Package jline.api.rl
Class RlTDAgent
-
- All Implemented Interfaces:
public final class RlTDAgent
Temporal Difference Learning Agent for Queueing Network Control Implements TD learning with tabular value and Q functions
-
-
Nested Class Summary
Nested Classes Modifier and Type Class Description public class
RlTDAgent.Companion
-
Field Summary
Fields Modifier and Type Field Description public final static RlTDAgent.Companion
Companion
-
Method Summary
Modifier and Type Method Description final Unit
reset(RlEnv env)
Reset the agent and environment to initial state final Array<DoubleArray>
getValueFunction()
Get the current value function final Array<Array<DoubleArray>>
getQFunction()
Get the current Q function final Unit
solve(RlEnv env)
Main solving method using temporal difference learning -
-
Method Detail
-
getValueFunction
final Array<DoubleArray> getValueFunction()
Get the current value function
-
getQFunction
final Array<Array<DoubleArray>> getQFunction()
Get the current Q function
-
-
-
-