A B C D E F G H I L M N O P Q R S T U V W Z

A

abssum(double[]) - Static method in class net.pakl.rl.VectorTools

Action - Interface in net.pakl.rl

A basic element of our Reinforcement Learning simulation framework; Actions are returned by a ActionSet, and when performed by an Agent, moves it to another state in a World

Action2D - Class in net.pakl.rl.maze

This class represents a one-dimensional action, which could correspond to a movement vector in a 2D World such as MazeWorld

Action2D(int, int) - Constructor for class net.pakl.rl.maze.Action2D

Action2D(State2D, State2D) - Constructor for class net.pakl.rl.maze.Action2D

This constructor allows you to create an action based on the difference between two states -- moving from state1 to state2

actionPerformed(ActionEvent) - Method in class org.eyelanguage.rl.analysis.AgentTestVisualizer

ActionSet - Class in net.pakl.rl

A ActionSet maps States to possible Actions and is used by an Agent in considering its possible next moves.

ActionSet() - Constructor for class net.pakl.rl.ActionSet

ACUITY_LIMIT - Variable in class org.eyelanguage.rl.reading.SentenceWorld

Beyond this distance, visual acuity goes non-linearly to zero.

ACUITY_LINEAR_PENALIZE - Variable in class org.eyelanguage.rl.reading.SentenceWorld

If true, means that as word identifcation time increases linearly as fovea is distanced from attended word center; otherwise just a constant penalty for any distance from the word center

ACUITY_LINEAR_PENALTY_SLOPE - Variable in class org.eyelanguage.rl.reading.SentenceWorld

Amount of extra time required per character eccentricity.

acuityAdjustment(ReadingState, ReadingState) - Method in class org.eyelanguage.rl.reading.SentenceWorld

If we saccade to a position, the time attended is worth less than future time that will be spent (see detail).

acuityAdjustmentParallel(int, ReadingStateParallelRelative) - Method in class org.eyelanguage.rl.reading.SentenceWorldParallel

acuityIdentificationPenalty(int, int) - Method in class org.eyelanguage.rl.reading.SentenceWorld

acuityIdentificationPenalty(Word, int) - Method in class org.eyelanguage.rl.reading.SentenceWorld

acuityIdentificationPenaltyAbsolute(int) - Method in class org.eyelanguage.rl.reading.SentenceWorld

acuityLimit - Variable in class org.eyelanguage.rl.reading.ReadingMain

The maximum allowed distance in the state space between fovea and center of attention.

acuityLinearPenalize - Variable in class org.eyelanguage.rl.reading.ReadingMain

reading.prop parameter: If true, one extra timestemp of processing is required for each character space from the center of the word being processed for word identification.

acuityLinearPenaltySlope - Variable in class org.eyelanguage.rl.reading.ReadingMain

Amount of cost added per character eccentricity for linear acuity penalty.

add(SentenceWorld, ReadingPolicy, ReadingReinforcementFunction) - Method in class org.eyelanguage.rl.reading.ReadingSet

addSentence(String, String, String, String) - Method in class org.eyelanguage.rl.reading.Corpus

addTeleporter(State, State) - Method in class net.pakl.rl.maze.MazeWorld

addTimer(double) - Method in class net.pakl.rl.ValueFunctionHashMap

addToTallies(String) - Static method in class org.eyelanguage.rl.analysis.LogAnalyzer2

advanceAttentionWindow(ReadingStateParallelRelative) - Method in class org.eyelanguage.rl.reading.SentenceWorldParallel

Agent - Class in net.pakl.rl

This class represents an agent, which is capable of iterating over all of the actions from its given state given a ActionSet.

Agent() - Constructor for class net.pakl.rl.Agent

Agent(String) - Constructor for class net.pakl.rl.Agent

AgentParallelized - Class in net.pakl.rl

This class represents a multi-threaded agent (therefore faster if you have multiple CPUs) appropriate for reinforcement learning with full Value Iteration, since during value iteration each state can be updated independently of others (as long as testTrainSameVf is false).

AgentParallelized(String, int) - Constructor for class net.pakl.rl.AgentParallelized

AgentParallelized(int) - Constructor for class net.pakl.rl.AgentParallelized

agentParallelNumThreads - Variable in class org.eyelanguage.rl.reading.ReadingMain

reading.prop parameter

AgentTestVisualizer - Class in org.eyelanguage.rl.analysis

Permits graphical visualization of an adaptive reading agents eye movements for demonstration or presentation purposes.

AgentTestVisualizer() - Constructor for class org.eyelanguage.rl.analysis.AgentTestVisualizer

agentType - Variable in class org.eyelanguage.rl.reading.ReadingMain

reading.prop parameter

aidTimes - Variable in class org.eyelanguage.rl.reading.ReadingMain

Specified the amount of time it will take the agent to recognize each word, if that word if foveated in its center.

Alert - Class in tools

Alert() - Constructor for class tools.Alert

Creates new form Alert

allocationCounter - Variable in class org.eyelanguage.rl.reading.ReadingStateFactory

ALLOW_SIMULTANEOUS_ATTNEXT_AND_IDENT - Variable in class org.eyelanguage.rl.reading.ReadingMain

Specifies in generic policy if attention shifts and word identification can occur at the same time.

ALLOW_SIMULTANEOUS_SACREQ_AND_ATTNEXT - Variable in class org.eyelanguage.rl.reading.ReadingMain

Specifies in generic policy if saccade request actions and attention shift actions can occur at the same time.

allowAction(State, Action) - Method in class net.pakl.rl.ActionSet

This method allows you to program in a possible action given a state.

allowDiagonals - Variable in class net.pakl.rl.maze.Toolbox

allowSaccadeActions(int, int, int) - Method in class org.eyelanguage.rl.reading.ReadingPolicy

allowSaccadeActions(int, int, int) - Method in class org.eyelanguage.rl.reading.ReadingPolicyParallel

applyAcuityAdjustmentsParallel(ReadingStateParallelRelative, ReadingStateParallelRelative) - Method in class org.eyelanguage.rl.reading.SentenceWorldParallel

applySaccadicError(int) - Method in class org.eyelanguage.rl.reading.SentenceWorld

attemptAttendNextWord(ReadingState) - Method in class org.eyelanguage.rl.reading.SentenceWorld

attemptAttendNextWord(ReadingState) - Method in class org.eyelanguage.rl.reading.SentenceWorldParallel

If the next word is already identified, a single attNext action keeps moving you through the identified word to the following word.

ATTEND_INTERVAL - Variable in class org.eyelanguage.rl.reading.SentenceWorld

By how much the 'attended time' dimension is incremented on each simulated timestep.

attendCurrentWord(ReadingState) - Method in class org.eyelanguage.rl.reading.SentenceWorld

attendCurrentWord(ReadingState) - Method in class org.eyelanguage.rl.reading.SentenceWorldParallel

attendedWordID - Variable in class org.eyelanguage.rl.reading.ReadingState

A unique word identification number of the attended word.

attendedWordLen - Variable in class org.eyelanguage.rl.reading.ReadingState

This is an integer which indicates the number of characters in the word being attended.

attendedWordPredictability - Variable in class org.eyelanguage.rl.reading.ReadingState

attendingWord() - Method in class org.eyelanguage.rl.reading.ReadingAction

attendNextWord - Variable in class org.eyelanguage.rl.reading.ReadingAction

attendThisWord - Variable in class org.eyelanguage.rl.reading.ReadingAction

attention - Variable in class org.eyelanguage.rl.reading.ReadingMain

reading.prop parameter: Serial attention means attend one word at a time, semiparallel means multiple but with a serial sliding window, and parallel means fully parallel processing of words in any order.

attnWindowLabels(int) - Method in class org.eyelanguage.rl.analysis.Extractor

attWindowIdentified - Variable in class org.eyelanguage.rl.reading.ReadingStateParallelRelative

attWindowLengths - Variable in class org.eyelanguage.rl.reading.ReadingStateParallelRelative

attWindowPredictabilities - Variable in class org.eyelanguage.rl.reading.ReadingStateParallelRelative

attWindowTimes - Variable in class org.eyelanguage.rl.reading.ReadingStateParallelRelative

attWindowWordIDs - Variable in class org.eyelanguage.rl.reading.ReadingStateParallelRelative