diff --git a/docs/docs/ml.xml b/docs/docs/ml.xml index 50a8c5944..4e478832a 100644 --- a/docs/docs/ml.xml +++ b/docs/docs/ml.xml @@ -135,6 +135,10 @@ Davis E. King. assignment_function track_association_function graph_labeler + policy
@@ -252,6 +257,7 @@ Davis E. King. + + + + lspi + dlib/control.h + dlib/control/lspi_abstract.h + + This object is an implementation of the reinforcement learning algorithm + described in the following paper: +
+ Lagoudakis, Michail G., and Ronald Parr. "Least-squares policy + iteration." The Journal of Machine Learning Research 4 (2003): + 1107-1149. +
+ +
+
+ + + + + policy + dlib/control.h + dlib/control/approximate_linear_models_abstract.h + + This is a policy (i.e. a control law) based on a linear function approximator. + You can use a tool like
lspi to learn the parameters + of a policy. + + + + + + + process_sample + dlib/control.h + dlib/control/approximate_linear_models_abstract.h + + This object holds a training sample for a reinforcement learning algorithm + (e.g. lspi). + In particular, it contains a state, action, reward, next state sample from + some process. + + + diff --git a/docs/docs/term_index.xml b/docs/docs/term_index.xml index 381a44569..76c4790bc 100644 --- a/docs/docs/term_index.xml +++ b/docs/docs/term_index.xml @@ -267,6 +267,9 @@ + + +