Because TensorFlow requires numeric arrays and input parameters to learn the mapping between them when building a Recurrent Neural Network (RNN) model, this function transforms simulated data into a standardized dataset and invokes TensorFlow to train the model.
engine_RNN(
data,
colnames,
behrule,
model,
funcs = NULL,
priors,
settings = NULL,
control = control,
...
)A specialized TensorFlow-trained Recurrent Neural Network (RNN) object.
The model can be used with the predict() function to make predictions
on a new data frame, estimating the input parameters that are most likely
to have generated the given dataset.
A data frame in which each row represents a single trial, see data
Column names in the data frame, see colnames
The agent’s implicitly formed internal rule, see behrule
Reinforcement Learning Model
The functions forming the reinforcement learning model, see funcs
Prior probability density function of the free parameters, see priors
Other model settings, see settings
Settings manage various aspects of the iterative process, see control
Additional arguments passed to internal functions.