|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
PA
- - the type of ReinforcementLearner parameters (RLParameters)
this learner accepts. This will usually be a specific set of
paramters needed for a particular learning algorithm.I
- - the type of identifier being used to distiguish ActionsA
- - the type of Actions this learner is working withF
- - the type of reinforcement object (Feedback) that this learner acceptsPO
- - the type of Policy that this learner updates and uses make new
Action selectionspublic interface ReinforcementLearner<PA extends RLParameters,I,A extends Action,F extends Feedback,PO extends Policy>
For classes that implement reinforcement learning algorithms. Classes implementing this interface are responsible for driving the learning process of specific algorithms. Reinforcement learning algorithms make use of a policy to represent learned knowledge. Policies themselves require access to the space of possible actions, represented by ActionDomains. As such an ReinforcementLearner will make use of with a StatelessPolicy and an ActionDomain.
Feedback is parameterized since required input will vary depending on the specific reinforcement learning algorithm and the particular simulation environment.
Method Summary | |
---|---|
A |
chooseAction()
Elicits a new choice of action. |
java.lang.String |
getName()
Retrieves the name of the learning algorithm this learner implements. |
PA |
getParameters()
Retrieve the RLParameters that contain settings for this learning algorithm. |
PO |
getPolicy()
Retrieve the StatelessPolicy being used to represent learned knowledge. |
PA |
makeParameters()
Create a default set of parameters that can be used with this learner. |
void |
setParameters(PA newParams)
Sets the current settings for this learning algorithm. |
void |
setPolicy(PO newPolicy)
Set the StatelessPolicy to be used to represent learned knowledge. |
void |
update(F reward)
Initiate the learning process using given feedback. |
Method Detail |
---|
void update(F reward)
Note: Most often feedback is for the last Action chosen, so given ActionID will usually point to this Action. As such, many RLEnigine implementations may also provide update() methods that simply accept feedback and associate it with the last Action chosen.
reward
- - feedback for the specified actionA chooseAction()
Action
PA getParameters()
PA makeParameters()
void setParameters(PA newParams)
parameters
- - new settings for this algorithm as RLParametersPO getPolicy()
StatelessPolicy
void setPolicy(PO newPolicy)
p
- - The policy can be any object implementing the StatelessPolicy interface.StatelessPolicy
java.lang.String getName()
|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |