MultiAgentDecisionProcess
Release 0.2.1
|
POSGDiscreteInterface is the interface for a discrete POSG model: it defines the set/get reward functions. More...
#include <POSGDiscreteInterface.h>
Public Member Functions | |
virtual POSGDiscreteInterface * | Clone () const =0 |
Returns a copy of this class. | |
virtual void | CreateNewRewardModelForAgent (Index agentI)=0 |
Creates a new reward model mapping. | |
virtual double | GetRewardForAgent (Index agentI, Index sI, Index jaI) const =0 |
Return the reward for state, joint action indices. | |
virtual void | SetRewardForAgent (Index agentI, Index sI, Index jaI, double r)=0 |
Set the reward for state, joint action indices. | |
virtual void | SetRewardForAgent (Index agentI, Index sI, Index jaI, Index sucSI, double r)=0 |
Set the reward for state, joint action , suc. state indices. | |
virtual void | SetRewardForAgent (Index agentI, Index sI, Index jaI, Index sucSI, Index joI, double r)=0 |
Set the reward for state, joint action, suc.state, joint obs indices. | |
virtual | ~POSGDiscreteInterface () |
Destructor.Can't make a virt.destr. pure abstract! | |
![]() | |
virtual const Action * | GetAction (Index agentI, Index a) const =0 |
Return a ref to the a-th action of agent agentI. | |
virtual double | GetInitialStateProbability (Index sI) const =0 |
virtual const StateDistribution * | GetISD () const =0 |
Returns the complete initial state distribution. | |
virtual const JointAction * | GetJointAction (Index i) const =0 |
Return a ref to the i-th joint action. | |
virtual const JointObservation * | GetJointObservation (Index i) const =0 |
Return a ref to the i-th joint observation. | |
virtual const std::vector < size_t > & | GetNrActions () const =0 |
Return the number of actions vector. | |
virtual size_t | GetNrActions (Index AgentI) const =0 |
Return the number of actions of agent agentI. | |
virtual size_t | GetNrJointActions () const =0 |
Return the number of joiny actions. | |
virtual size_t | GetNrJointObservations () const =0 |
Return the number of joiny observations. | |
virtual const std::vector < size_t > & | GetNrObservations () const =0 |
Return the number of observations vector. | |
virtual size_t | GetNrObservations (Index AgentI) const =0 |
Return the number of observations of agent agentI. | |
virtual size_t | GetNrStates () const =0 |
Return the number of states. | |
virtual const Observation * | GetObservation (Index agentI, Index a) const =0 |
Return a ref to the a-th observation of agent agentI. | |
virtual const ObservationModelDiscrete * | GetObservationModelDiscretePtr () const =0 |
Returns a pointer to the underlying observation model. | |
virtual double | GetObservationProbability (Index jaI, Index sucSI, Index joI) const =0 |
Return the probability of joint observation joI: P(joI|jaI,sucSI). | |
virtual OGet * | GetOGet () const =0 |
virtual const State * | GetState (Index i) const =0 |
Returns a pointer to state i. | |
virtual TGet * | GetTGet () const =0 |
virtual const TransitionModelDiscrete * | GetTransitionModelDiscretePtr () const =0 |
Returns a pointer to the underlying transition model. | |
virtual double | GetTransitionProbability (Index sI, Index jaI, Index sucSI) const =0 |
Return the probability of successor state sucSI: P(sucSI|sI,jaI). | |
virtual Index | IndividualToJointActionIndices (const Index *AI_ar) const =0 |
Returns the joint action index that corresponds to the array of specified individual action indices. | |
virtual Index | IndividualToJointActionIndices (const std::vector< Index > &indivActionIndices) const =0 |
Returns the joint action index that corresponds to the vector of specified individual action indices. | |
virtual Index | IndividualToJointObservationIndices (const std::vector< Index > &indivObservationIndices) const =0 |
Returns the joint observation index that corresponds to the vector of specified individual observation indices. | |
virtual const std::vector < Index > & | JointToIndividualActionIndices (Index jaI) const =0 |
Returns a vector of indices to indiv. | |
virtual const std::vector < Index > & | JointToIndividualObservationIndices (Index joI) const =0 |
Returns a vector of indices to indiv. | |
virtual Index | SampleInitialState (void) const =0 |
Sample a state according to the initial state PDF. | |
virtual Index | SampleJointObservation (Index jaI, Index sucI) const =0 |
Sample an observation - needed for simulations. | |
virtual Index | SampleSuccessorState (Index sI, Index jaI) const =0 |
Sample a successor state - needed by simulations. | |
virtual std::string | SoftPrint () const =0 |
Prints some information on the MultiAgentDecisionProcessDiscreteInterface. | |
virtual std::string | SoftPrintState (Index sI) const =0 |
virtual | ~MultiAgentDecisionProcessDiscreteInterface () |
Destructor. Can't make a virt.destr. pure abstract! | |
![]() | |
virtual size_t | GetNrAgents () const =0 |
Return the number of agents. | |
virtual std::string | GetUnixName () const =0 |
Returns the base part of the problem filename. | |
virtual | ~MultiAgentDecisionProcessInterface () |
Destructor. | |
![]() | |
virtual double | GetDiscountForAgent (Index agentI) const =0 |
Returns the discount parameter. | |
virtual double | GetRewardForAgent (Index agentI, State *s, JointAction *ja) const =0 |
Function that returns the reward for a state and joint action. | |
virtual reward_t | GetRewardTypeForAgent (Index agentI) const =0 |
Returns the reward type. | |
virtual void | SetDiscountForAgent (Index agentI, double d)=0 |
Sets the discount parameter to 0 < d <= 1. | |
virtual void | SetRewardForAgent (Index agentI, State *s, JointAction *ja, double r)=0 |
Function that sets the reward for an agent, state and joint action. | |
virtual void | SetRewardTypeForAgent (Index agentI, reward_t r)=0 |
Sets the reward type to reward_t r. | |
virtual | ~POSGInterface () |
Virtual destructor. |
POSGDiscreteInterface is the interface for a discrete POSG model: it defines the set/get reward functions.
POSGDiscreteInterface is an interface (i.e. pure abstract class) for a discrete POSG model. This means that there is a single reward function and that states, actions and observations are discrete.
Classes that implement this interface are, for instance, POSGDiscrete and TransitionObservationIndependentPOSGDiscrete.
Definition at line 49 of file POSGDiscreteInterface.h.
|
inlinevirtual |
Destructor.Can't make a virt.destr. pure abstract!
Definition at line 59 of file POSGDiscreteInterface.h.
|
pure virtual |
Returns a copy of this class.
Implements MultiAgentDecisionProcessDiscreteInterface.
Implemented in TOIDecPOMDPDiscrete, DecPOMDPDiscrete, POSGDiscrete, DecPOMDPDiscreteInterface, TOICompactRewardDecPOMDPDiscrete, and TOIFactoredRewardDecPOMDPDiscrete.
|
pure virtual |
Creates a new reward model mapping.
Implemented in TOIDecPOMDPDiscrete, and DecPOMDPDiscrete.
|
pure virtual |
Return the reward for state, joint action indices.
Implemented in TOIDecPOMDPDiscrete, and DecPOMDPDiscrete.
|
pure virtual |
Set the reward for state, joint action indices.
Implemented in TOIDecPOMDPDiscrete, and DecPOMDPDiscrete.
|
pure virtual |
Set the reward for state, joint action , suc. state indices.
Implemented in TOIDecPOMDPDiscrete, and DecPOMDPDiscrete.
|
pure virtual |
Set the reward for state, joint action, suc.state, joint obs indices.
Implemented in TOIDecPOMDPDiscrete, and DecPOMDPDiscrete.