Package uk.ac.liv.ai.learning

A library of learning algorithms used by JASA agents.

See:
Description

Interface Summary

ContinuousLearner	A learning algorithm that outputs a continuous signal.
DiscreteLearner	A learner that learns a discrete number of different actions.
Learner	Classes implementing this interface indicate that they implement a learning algorithm.
LearnerMonitor
MDPLearner	Classes implementing this interface implement learning algorithms for markoff descision processes.
MimicryLearner	A learner that attempts to adjust its output to match a training signal.
StimuliResponseLearner	Classes implementing this interface implement myopic stimuli-response reinformcement learning algorithms.

Class Summary

AbstractLearner
DumbLearner	A learner that chooses the same specified action on every iteration.
DumbRandomLearner	A learner that simply plays a random action on each iteration without any learning.
GraphLearnerMonitor
MetaLearner
NPTRothErevLearner	A modification of RothErev to address parameter degeneracy, and modified learning with 0-reward.
QLearner	An implementation of the Q-learning algorithm, with epsilon-greedy exploration.
RothErevLearner	A class implementing the Roth-Erev learning algorithm.
StatelessQLearner	A memory-less version of the Q-Learning algorithm.
WidrowHoffLearner	An implementation of the Widrow-Hoff learning algorithm for 1-dimensional training sets.
WidrowHoffLearnerWithMomentum

Package uk.ac.liv.ai.learning Description

A library of learning algorithms used by JASA agents.