Package jline.api.rl
Class RlEnvGeneral
-
- All Implemented Interfaces:
public final class RlEnvGeneral
General Reinforcement Learning Environment for Queueing Networks Provides a more general interface for RL agents with configurable action spaces
-
-
Nested Class Summary
Nested Classes Modifier and Type Class Description public final class
RlEnvGeneral.SampleResult
Data class to hold sample results
-
Method Summary
Modifier and Type Method Description final Network
getModel()
final Integer
getNqueues()
final Map<Integer, IntArray>
getActionSpace()
final IntArray
getIdxOfQueueInNodes()
final IntArray
getIdxOfActionNodes()
final Integer
getStateSize()
final Double
getGamma()
final Boolean
isInStateSpace(IntArray state)
Check if the current state is within the defined state space final Boolean
isInActionSpace(IntArray state)
Check if the current state is within the action space final RlEnvGeneral.SampleResult
sample()
Sample the next event from the queueing network Returns time delta, departure node, arrival node, and full sample resultNOTE: This is a placeholder implementation. final Unit
update(RlEnvGeneral.SampleResult sample)
Update the model state based on sample resultNOTE: This is a placeholder implementation. final Unit
reset()
Reset the environment to initial state -
-
Method Detail
-
getNqueues
final Integer getNqueues()
-
getActionSpace
final Map<Integer, IntArray> getActionSpace()
-
getIdxOfQueueInNodes
final IntArray getIdxOfQueueInNodes()
-
getIdxOfActionNodes
final IntArray getIdxOfActionNodes()
-
getStateSize
final Integer getStateSize()
-
isInStateSpace
final Boolean isInStateSpace(IntArray state)
Check if the current state is within the defined state space
-
isInActionSpace
final Boolean isInActionSpace(IntArray state)
Check if the current state is within the action space
-
sample
final RlEnvGeneral.SampleResult sample()
Sample the next event from the queueing network Returns time delta, departure node, arrival node, and full sample result
NOTE: This is a placeholder implementation. In the actual implementation, this would use SolverSSA.
-
update
final Unit update(RlEnvGeneral.SampleResult sample)
Update the model state based on sample result
NOTE: This is a placeholder implementation.
-
-
-
-