Uses of Interface
net.pakl.rl.ValueFunction

Packages that use ValueFunction

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.
org.eyelanguage.rl.reading	Code for the Adaptive Reading Agent; see ReadingMain for parameters and default values.

Uses of ValueFunction in net.pakl.rl

Classes in net.pakl.rl that implement ValueFunction

class	ValueFunctionHashMap A ValueFunction maps states, which are positions in a World, to values, and may be replaced with a neural network.
class	ValueFunctionHashMapZipped
class	ValueFunctionPerceptron
class	ValueFunctionResidualAlgorithmBairdPerceptron
class	ValueFunctionResidualAlgorithmLinear
class	ValueFunctionResidualAlgorithmPatrykNetwork
class	ValueFunctionResidualAlgorithmPerceptron

Methods in net.pakl.rl that return ValueFunction

ValueFunction	AgentParallelized.performValueIteration(ValueFunction newValueFunction, ValueFunction valueFunction)
ValueFunction	Agent.performValueIteration(ValueFunction newValueFunction, ValueFunction valueFunction) This is the MAIN learning function in the Agent.

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

void	Agent.experience(ValueFunction newValueFunction, ValueFunction valueFunction, State startState, State nextState, double reinforcement)
java.lang.String	PolicyExtractor.extractOptimalPolicy(ActionSet naivePolicy, ValueFunction valueFunction, World trainedWorld, World testWorld, ReinforcementFunction rf, double discountFactor)
Action	Agent.getBestActionForValueFrom(State s, ValueFunction vf, ActionSet p) This is a function which should probably be called more often to reduce duplicated code.
ValueFunction	AgentParallelized.performValueIteration(ValueFunction newValueFunction, ValueFunction valueFunction)
ValueFunction	Agent.performValueIteration(ValueFunction newValueFunction, ValueFunction valueFunction) This is the MAIN learning function in the Agent.
void	Agent.performValueIterationTrajectorySample(ValueFunction newValueFunction, ValueFunction valueFunction)
protected void	Agent.performValueIterationUpdateOnState(ValueFunction newValueFunction, ValueFunction valueFunction, State currentState)

Uses of ValueFunction in org.eyelanguage.rl.reading

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

class

ParallelToSerialVFAdapter Wraps a normal value function but converts parallel states into serial states before relaying state value requests to the value function.

Constructors in org.eyelanguage.rl.reading with parameters of type ValueFunction

ParallelToSerialVFAdapter(ValueFunction vf)