API for markdumke/reinforceR
Reinforcement Learning

Global functions
CliffWalking Man page
Eligibility Man page
Environment Man page
EpsilonGreedyPolicy Man page
GreedyPolicy Man page
Gridworld Man page
GymEnvironment Man page
MdpEnvironment Man page
MountainCar Man page
MountainCarContinuous Man page
MountainCarContinuous, Man page
Policy Man page
QLearning Man page
RandomPolicy Man page
SoftmaxPolicy Man page
ValueNetwork Man page
ValueTable Man page
WindyGridworld Man page
applyWind Source code
cliff.walking Man page
eligibility Man page
experience.replay, Man page
extractBoxInfo Source code
extractDiscreteInfo Source code
extractSpaceClass Source code
fillTarget Source code
getEligibilityTraces Man page Source code
getIntoBounds Source code
getReplayMemory Man page Source code
getStateValues Man page Source code
getValueFunction Man page Source code
go Source code
go.down Source code
go.left Source code
go.leftdown Source code
go.leftup Source code
go.right Source code
go.rightdown Source code
go.rightup Source code
go.up Source code
hashcoords Source code
iht Man page Source code
interact Man page Source code
makeAgent Man page Source code
makeAlgorithm Man page Source code
makeEnvironment Man page Source code
makePolicy Man page Source code
makeReplayMemory Man page Source code
makeRewardMatrix Source code
makeValueFunction Man page Source code
mountain.car Man page
nHot Man page Source code
neural.network Man page
qlearning Man page
reinforcelearn Man page
reinforcelearn-package Man page
reinforcementlearning Man page
replay.memory Man page
table Man page
tiles Man page Source code
visualizeGridworld Source code
windy.gridworld Man page
markdumke/reinforceR documentation built on Nov. 17, 2022, 12:53 a.m.