PAC optimal exploration in continuous space Markov decision processes

Proceedings of the 27th AAAI Conference on Artificial Intelligence, AAAI 2013

Volumn , Issue , 2013, Pages 774-781

  Pazis, Jason ^a   Parr, Ronald ^a  

^a Duke University   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

CONTINUOUS SPACES; EXPLORATION ALGORITHMS; FINITE SAMPLES; GREEDY EXPLORATION; HEURISTIC APPROACH; MARKOV DECISION PROCESSES; THEORETICAL GUARANTEES; THEORY AND PRACTICE;

ARTIFICIAL INTELLIGENCE; HEURISTIC ALGORITHMS; HEURISTIC METHODS; MARKOV PROCESSES; SAMPLING;

OPTIMIZATION;

EID: 84893414333     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (17)

1. Adams, B.; Banks, H.; Kwon, H.-D.; and Tran, H. 2004. Dynamic multidrug therapies for HIV: Optimal and STI control approaches. In Mathematical Biosciences and Engineering, volume 1, 223-241.
2. Brunskill, E.; Leffler, B.; Li, L.; Littman, M.; and Roy, N. 2009. Provably efficient learning with typed parametric models. The Journal of Machine Learning Research 10:1955-1988.
3. Busoniu, L.; Munos, R.; Schutter, B. D.; and Babuska, R. 2011. Optimistic planning for sparsely stochastic systems. In IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning.
4. Ernst, D.; Stan, G.-B.; Goncalves, J.; and Wehenkel, L. 2006. Clinical data based optimal STI strategies for HIV; a reinforcement learning approach. In Machine Learning Conference of Belgium and The Netherlands (Benelearn), 65-72.
5. Jong, N., and Stone, P. 2007. Model-based exploration in continuous state spaces. Abstraction, Reformulation, and Approximation 258-272.
6. Kakade, S.; Kearns, M. J.; and Langford, J. 2003. Exploration in metric state spaces. In ICML, 306-312.
7. Kakade, S. M. 2003. On the sample complexity of reinforcement learning. Ph.D. Dissertation, Gatsby Computational Neuroscience Unit, University College London.
8. Kearns, M. J., and Singh, S. P. 2002. Near-optimal reinforcement learning in polynomial time. Machine Learning 49(2-3):209-232.
9. Kolter, J. Z., and Ng, A. Y. 2009. Near-bayesian exploration in polynomial time. In ICML '09, 513-520.
10. Li, L. 2009. A unifying framework for computational reinforcement learning theory. Ph.D. Dissertation, Rutgers University, New Brunswick, NJ, USA. AAI3386797.
11. Moldovan, T. M., and Abbeel, P. 2012. Safe exploration in Markov decision processes. CoRR abs/1205.4810.
12. Nouri, A., and Littman, M. 2008. Multi-resolution exploration in continuous spaces. Advances in neural information processing systems 21:1209-1216.
13. Strehl, A. L., and Littman, M. L. 2005. A theoretical analysis of model-based interval estimation. In ICML '05, 856-863. New York, NY, USA: ACM.
14. Strehl, A., and Littman, M. 2008. Online linear regression and its application to model-based reinforcement learning. Advances in Neural Information Processing Systems 20:1417-1424.
15. Strehl, A. L.; Li, L.; Wiewiora, E.; Langford, J.; and Littman, M. L. 2006. PAC model-free reinforcement learning. In ICML, 881-888.
16. Szita, I., and Szepesvári, C. 2010. Model-based reinforcement learning with nearly tight exploration complexity bounds. In ICML, 1031-1038.
17. Williams, R., and Baird, L. 1993. Tight performance bounds on greedy policies based on imperfect value functions. Technical report, Northeastern University, College of Computer Science.