Index

_

__copy__() (lspi.policy.Policy method)

__repr__() (lspi.sample.Sample method)

A

action_name() (lspi.domains.ChainDomain method) (lspi.domains.Domain method)

apply_action() (lspi.domains.ChainDomain method) (lspi.domains.Domain method)

B

BasisFunction (class in lspi.basis_functions)

best_action() (lspi.policy.Policy method)

C

calc_q_value() (lspi.policy.Policy method) ChainDomain (class in lspi.domains)

ChainDomain.RewardLocation (class in lspi.domains) current_state() (lspi.domains.ChainDomain method) (lspi.domains.Domain method)

D

Domain (class in lspi.domains)

E

Ends (lspi.domains.ChainDomain.RewardLocation attribute) evaluate() (lspi.basis_functions.BasisFunction method) (lspi.basis_functions.ExactBasis method) (lspi.basis_functions.FakeBasis method) (lspi.basis_functions.OneDimensionalPolynomialBasis method) (lspi.basis_functions.RadialBasisFunction method)

ExactBasis (class in lspi.basis_functions)

F

FakeBasis (class in lspi.basis_functions)

FirstWins (lspi.policy.Policy.TieBreakingStrategy attribute)

G

get_state_action_index() (lspi.basis_functions.ExactBasis method)

H

HalfMiddles (lspi.domains.ChainDomain.RewardLocation attribute)

L

LastWins (lspi.policy.Policy.TieBreakingStrategy attribute) learn() (in module lspi.lspi) lspi (module) lspi.basis_functions (module) lspi.domains (module)

lspi.lspi (module) lspi.policy (module) lspi.sample (module) lspi.solvers (module) LSTDQSolver (class in lspi.solvers)

M

Middle (lspi.domains.ChainDomain.RewardLocation attribute)

N

num_actions (lspi.basis_functions.BasisFunction attribute) (lspi.basis_functions.ExactBasis attribute) (lspi.basis_functions.FakeBasis attribute) (lspi.basis_functions.OneDimensionalPolynomialBasis attribute) (lspi.basis_functions.RadialBasisFunction attribute) (lspi.policy.Policy attribute)

num_actions() (lspi.domains.ChainDomain method) (lspi.domains.Domain method)

O

OneDimensionalPolynomialBasis (class in lspi.basis_functions)

P

Policy (class in lspi.policy)

Policy.TieBreakingStrategy (class in lspi.policy)

R

RadialBasisFunction (class in lspi.basis_functions) random() (in module lspi.domains)

RandomWins (lspi.policy.Policy.TieBreakingStrategy attribute) reset() (lspi.domains.ChainDomain method) (lspi.domains.Domain method)

S

Sample (class in lspi.sample) select_action() (lspi.policy.Policy method) size() (lspi.basis_functions.BasisFunction method) (lspi.basis_functions.ExactBasis method) (lspi.basis_functions.FakeBasis method) (lspi.basis_functions.OneDimensionalPolynomialBasis method) (lspi.basis_functions.RadialBasisFunction method)

solve() (lspi.solvers.LSTDQSolver method) (lspi.solvers.Solver method) Solver (class in lspi.solvers)