Index

A

act() (deer.base_classes.Environment method) action() (deer.base_classes.Policy method) actions() (deer.agent.DataSet method)

addSample() (deer.agent.DataSet method) avgBellmanResidual() (deer.agent.NeuralAgent method) avgEpisodeVValue() (deer.agent.NeuralAgent method)

B

bestAction() (deer.agent.NeuralAgent method) (deer.base_classes.Policy method)

C

chooseBestAction() (deer.base_classes.QNetwork method) (deer.q_networks.AC_net_keras.MyACNetwork method) (deer.q_networks.q_net_keras.MyQNetwork method) (deer.q_networks.q_net_theano.MyQNetwork method)

Controller (class in deer.experiment.base_controllers)

D

DataSet (class in deer.agent) deer.agent (module) deer.base_classes.Environment (module) deer.experiment.base_controllers (module)

discountFactor() (deer.agent.NeuralAgent method) (deer.base_classes.QNetwork method) DiscountFactorController (class in deer.experiment.base_controllers) dumpNetwork() (deer.agent.NeuralAgent method)

E

end() (deer.base_classes.Environment method) Environment (class in deer.base_classes) epsilon() (deer.policies.EpsilonGreedyPolicy method) (deer.policies.LongerExplorationPolicy method)

EpsilonController (class in deer.experiment.base_controllers) EpsilonGreedyPolicy (class in deer.policies)

F

FindBestController (class in deer.experiment.base_controllers)

I

inputDimensions() (deer.base_classes.Environment method) InterleavedTestEpochController (class in deer.experiment.base_controllers)

inTerminalState() (deer.base_classes.Environment method)

L

learningRate() (deer.agent.NeuralAgent method) (deer.base_classes.QNetwork method) LearningRateController (class in deer.experiment.base_controllers)

LongerExplorationPolicy (class in deer.policies)

M

MyACNetwork (class in deer.q_networks.AC_net_keras)

MyQNetwork (class in deer.q_networks.q_net_keras) (class in deer.q_networks.q_net_theano)

N

nActions() (deer.base_classes.Environment method)

NeuralAgent (class in deer.agent)

O

observations() (deer.agent.DataSet method) observationType() (deer.base_classes.Environment method) observe() (deer.base_classes.Environment method) onActionChosen() (deer.experiment.base_controllers.Controller method) onActionTaken() (deer.experiment.base_controllers.Controller method)

onEnd() (deer.experiment.base_controllers.Controller method) onEpisodeEnd() (deer.experiment.base_controllers.Controller method) onEpochEnd() (deer.experiment.base_controllers.Controller method) onStart() (deer.experiment.base_controllers.Controller method) overrideNextAction() (deer.agent.NeuralAgent method)

P

Policy (class in deer.base_classes)

Q

QNetwork (class in deer.base_classes)

qValues() (deer.base_classes.QNetwork method) (deer.q_networks.q_net_keras.MyQNetwork method) (deer.q_networks.q_net_theano.MyQNetwork method)

R

randomAction() (deer.base_classes.Policy method) randomBatch() (deer.agent.DataSet method) reset() (deer.base_classes.Environment method)

rewards() (deer.agent.DataSet method) run() (deer.agent.NeuralAgent method)

S

setActive() (deer.experiment.base_controllers.Controller method) setControllersActive() (deer.agent.NeuralAgent method) setDiscountFactor() (deer.agent.NeuralAgent method) (deer.base_classes.QNetwork method) setEpsilon() (deer.policies.EpsilonGreedyPolicy method) (deer.policies.LongerExplorationPolicy method)

setLearningRate() (deer.agent.NeuralAgent method) (deer.base_classes.QNetwork method) setNetwork() (deer.agent.NeuralAgent method) summarizePerformance() (deer.base_classes.Environment method)

T

terminals() (deer.agent.DataSet method) totalRewardOverLastTest() (deer.agent.NeuralAgent method)

train() (deer.agent.NeuralAgent method) (deer.base_classes.QNetwork method) (deer.q_networks.AC_net_keras.MyACNetwork method) (deer.q_networks.q_net_keras.MyQNetwork method) (deer.q_networks.q_net_theano.MyQNetwork method) TrainerController (class in deer.experiment.base_controllers)

U

updatePriorities() (deer.agent.DataSet method)