Object-oriented representation and hierarchical reinforcement learning in infinite Mario

Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI

Volumn 1, Issue , 2012, Pages 1076-1081

  Joshi, Mandar ^a   Khobragade, Rakesh ^a   Sarda, Saurabh ^a   Deshpande, Umesh ^a   Mohan, Shiwali ^b  

^a VISVESVARAYA NATIONAL INSTITUTE OF TECHNOLOGY   (India)

^b UNIVERSITY OF MICHIGAN   (United States)

Author keywords

action games; action selection; hierarchical reinforcement learning; object oriented representation

Indexed keywords

ACTION GAMES; ACTION SELECTION; DOMAIN-SPECIFIC KNOWLEDGE; EFFICIENT LEARNING; HIERARCHICAL REINFORCEMENT LEARNING; LEARNING FRAMEWORKS; OBJECT-ORIENTED REPRESENTATION; REINFORCEMENT LEARNING TECHNIQUES;

ARTIFICIAL INTELLIGENCE;

REINFORCEMENT LEARNING;

EID: 84876838136     PISSN: 10823409     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICTAI.2012.152     Document Type: Conference Paper

References (13)

1. B. Tanner and A. White, "RL-Glue: Language-indepenent software for reinforcement learning experiments," The Journal of Machine Learning Research, vol. 10, pp. 2133-2136, September 2009.
2. R. Sutton and A. Barto, Introduction to reinforcement learning, 1st Edition ed., MIT Press, 1998.
3. T. G. Dietterich, "The MAXQ method for hierarchical reinforcement learning," in the Fifteenth International Conference on Machine Learning, 1998.
4. R. S. Sutton, D. Precup and S. Singh, "Between MDPs and semi-MDPs: a framework for temporal abstraction in reinforcement learning," Artificial Intelligence, vol. 112, pp. 181-211, 1999.
5. R. Parr and S. Russell, "Reinforcement learning with hierarchies of machines," in Advances in Neural Information Processing Systems [NIPS-97], 1997.
6. A. G. Barto and S. Mahadevan, "Recent advances in hierarchical reinforcement learning," in Discrete Events Dynamic Systems: Theory and Applications, 2003.
7. J. Laird and M. van Lent, "Human-Level AI's Killer Application: Interactive Computer Games," in the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence, 2000.
8. K. Driessens, "Relational reinforcement learning," 2004.
9. B. Marthi, S. Russell, D. Latham and C. Guestrin, "Concurrent hierarchical reinforcement learning.," in The 20th National Conference on Artificial Intelligence, 2005.
10. M. Ponsen, P. Spronck and K. Tuyls, "Hierarchical reinforcement learning with diectic representation in a computer game," in the 18th Belgium-Netherlands Conference on Artificial Intelligence, 2006.
11. C. Diuk, A. Cohen and M. Littman, "An object oriented representation for efficient reinforcement learning," in the 25th International Conference on Machine Learning, 2008.
12. S. Mohan and J. Laird, "An object-oreiented approach to reinforcement learning in an action game," in the 7th Artificial Intelligence for Interactive Digital Entertainment Conference, 2011.
13. G. Rummery and M. Niranjan, "Online Q-Learning using connectionist systems," 1994. [Online]. Available: http://2009.rl-competition.org/mario. php.