burlap.mdp.stochasticgames.agent

Interface SGAgent

All Known Implementing Classes:

EquilibriumPlayingSGAgent, GrimTrigger, LearningAgentToSGAgentInterface, ManualAgentsCommands.ManualSGAgent, MultiAgentDPPlanningAgent, MultiAgentQLearning, RandomSGAgent, SetStrategySGAgent, SGAgentBase, SGNaiveQLAgent, SGQWActionHistory, TitForTat

public interface SGAgent

This abstract class defines the the shell code and interface for creating agents that can make decisions in mutli-agent stochastic game worlds. Agents have names to identify themselves and can joint multi-agent worlds as a specific type of agent that is specified by their SGAgentType. Agents are informed by the world when a game is starting and ending and they are also queried by the world for the action they will take. After all agents in the world have chosen their action, the world changes and informs each agent of the outcome for all agents in the world.

Author:

James MacGlashan

Method Summary

Modifier and Type	Method and Description
Action	action(State s) This method is called by the world when it needs the agent to choose an action
java.lang.String	agentName() Returns this agent's name
SGAgentType	agentType() Returns this agent's type
void	gameStarting(World w, int agentNum) This method is called by the world when a new game is starting.
void	gameTerminated() This method is called by the world when a game has ended.
void	observeOutcome(State s, JointAction jointAction, double[] jointReward, State sprime, boolean isTerminal) This method is called by the world when every agent in the world has taken their action.

Method Detail

agentName

java.lang.String agentName()

Returns this agent's name

Returns:

this agent's name

agentType

SGAgentType agentType()

Returns this agent's type

Returns:

this agent's type

gameStarting

void gameStarting(World w,
                  int agentNum)

This method is called by the world when a new game is starting.

Parameters:

w - the world in which the game is starting

agentNum - the agent number of the agent in the world

action

Action action(State s)

This method is called by the world when it needs the agent to choose an action

Parameters:

s - the current state of the world

Returns:

the action this agent wishes to take

observeOutcome

void observeOutcome(State s,
                    JointAction jointAction,
                    double[] jointReward,
                    State sprime,
                    boolean isTerminal)

This method is called by the world when every agent in the world has taken their action. It conveys the result of the joint action.

Parameters:

s - the state in which the last action of each agent was taken

jointAction - the joint action of all agents in the world

jointReward - the joint reward of all agents in the world

sprime - the next state to which the agent transitioned

isTerminal - whether the new state is a terminal state

gameTerminated

void gameTerminated()

This method is called by the world when a game has ended.