Uses of Interface
net.pakl.rl.World

Packages that use World

net.pakl.rl	These are the basic reinforcement learning model classes -- every reinforcement learning problem can be described (minimally) as a World (collection of states), Policy, ValueFunction, and Actions.
net.pakl.rl.maze	World and policy for a 2D problem with impassable obstacles.
org.eyelanguage.rl.reading	Code for the Adaptive Reading Agent; see ReadingMain for parameters and default values.

Uses of World in net.pakl.rl

Fields in net.pakl.rl declared as World

protected World

Agent.world

Methods in net.pakl.rl with parameters of type World

java.lang.String	PolicyExtractor.extractOptimalPolicy(ActionSet naivePolicy, ValueFunction valueFunction, World trainedWorld, World testWorld, ReinforcementFunction rf, double discountFactor)
void	ValueFunctionHashMap.init(World sourceWorld)
void	ValueFunctionResidualAlgorithmLinear.setWorld(World w)
void	ValueFunctionPerceptron.setWorld(World w)
void	ValueFunctionHashMap.setWorld(World w)
void	ValueFunction.setWorld(World w)
void	Agent.setWorld(World newWorld)

Constructors in net.pakl.rl with parameters of type World

ValueFunctionHashMap(World sourceWorld)
While the initial ValueFunction is arbitrary, it must be based on a World's states.

ValueFunctionHashMap(World sourceWorld, boolean SAFE_MODE)

ValueFunctionHashMapZipped(World sourceWorld)

ValueFunctionHashMapZipped(World sourceWorld, boolean safety)

ValueFunctionPerceptron(World w)

ValueFunctionResidualAlgorithmBairdPerceptron(World w)

ValueFunctionResidualAlgorithmLinear(World w)

ValueFunctionResidualAlgorithmPatrykNetwork(World w)

ValueFunctionResidualAlgorithmPerceptron(World w)

Uses of World in net.pakl.rl.maze

Classes in net.pakl.rl.maze that implement World

class

MazeWorld This is a model of a 2D gridworld and supports all the functions specified in the World interface.

Uses of World in org.eyelanguage.rl.reading

Classes in org.eyelanguage.rl.reading that implement World

class	SentenceWorld Describes how states evolve in response to actions in a serial attention and word identification model.
class	SentenceWorldParallel Defines how states evolve in response to actions when a parallel reading process is underway, such as when various words become identified.

Methods in org.eyelanguage.rl.reading with parameters of type World

void	ParallelToSerialVFAdapter.setWorld(World w)