He Qiming, Shayman M. A., (1999), Using Reinforcement Learning for Proactive Network Fault Management, ISR Technical Report, UMCP. Home/Search Document Details and Download
Summary Related Articles |
This paper is cited in the following contexts:
Solving POMDP by On-Policy Linear Approximate Learning Algorithm - He, Shayman (1999) (2 citations) (Correct)
....also obtained the policy for the simulator which can be used as a jump starter to supply the next phase. In the execution phase where the state cannot be observed completely, the belief is updated by previously estimated model and policy is thus fine tuned. A pseudo code procedure is reported in [9]. 3.2 Performance In order to measure the performances, we build a tester which can execute greedy policies derived from both exact algorithm and our algorithm referred as FastRL . Average discounted reward (ADR) and steps togoal (STG) are two metrics to measure Fast RL vs. the exact ....
He Qiming, Shayman M. A., (1999), Using Reinforcement Learning for Proactive Network Fault Management, ISR Technical Report, UMCP.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC