Package | Description |
---|---|
net.sourceforge.jabm.learning |
A library of algorithms for individual learning.
|
net.sourceforge.jabm.strategy |
Classes representing the strategies used by the agents in the simulation.
|
Modifier and Type | Class and Description |
---|---|
class |
QLearner
An implementation of the Q-learning algorithm.
|
Modifier and Type | Method and Description |
---|---|
int |
ActionSelector.act(int state,
MDPLearner learner)
Choose an action according to the current state and the
current value estimates for each action.
|
int |
SoftMaxActionSelector.act(int state,
MDPLearner learner) |
int |
EpsilonGreedyActionSelector.act(int state,
MDPLearner qLearner) |
Modifier and Type | Field and Description |
---|---|
protected MDPLearner |
RlStrategyWithState.learner |
Modifier and Type | Method and Description |
---|---|
MDPLearner |
RlStrategyWithState.getLearner() |
Modifier and Type | Method and Description |
---|---|
void |
RlStrategyWithState.setLearner(MDPLearner learner) |
Constructor and Description |
---|
RlStrategyWithState(Agent agent,
org.springframework.beans.factory.ObjectFactory<Strategy> strategyFactory,
MDPLearner learner) |
RlStrategyWithState(org.springframework.beans.factory.ObjectFactory<Strategy> strategyFactory,
MDPLearner learner) |
Copyright © 2014. All rights reserved.