A reinforcement learning framework for dynamic resource allocation: First results

Proceedings - Second International Conference on Autonomic Computing, ICAC 2005

Volumn 2005, Issue , 2005, Pages 339-340

  Vengerov, David ^a   Iakovlev, Nikolai ^a  

^a SUN MICROSYSTEMS   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

CPU MIGRATION COSTS; FUNCTION APPROXIMATION ARCHITECTURES; NEAR-OPTIMAL PERFORMANCE;

APPROXIMATION THEORY; COMPUTER ARCHITECTURE; PROGRAM PROCESSORS; RESOURCE ALLOCATION; ROBUSTNESS (CONTROL SYSTEMS); SET THEORY;

LEARNING SYSTEMS;

EID: 33745504762     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICAC.2005.4     Document Type: Conference Paper

References (4)

1. D. Bertsekas and J. Tsitsiklis, Neuro-Dynamic Programming, Athena Scientific, 1996.
2. G. Tesauro, "RL-Based Online Resource Allocation in Multi-Workload Computing Systems," Presentation at AAAI Fall Symposium on Real-Life Reinforcement Learning, Washington DC, Oct. 22, 2004.
3. J. N. Tsitsiklis and B. Van Roy, "An Analysis of Temporal-Difference Learning with Function Approximation," IEEE Transactions on Automatic Control, Vol. 42, No. 5, May 1997, pp. 674-690.
4. D. Vengerov, Multi-Agent Learning and Coordination Algorithms for Distributed Dynamic Resource Allocation. Ph.D. Dissertation, Department of Management Science and Engineering, Stanford University, March 2004. Available electronically at http://research.sun.com/people/vengerov/dissertation.pdf