MultiAgentDecisionProcess
Release 0.2.1
|
BayesianGameForDecPOMDPStageInterface is a class that represents TODO: fill out... More...
#include <BayesianGameForDecPOMDPStageInterface.h>
Public Member Functions | |
BayesianGameForDecPOMDPStageInterface (const PartialJointPolicyDiscretePure *pastJPol) | |
(default) Constructor | |
BayesianGameForDecPOMDPStageInterface (Index t) | |
virtual void | ClearAllImmediateRewards ()=0 |
We can also clear this cache. | |
virtual void | ComputeAllImmediateRewards ()=0 |
When performing a lot of GetImmediateReward calls we can first compute a cache of immediate rewards, to speed things up. | |
virtual double | ComputeDiscountedImmediateRewardForJPol (JointPolicyDiscretePure *jpolBG) const =0 |
Compute the discounted expected imm reward for jpolBG. | |
virtual double | GetImmediateReward (Index jtI, Index jaI) const =0 |
Returns the (expected) immediate reward for jtI, jaI. | |
const PartialJointPolicyDiscretePure * | GetPastJointPolicy () const |
Index | GetStage () const |
virtual | ~BayesianGameForDecPOMDPStageInterface () |
Destructor. |
Protected Attributes | |
const PartialJointPolicyDiscretePure * | _m_pJPol |
Stores pointer to the past policy - perhaps not needed? | |
Index | _m_t |
The stage (time step) that this BG represents. |
BayesianGameForDecPOMDPStageInterface is a class that represents TODO: fill out...
Definition at line 39 of file BayesianGameForDecPOMDPStageInterface.h.
BayesianGameForDecPOMDPStageInterface::BayesianGameForDecPOMDPStageInterface | ( | const PartialJointPolicyDiscretePure * | pastJPol | ) |
(default) Constructor
Definition at line 33 of file BayesianGameForDecPOMDPStageInterface.cpp.
BayesianGameForDecPOMDPStageInterface::BayesianGameForDecPOMDPStageInterface | ( | Index | t | ) |
Definition at line 40 of file BayesianGameForDecPOMDPStageInterface.cpp.
|
inlinevirtual |
Destructor.
Definition at line 55 of file BayesianGameForDecPOMDPStageInterface.h.
|
pure virtual |
We can also clear this cache.
Implemented in BayesianGameForDecPOMDPStage.
|
pure virtual |
When performing a lot of GetImmediateReward calls we can first compute a cache of immediate rewards, to speed things up.
Implemented in BayesianGameForDecPOMDPStage.
|
pure virtual |
Compute the discounted expected imm reward for jpolBG.
Implemented in BayesianGameForDecPOMDPStage.
|
pure virtual |
Returns the (expected) immediate reward for jtI, jaI.
Implemented in BayesianGameForDecPOMDPStage.
|
inline |
Definition at line 65 of file BayesianGameForDecPOMDPStageInterface.h.
References _m_pJPol.
|
inline |
Definition at line 63 of file BayesianGameForDecPOMDPStageInterface.h.
References _m_t.
|
protected |
Stores pointer to the past policy - perhaps not needed?
Definition at line 47 of file BayesianGameForDecPOMDPStageInterface.h.
Referenced by GetPastJointPolicy(), BayesianGameForDecPOMDPStage::Initialize(), and BayesianGameForDecPOMDPStage::SoftPrint().
|
protected |
The stage (time step) that this BG represents.
Definition at line 45 of file BayesianGameForDecPOMDPStageInterface.h.
Referenced by BayesianGameForDecPOMDPStage::ComputeDiscountedImmediateRewardForJPol(), GetStage(), BayesianGameForDecPOMDPStage::Initialize(), and BayesianGameForDecPOMDPStage::SoftPrint().