public class SimulatedPOEnvironment extends SimulatedEnvironment
Environment
specifically for simulating interaction with a POMDP
environments (PODomain
). In this case, the getCurrentObservation()
returns the last observation made from the Environment
, not the hidden
state, and the executeAction(burlap.oomdp.singleagent.GroundedAction)
method does not return EnvironmentOutcome
objects that contain the full state
of the environment, but an observation drawn from the POMDP ObservationFunction
following
the execution of the action. If you would like to access the true hidden state of the environment, use the
getCurrentHiddenState()
method.Modifier and Type | Field and Description |
---|---|
protected State |
curObservation
The current observation from the POMDP environment
|
allowActionFromTerminalStates, curState, domain, lastReward, observers, rf, stateGenerator, tf
Constructor and Description |
---|
SimulatedPOEnvironment(PODomain domain,
RewardFunction rf,
TerminalFunction tf) |
SimulatedPOEnvironment(PODomain domain,
RewardFunction rf,
TerminalFunction tf,
State initialHiddenState) |
SimulatedPOEnvironment(PODomain domain,
RewardFunction rf,
TerminalFunction tf,
StateGenerator hiddenStateGenerator) |
Modifier and Type | Method and Description |
---|---|
EnvironmentOutcome |
executeAction(GroundedAction ga)
Executes the specified action in this environment
|
State |
getCurrentHiddenState()
Returns the current hidden state of this
Environment . |
State |
getCurrentObservation()
Returns the current observation of the environment as a
State . |
PODomain |
getPODomain() |
void |
resetEnvironment()
Resets this environment to some initial state, if the functionality exists.
|
void |
setCurObservationTo(State observation)
Overrides the current observation of this environment to the specified value
|
void |
setDomain(Domain domain) |
addObservers, clearAllObservers, getDomain, getLastReward, getObservers, getRf, getStateGenerator, getTf, isInTerminalState, removeObservers, setAllowActionFromTerminalStates, setCurStateTo, setRf, setStateGenerator, setTf
protected State curObservation
public SimulatedPOEnvironment(PODomain domain, RewardFunction rf, TerminalFunction tf)
public SimulatedPOEnvironment(PODomain domain, RewardFunction rf, TerminalFunction tf, State initialHiddenState)
public SimulatedPOEnvironment(PODomain domain, RewardFunction rf, TerminalFunction tf, StateGenerator hiddenStateGenerator)
public PODomain getPODomain()
public void setDomain(Domain domain)
setDomain
in class SimulatedEnvironment
public void setCurObservationTo(State observation)
observation
- the current observation of this environment to the specified valuepublic State getCurrentObservation()
Environment
State
.getCurrentObservation
in interface Environment
getCurrentObservation
in class SimulatedEnvironment
State
.public State getCurrentHiddenState()
Environment
.State
representing the current hidden state of the environment.public EnvironmentOutcome executeAction(GroundedAction ga)
Environment
executeAction
in interface Environment
executeAction
in class SimulatedEnvironment
ga
- the GroundedAction that is to be performed in this environment.public void resetEnvironment()
Environment
resetEnvironment
in interface Environment
resetEnvironment
in class SimulatedEnvironment