzzy ANN system for agent adaptation in a first person shooter. International Journal of Computer Games Technology, 2008, 2008. [OpenAIRE]

[8] A I Esparcia-Alcazar, A Martinez-Garcia, A Mora, J J Merelo, and P Garcia-Sanchez. Controlling bots in a First Person Shooter game using genetic algorithms. In Evolutionary Computation (CEC), 2010 IEEE Congress on, pages 1-8, jul 2010.

[9] Chris Gaskett, Luke Fletcher, and Alexander Zelinsky. Reinforcement learning for a vision based mobile robot. In Intelligent Robots and Systems, 2000.(IROS 2000). Proceedings. 2000 IEEE/RSJ International Conference on, volume 1, pages 403-409. IEEE, 2000.

[10] Benjamin Geisler. An empirical study of machine learning algorithms applied to modeling player behavior in a first person shooter video game. PhD thesis, University of Wisconsin-Madison, 2002.

[11] F G Glavin and M G Madden. DRE-Bot: A hierarchical First Person Shooter bot using multiple Sarsa( ) reinforcement learners. In Computer Games (CGAMES), 2012 17th International Conference on, pages 148- 152, jul 2012.

[12] F G Glavin and M G Madden. Adaptive Shooting for Bots in First Person Shooter Games Using Reinforcement Learning. Computational Intelligence and AI in Games, IEEE Transactions on, 7(2):180-192, jun 2015.

[13] Xavier Glorot, Antoine Bordes, and Yoshua Bengio. Deep sparse rectifier neural networks. In Geoffrey J. Gordon and David B. Dunson, editors, Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics (AISTATS-11), volume 15, pages 315- 323. Journal of Machine Learning Research - Workshop and Conference Proceedings, 2011.

[14] S Hladky and V Bulitko. An evaluation of models for predicting opponent positions in first-person shooter video games. In Computational Intelligence and Games, 2008. CIG '08. IEEE Symposium On, pages 39-46, dec 2008.

[15] Igor V. Karpov, Jacob Schrum, and Risto Miikkulainen. Believable Bot Navigation via Playback of Human Traces, pages 151-170. Springer Berlin Heidelberg, 2012.

27 references, page 1 of 2
Abstract
The recent advances in deep neural networks have led to effective vision-based reinforcement learning methods that have been employed to obtain human-level controllers in Atari 2600 games from pixel data. Atari 2600 games, however, do not resemble real-world tasks since they involve non-realistic 2D environments and the third-person perspective. Here, we propose a novel test-bed platform for reinforcement learning research from raw visual information which employs the first-person perspective in a semi-realistic 3D world. The software, called ViZDoom, is based on the classical first-person shooter video game, Doom. It allows developing bots that play the game us...
Subjects
ACM Computing Classification System: ComputingMilieux_PERSONALCOMPUTING
free text keywords: Reinforcement learning, Machine learning, computer.software_genre, computer, Pixel, Computer science, Artificial intelligence, business.industry, business, Scenario, Visual learning, Software, Screen buffer, Visualization, Artificial neural network, Human–computer interaction, Computer Science - Learning, Computer Science - Artificial Intelligence, Computer Science - Computer Vision and Pattern Recognition
Related Organizations
27 references, page 1 of 2

[1] Zdoom wiki page. http://zdoom.org/wiki/Main Page. Accessed: 2016- 01-30.

[2] Minoru Asada, Shoichi Noda, Sukoya Tawaratsumida, and Koh Hosoda. Purposive behavior acquisition for a real robot by vision-based reinforcement learning. In Recent Advances in Robot Learning, pages 163-187. Springer, 1996.

[3] Minoru Asada, Eiji Uchibe, Shoichi Noda, Sukoya Tawaratsumida, and Koh Hosoda. A vision-based reinforcement learning for coordination of soccer playing behaviors. In Proceedings of AAAI-94 Workshop on AI and A-life and Entertainment, pages 16-21, 1994. [OpenAIRE]

[4] Nicholas Cole, Sushil J Louis, and Chris Miles. Using a genetic algorithm to tune first-person shooter bots. In Evolutionary Computation, 2004. CEC2004. Congress on, volume 1, pages 139-145. IEEE, 2004.

[5] Giuseppe Cuccu, Matthew Luciw, Ju¨rgen Schmidhuber, and Faustino Gomez. Intrinsically motivated neuroevolution for vision-based reinforcement learning. In Development and Learning (ICDL), 2011 IEEE International Conference on, volume 2, pages 1-7. IEEE, 2011.

[6] Mark Dawes and Richard Hall. Towards using first-person shooter computer games as an artificial intelligence testbed. In KnowledgeBased Intelligent Information and Engineering Systems, pages 276-282. Springer, 2005.

[7] Abdennour El Rhalibi and Madjid Merabti. A hybrid fuzzy ANN system for agent adaptation in a first person shooter. International Journal of Computer Games Technology, 2008, 2008. [OpenAIRE]

[8] A I Esparcia-Alcazar, A Martinez-Garcia, A Mora, J J Merelo, and P Garcia-Sanchez. Controlling bots in a First Person Shooter game using genetic algorithms. In Evolutionary Computation (CEC), 2010 IEEE Congress on, pages 1-8, jul 2010.

[9] Chris Gaskett, Luke Fletcher, and Alexander Zelinsky. Reinforcement learning for a vision based mobile robot. In Intelligent Robots and Systems, 2000.(IROS 2000). Proceedings. 2000 IEEE/RSJ International Conference on, volume 1, pages 403-409. IEEE, 2000.

[10] Benjamin Geisler. An empirical study of machine learning algorithms applied to modeling player behavior in a first person shooter video game. PhD thesis, University of Wisconsin-Madison, 2002.

[11] F G Glavin and M G Madden. DRE-Bot: A hierarchical First Person Shooter bot using multiple Sarsa( ) reinforcement learners. In Computer Games (CGAMES), 2012 17th International Conference on, pages 148- 152, jul 2012.

[12] F G Glavin and M G Madden. Adaptive Shooting for Bots in First Person Shooter Games Using Reinforcement Learning. Computational Intelligence and AI in Games, IEEE Transactions on, 7(2):180-192, jun 2015.

[13] Xavier Glorot, Antoine Bordes, and Yoshua Bengio. Deep sparse rectifier neural networks. In Geoffrey J. Gordon and David B. Dunson, editors, Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics (AISTATS-11), volume 15, pages 315- 323. Journal of Machine Learning Research - Workshop and Conference Proceedings, 2011.

[14] S Hladky and V Bulitko. An evaluation of models for predicting opponent positions in first-person shooter video games. In Computational Intelligence and Games, 2008. CIG '08. IEEE Symposium On, pages 39-46, dec 2008.

[15] Igor V. Karpov, Jacob Schrum, and Risto Miikkulainen. Believable Bot Navigation via Playback of Human Traces, pages 151-170. Springer Berlin Heidelberg, 2012.

27 references, page 1 of 2
Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue