Obtenção dos compromissos Meta versus Custo em Processos Markovianos de Decisão
Resumo
Processos Markovianos de Decisão modelam problemas de atingir uma meta com menor custo possível. Nesse trabalho estuda-se o compromisso entre probabilidade de chegar à meta e o custo médio incorrido.Referências
Bertsekas, D. P. and Tsitsiklis, J. N. (1991). An analysis of stochastic shortest path problems. Mathematics of Operations Research, 16(3):580–595.
Freire, V. and Delgado, K. V. (2017). Gubs: a utility-based semantic for goal-directed In Proceedings of the 16th Conference on Autonomous markov decision processes. Agents and MultiAgent Systems, pages 741–749.
Freire, V., Delgado, K. V., and Reis, W. A. S. (2019). An exact algorithm to make a In Proceedings of the Twenty-Ninth trade-off between cost and probability in ssps. International Conference on Automated Planning and Scheduling, pages 146–154.
Mausam and Kolobov, A. (2012). Planning with markov decision processes: An ai perspective. Synthesis Lectures on Articial Intelligence and Machine Learning, 6(1).
Silva, V. F. d. and Costa, A. H. R. (2011). A geometric approach to nd nondominated policies to imprecise reward mdps. In Proceedings of the 2011 European Conference on Machine Learning and Knowledge Discovery in Databases, pages 439–454.
Silva, V. F. d., Costa, A. H. R., and Lima, P. (2006). Inverse reinforcement learning with evaluation. In IEEE International Conference on Robotics and Automation (ICRA'06), pages 4246–4251, Orlando, FL. IEEE.
Trevizan, F., Teichteil-Königsbuch, F., and Thiébaux, S. (2017). Efcient solutions for stochastic shortest path problems with dead ends. In Proceedings of the Thirty-Third Conference on Uncertainty in Articial Intelligence (UAI).
Freire, V. and Delgado, K. V. (2017). Gubs: a utility-based semantic for goal-directed In Proceedings of the 16th Conference on Autonomous markov decision processes. Agents and MultiAgent Systems, pages 741–749.
Freire, V., Delgado, K. V., and Reis, W. A. S. (2019). An exact algorithm to make a In Proceedings of the Twenty-Ninth trade-off between cost and probability in ssps. International Conference on Automated Planning and Scheduling, pages 146–154.
Mausam and Kolobov, A. (2012). Planning with markov decision processes: An ai perspective. Synthesis Lectures on Articial Intelligence and Machine Learning, 6(1).
Silva, V. F. d. and Costa, A. H. R. (2011). A geometric approach to nd nondominated policies to imprecise reward mdps. In Proceedings of the 2011 European Conference on Machine Learning and Knowledge Discovery in Databases, pages 439–454.
Silva, V. F. d., Costa, A. H. R., and Lima, P. (2006). Inverse reinforcement learning with evaluation. In IEEE International Conference on Robotics and Automation (ICRA'06), pages 4246–4251, Orlando, FL. IEEE.
Trevizan, F., Teichteil-Königsbuch, F., and Thiébaux, S. (2017). Efcient solutions for stochastic shortest path problems with dead ends. In Proceedings of the Thirty-Third Conference on Uncertainty in Articial Intelligence (UAI).
Publicado
19/08/2020
Como Citar
KUO, Isabella; FREIRE, Valdinei.
Obtenção dos compromissos Meta versus Custo em Processos Markovianos de Decisão. In: ESCOLA REGIONAL DE APRENDIZADO DE MÁQUINA E INTELIGÊNCIA ARTIFICIAL DE SÃO PAULO, 1. , 2020, São Paulo.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2020
.
p. 26-29.
