RLtoolbox Function

Iter_Policy_Improv - Search an optimal policy.

Calling Sequence

[Pi,V,T_V,T_Pi]=Iter_Policy_Improvement(NbStates, NbActions, TransProb, Rewards, Gamma, Actions_States)

Parameters

Description

Search an optimal policy for the environnment described by the others parameters.

Examples

See Also

Value_Iteration