ε-first policies for budget-limited multi-armed bandits

Proceedings of the National Conference on Artificial Intelligence

Volumn 2, Issue , 2010, Pages 1211-1216

  Tran Thanh, Long ^a   Chapman, Archie ^a   De Cote, Enrique Munoz ^a   Rogers, Alex ^a   Jennings, Nicholas R ^a  

^a UNIVERSITY OF SOUTHAMPTON   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE;

ALGORITHM FOR SOLVING; DERIVE BOUNDS; FIXED BUDGET; MULTI ARMED BANDIT; NEW APPROACHES; OPTIMAL COMBINATION; OPTIMAL EXPLOITATION; UNIFORM EXPLORATIONS;

BUDGET CONTROL;

EID: 77958583895     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (9)

1. Andonov, R.; Poirriez, V.; and Rajopadhye, S. 2000. Unbounded knapsack problem: dynamic programming revisited. European Journal of Operational Research 123(2):394-407.
2. Antos, A.; Grover, V.; and Szepesvari, C. 2008. Active learning in multi-armed bandits. In Proc. of 19th Int. Conf. on Algorithmic Learning Theory 287-302.
3. Auer, P.; Cesa-Bianchi, N.; and Fischer, P. 2002. Finite-time analysis of the multiarmed bandit problem. Machine Learning 47:235-256.
4. Bubeck, S.; Munos, R.; and Stoltz, G. 2009. Pure exploration for multi-armed bandit problems. Algorithmic Learning Theory 23-37.
5. Cicirello, V. A., and Smith, S. F. 2005. The max k-armed bandit: a new model of exploration applied to search heuristic selection. In Proc. of AAAI'05 1355-1361.
6. Guha, S., and Munagala, K. 2007. Approximation algorithms for budgeted learning problems. Proc. of STOC'07 104-113.
7. Kohli, R.; Krishnamurti, R.; and Mirchandani, P. 2004. Average performance of greedy heuristics for the integer knapsack problem. European Journal of Operational Research 154(l):36-45.
8. Padhy, P.; Dash, R. K.; Martinez, K.; and Jennings, N. R. 2006. A utility-based sensing and communication model for a glacial sensor network. In Proc. of AAMAS'06 1353-1360.
9. Robbins, H. 1952. Some aspects of the sequential design of experiments. Bulletin of the AMS 55:527-535.