Value

PURPOSE

SYNOPSIS

DESCRIPTION

   Evaluation of a Gaussian.

   Returns the evaluation of a Gaussian on a given set of points, 'x'.

CROSS-REFERENCE INFORMATION

• size Returns the size of a policy.

• DiscretizeActionModel Produces a new action model discretizing the state space.
• DiscretizeActionModel Generates a new action model discretizing the action space of the given model.
• GetActionModelFixedA Returns the action model for a given action.
• Expectation Expectation between a belief and a alpha-element.
• Update Belief evolution under an observation model.
• ComponentsValue Evaluates a Gaussian mixture component-wise.
• ProductInt Product and marginalization of two GMixtures.
• Value Evaluates a GMixture.
• plot Plots a Gaussian mixture.
• ProductNormFactor Normalization constant of the product of two Gaussians.
• plot Plots a Gaussian.
• CS_CO_ObsModel CS_CO_ObsModel constructor.
• GetObsModelFixedO Defines p(o|s) for a fixed 'o'.
• GetObsModelFixedS Defines p(o|s) for a fixed 's'.
• plot Plots the CS_CO_ObsModel
• CS_DO_ObsModel CS_DO_ObsModel constructor.
• DiscretizeObsModel Discretizes the observation model on the state side.
• GetObsModelFixedS Defines p(o|s)
• GetObsModelFixedO Defines p(s|o).
• Perseus The Perseus point-based POMDP solver.
• iPerseus Improved version of Perseus.
• DiscretizeRewardModel Discretizes the reward model on the action side.
• GetRewardModelFixedA Defines the reward function for a given action.
• Reward Evaluates the reward function.
• plot Plots the CS_CA_RewardModel
• DiscretizeRewardModel Discretizes the reward model on the state side.
• Reward Evaluates the reward function.
• GetRewardModelFixedA Defines the reward function for a given action.
• Reward Evaluates the reward function.
• UniformDistribution Uniform probability on a continuous space.

SOURCE CODE

0001 function v=Value(g,x)
0002 %   Evaluation of a Gaussian.
0003 %
0004 %   Returns the evaluation of a Gaussian on a given set of points, 'x'.
0005 
0006   l=size(x,2);
0007   Sn=-0.5*g.iS;
0008 
0009   v=zeros(1,l);
0010   for i=1:l
0011     m=x(:,i)-g.m;
0012     v(i)=g.ct*exp(m'*Sn*m);
0013   end
0014