SimulationStep
PURPOSE 
Executes one step of a POMDP simulation.
SYNOPSIS
function [s b o r]=SimulationStep(P,b,s,a)
DESCRIPTION
Executes one step of a POMDP simulation.
It updates the belief using the corresponding Prediction method and the
given action and then corrects the belief using the corresponding
Update method.
The implementation of both the Prediction and Update methods are
dependant on the nature of the beliefs.
Parameters:
P: The POMDP.
b: The belief to update.
s: The hidden state (used to query the observation and reward models)
a: The action to execute.
Outputs:
s: The new hidden state.
b: The new belief.
o: The observation used in the Update.
r: The reward obtained in the new attained (hidden) state.
See also DBelief, GBelief, PBelief, SimulateFrom.CROSS-REFERENCE INFORMATION
This function calls:
- Prediction Belief evolution under the given action.
- Prediction Belief evolution under the given action.
- Prediction Belief evolution under the given action.
- Prediction Belief evolution under the given action.
- Prediction Belief evolution given a transition model.
- Update Belief evolution under an observation model.
- rand Random state from a discrete belief.
- Prediction Belief evolution given a transition model.
- Update Belief evolution under an observation model.
- get Get for GBeliefs.
- Prediction Belief evolution given a transition model.
- Update Belief evolution under an observation model.
- rand Random state from a belief.
- get Get function for the GMixture object.
- rand Generates random points on a GMixture.
- get Gaussian object get function.
- rand Generates random ponts on a Gaussian.
- RandVector Selects and element from a discrete probability distribution.
- GetObsModelFixedS Defines p(o|s) for a fixed 's'.
- GetObsModelFixedS Defines p(o|s)
- GetObsModelFixedS Defines p(o|s).
- GetObsModelFixedS Defines p(o|s).
- Update Belief evolution under an observation model.
- get Get function for CS_CO_CA_POMDPs.
- get Get function for CS_CO_DA_POMDPs.
- get Get function for CS_CO_POMDPs.
- get Get function for CS_DO_CA_POMDPs.
- get Get function for CS_DO_DA_POMDPs.
- get Get function for CS_POMDPs.
- get Get function for DS_CO_CA_POMDPs.
- get Get function for DS_CO_DA_POMDPs.
- get Get function for DS_DO_CA_POMDPs.
- get Get function for DS_DO_DA_POMDPs.
- get Get functio for POMDPs.
- Reward Evaluates the reward function.
- Reward Evaluates the reward function.
- Reward Evaluates the reward function.
- Reward Evaluates the reward function.
- rand Random state from a continuous space.
- rand Random state from a discrete space.
- MakeFigure3 Generates Figure 3.
- SampleBeliefs Samples a set of beliefs from a POMDP.
- SimulateFrom Simulates a POMDP from a given belief.
SOURCE CODE
0001 function [s b o r]=SimulationStep(P,b,s,a) 0002 % Executes one step of a POMDP simulation. 0003 % 0004 % It updates the belief using the corresponding Prediction method and the 0005 % given action and then corrects the belief using the corresponding 0006 % Update method. 0007 % The implementation of both the Prediction and Update methods are 0008 % dependant on the nature of the beliefs. 0009 % 0010 % Parameters: 0011 % P: The POMDP. 0012 % b: The belief to update. 0013 % s: The hidden state (used to query the observation and reward models) 0014 % a: The action to execute. 0015 % 0016 % Outputs: 0017 % s: The new hidden state. 0018 % b: The new belief. 0019 % o: The observation used in the Update. 0020 % r: The reward obtained in the new attained (hidden) state. 0021 % 0022 % See also DBelief, GBelief, PBelief, SimulateFrom. 0023 0024 S=get(P,'StateSpace'); 0025 0026 [s b]=Prediction(P,s,b,a,S); 0027 0028 po=GetObsModelFixedS(P,s); 0029 if isa(po,'double') 0030 o=RandVector(po); 0031 else 0032 o=rand(po); 0033 end 0034 b=Update(P,b,o,S); 0035 0036 r=Reward(P,a,s); 0037