|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
public interface StatelessPolicy<I,A extends Action>
Interface for building a stateless reinforcement learning policy. This type of policy simply maintains a distribution guiding action choice irrespective of the current state of the world. That is, it simply maintains a likelihood of selection for each action for all world states. This type of policy can be useful in simple or static environments or with learners that implement stateless algorithms (e.g. VRELearner)
Policy
Method Summary | |
---|---|
A |
generateAction()
Choose a new Action based on the current policy. |
ActionDomain<I,A> |
getActionDomain()
Get the ActionDomain that this policy selects Actions from. |
A |
getLastAction()
Retrieve the last Action chosen by this policy. |
double |
getProbability(I actionID)
Gets the current probability of choosing an action. |
void |
setProbability(I actionID,
double newValue)
Updates the probability of choosing the indicated Action. |
Methods inherited from interface edu.iastate.jrelm.rl.Policy |
---|
generateAction, getProbability, getStateDomain, setProbability, setRandomSeed |
Method Detail |
---|
A generateAction()
ActionDomain<I,A> getActionDomain()
getActionDomain
in interface Policy<I,A extends Action,java.lang.Object,State>
A getLastAction()
getLastAction
in interface Policy<I,A extends Action,java.lang.Object,State>
double getProbability(I actionID)
actionID
- - the identifier indicating which action to retrieve a probability for.
Policy#getProbability(SI, AI)
void setProbability(I actionID, double newValue)
actionID
- - the identifier of the desired Action in this policy's ActionDomain.newValue
- - new choice probability value to associate with this action.Policy#setProbability(SI, AI, double)
|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |