burlap.oomdp.singleagent

Interface RewardFunction

All Known Subinterfaces:

DifferentiableRF

All Known Implementing Classes:

BeliefMDPGenerator.BeliefRF, CartPoleDomain.CartPoleRewardFunction, DiffVFRF, ExampleGridWorld.ExampleRF, FrostbiteRF, GoalBasedRF, GraphRF, GridWorldRewardFunction, InvertedPendulum.InvertedPendulumRewardFunction, LinearDiffRFVInit, LinearStateActionDifferentiableRF, LinearStateDifferentiableRF, LocalSubgoalRF, LunarLanderRF, MacroCellGridWorld.LinearInPFRewardFunction, NullRewardFunction, OptionEvaluatingRF, PotentialShapedRF, PotentialShapedRMax.PotentialShapedRMaxRF, ShapedRewardFunction, SingleGoalPFRF, TigerDomain.TigerRF, UniformCostRF

public interface RewardFunction

Defines the reward function for a task.

Author:

James MacGlashan

Method Summary

Methods

Modifier and Type	Method and Description
double	reward(State s, GroundedAction a, State sprime) Returns the reward received when action a is executed in state s and the agent transitions to state sprime.

Method Detail

reward

double reward(State s,
            GroundedAction a,
            State sprime)

Returns the reward received when action a is executed in state s and the agent transitions to state sprime.

Parameters:

s - the state in which the action was executed

a - the action executed

sprime - the state to which the agent transitioned

Returns:

the reward received when action a is executed in state s and the agent transitions to state sprime.