An automated measure of MDP similarity for transfer in reinforcement learning

AAAI Workshop - Technical Report

Volumn WS-14-07, Issue , 2014, Pages 31-37

  Ammar, Haitham Bou ^a   Eaton, Eric ^a   Taylor, Mattliew E ^b   Mocanu, Decebal Constantin ^c   Driessens, Kurt ^d   Weiss, Gerhard ^d   Tüyls, Karl ^e  

^a UNIVERSITY OF PENNSYLVANIA   (United States)

^b WASHINGTON STATE UNIVERSITY   (United States)

^c EINDHOVEN UNIVERSITY OF TECHNOLOGY   (Netherlands)

^d MAASTRICHT UNIVERSITY   (Netherlands)

^e UNIVERSITY OF LIVERPOOL   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE; AUTONOMOUS AGENTS; LEARNING ALGORITHMS; LEARNING SYSTEMS; MARKOV PROCESSES;

BEHAVIORAL DYNAMICS; DATA DRIVEN; MARKOV DECISION PROCESSES; RECONSTRUCTION ERROR; RESTRICTED BOLTZMANN MACHINE; SIMILARITY MEASURE; TRANSFER LEARNING; TRANSFER LEARNING METHODS;

REINFORCEMENT LEARNING;

EID: 84974799118     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (14)

1. Ammar, H. B.; Taylor, M. E.; Tuyls, K.; Driessens. K.; and Weiss, G. 2012. Reinforcement learning transfer via sparse coding. In Proceedings of tììe 11th Conference on Autonomous Agents and Midtiagent Systems (AAMAS).
2. Ammar, H. B.; Mocanu, D. C; Taylor. M. E.; Driessens, K.; Weiss, G.; and Tuyls, K. 2013. Automatically mapped transfer between reinforcement learning tasks via three-way restricted Boltzmann machines. In Proceedings of the European Conference on Machine Learning (ECML).
3. Bengio, Y. 2009. Learning deep architectures for AI. Foundations and Trends in Machine Learning 2( 1 ): 1-127.
4. Buşoniu. L.; Babuška, R.; De Schutter. B.; and Ernst, D. 2010. Reinforcement Learning and Dynamic Programming Using Function Approximators. Boca Raton, Florida: CRC Press.
5. Ferns. N.; Castro, P. S.; Precup, D.: and Panangaden, P. 2006. Methods for computing state similarity in Markov decision processes. In Proceedings oftlie 22nd Conference on Uncertainty in Artificial Intelligence (UAI). 174-181.
6. Ferns, N.; Panangaden, P.; and Precup. D. 2011. Bisim-ulation metrics for continuous Markov decision processes. SIAM J. Computing 40(6): 1662-1714.
7. Hinton, G. E. 2002. Training products of experts by minimizing contrastive divergence. Neural Computation 14(8):1771-1800.
8. Salakhuldinov, R.; Mnih, A.; and Hinton, G. 2007. Restricted Boltzmann machines for collaborative fillering. In Proceedings of the 24th International Conference on Machine Learning (ICML), 791-798.
9. Taylor, M. E., and Stone, P 2009. Transfer learning for reinforcement learning domains: a survey. Journal of Machine Learning Research 10(1):163.3-1685.
10. Taylor, G. W.; Hinton, G. E.; and Roweis, S. T 2011. Two distributed-state models for generating high-dimensional time scries. Journal of Machine Learning Research 12:1025-1068.
11. Taylor. M. E.; .jong, N. K.; and Stone, P. 2008. Transferring instances for model-based reinforceinent learning. In the Adaptive Learning Agents and Multi-Agent Systems (ALA-MAS+ALAG) workshop at AAMAS.
12. Taylor. M. E.; Stone, P; and Liu, Y. 2007. Transfer learning via inter-task inappings for temporal difference learning. Journal of Machine Learning Research 8(1):2125-2167.
13. ToiTcy, L.; Shavlik. J. W.: Walker, T.; and Maclin, R. 2006. Skill acquisition via transfer learning and advice taking. In Proceedings of the European Conference on Machine Learning (ECML), 425-436.
14. Whiteson, S.; Tanner. B.; Taylor, M. E.; and Stone, P 2011. Protecting against evaluation overfitting in empirical reinforceinent learning. In the IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning.