文件名称:fast_rl_comm_matlab
介绍说明－－下载内容均来自于网络，请自行研究使用
To understand how the Q-learning algorithm works, we ll go through a few episodes step by step. The rest of the steps are illustrated in the source code examples
(系统自动生成,下载前可以参看下载内容)
下载文件列表
valueIter.m
alphaSchedule.m
approxeq.m
batch_constraint_nonstationary.m
batch_initArrRate_stationary.m
batch_virtual_experience_learning_experiments.m
BEP2PLR.m
betaSchedule.m
calcAfterstateValueFunction.m
calcDelayPowerPoint.m
calcOperatingPoint.m
calcStationaryDistr.m
constrainedPolicyIter.m
createNonstationaryDynamics.m
cumavg.m
epsilonSchedule.m
experiment_k_buffer.m
experiment_PDSlearning.m
experiment_Qlearning.m
getBeta.m
getSimStruct.m
getSNR.m
getTxPower.m
keep.m
main.m
parameters.m
PDSvalueIter.m
plots_constraint_nonstationary.m
plots_initArrRate.m
PLR2BEP.m
policy_iteration.m
populate_kpolicy.m
populateArrivalDistr.m
populateBufferCost.m
populateBufferTPF.m
populateChannelTPF.m
populateCost.m
populateDepartureDistr.m
populateKnownCost.m
populateKnownTPF.m
populatePowerCost.m
populatePowerManageTPF.m
populateStateTPF.m
populateUnknownCost.m
populateUnknownTPF.m
Q_from_V.m
rando.m
separatePolicies.m
test.m
testFiniteHorizon.m
tuneChannel.m
updateArrivalRate.m
updatePDSV.m
updateQ.m
updateT_h.m
value_determination.m