Model-based relational RL when object existence is partially observable

31st International Conference on Machine Learning, ICML 2014

Volumn 3, Issue , 2014, Pages 1955-1963

  Vien, Ngo Anh ^a   Toussaint, Marc ^a  

^a UNIVERSITY OF STUTTGART   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE;

BELIEF SPACE; COMPUTATIONALLY EFFICIENT; OPTIMAL POLICIES; PROBABILISTIC RULES;

LEARNING SYSTEMS;

EID: 84919905597     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (18)

1. Amir, Eyal. Learning partially observable deterministic action models. In IJCAI, pp. 1433-1439, 2005.
2. Blum, Avrim and Langford, John. Probabilistic planning in the graphplan framework. In ECP, pp. 319-332, 1999.
3. Carbonetto, Peter, Kisynski, Jacek, de Freitas, Nando, and Poole, David. Nonparametric Bayesian logic. In UAI, pp. 85-93, 2005.
4. Dietterich, Thomas G., Domingos, Pedro, Getoor, Lise, Muggleton, Stephen, and Tadepalli, Prasad. Structured machine learning: The next ten years. Machine Learning, 73(1):3-23, 2008.
5. Goodman, Noah D., Mansinghka, Vikash K., Roy, Daniel M., Bonawitz, Keith, and Tenenbaum, Joshua B. Church: A language for generative models. In UAI, pp. 220-229, 2008.
6. Kearns, Michael J., Mansour, Yishay, and Ng, Andrew Y. A sparse sampling algorithm for near-optimal planning in large markov decision processes. Machine Learning, 49(2-3): 193-208, 2002.
7. Kocsis, Levente and Szepesvari, Csaba. Bandit based monte-carlo planning. In ECML, pp. 282-293, 2006.
8. Kurniawati, Hanna, Hsu, David, and Lee, Wee Sun. Sarsop: Efficient point-based pomdp planning by approximating optimally reachable belief spaces. In Robotics: Science and Systems, 2008.
9. Lang, Tobias and Toussaint, Marc. Planning with noisy probabilistic relational rules. Journal of Artificial Intelligence Research, 39:1-49, 2010.
10. Milch, Brian, Marthi, Bhaskara, Russell, Stuart J., Sontag, David, Ong, Daniel L., and Kolobov, Andrey. BLOG: Probabilistic models with unknown objects. In IJCAI, pp. 1352-1359, 2005.
11. Pasula, Hanna M., Zettlemoyer, Luke S., and Kaelbling, Leslie Pack. Learning symbolic models of stochastic domains. J. Artif. Intell. Res. (JAIR), 29:309-352, 2007.
12. Sagiv, Shmuel, Reps, Thomas W., and Wilhelm, Reinhard. Parametric shape analysis via 3-valued logic. ACM Trans. Program. Lang. Syst., 24(3):217-298, 2002.
13. Sanner, Scott and Kersting, Kristian. Symbolic dynamic programming for first-order pomdps. In AAAI, 2010.
14. Smallwood, Richard D. and Sondik, Edward J. The Optimal Control of Partially Observable Markov Processes Over a Finite Horizon. Operations Research, 21(5): 1071-1088, 1973.
15. Srivastava, Siddharth, Immerman, Neil, and Zilberstein, Shlomo. Abstract planning with unknown object quantities and properties. In SARA, 2009.
16. Vien, Ngo Anh and Toussaint, Marc. Reasoning with uncertainties over existence of objects. In AAAI Fall Symposium: How Should Intelligence Be Abstracted in AI Research?, 2013.
17. Walsh, Thomas J. Efficient learning of relational models for sequential decision making. PhD thesis, The State University of New Jersey, 2010.
18. Wang, Chenggang and Khardon, Roni. Relational partially observable mdps. In AAAI, 2010.