1. A survey of approximate methods for solving partially observable Markov decision processes;Aberdeen,2003
2. Anjum F, Subhadrabandhu D, Sarkar S, Shetty R, “On optimal placement of intrusion detection modules in sensor networks,” In: Proc. of the First International Conference on Broadband Networks, pp. 690–699, 2004.
3. Baras JS, Radosavac S, et al., “Intrusion Detection System Resiliency to Byzantine attacks: the case study of wormholes in OLSR,” In: Proc. of the IEEE Military Communications Conference 2007, pp. 1–7, Oct. 2007, Orlando, USA.
4. Direct gradient-based reinforcement learning: I. Gradiment estimation algorithms;Baxter,1999
5. Direct gradient-based reinforcement learning: II. Gradiment descent algorithms and experiments;Baxter,1999