mlpy.mdp.continuous.casml.CASML¶
-
class
mlpy.mdp.continuous.casml.
CASML
(cbtdata, cbvdata=None, ncomponents=1, proba_calc_method=None, actions=None, n_init=1, **kwargs)[source]¶ Bases:
mlpy.mdp.IMDPModel
Continuous Action and State Model Learner (CASML).
Parameters: cbtdata : CbTData
The transition case base data.
cbvdata : CbVData
The value case base data.
ncomponents : int, optional
Number of states of the hidden Markov model. Default is 1.
proba_calc_method : str, optional
The method used to calculate the probability distribution for the initial states. Default is DefaultProbaCalcMethod.
actions : list or dict, optional
A list of possible discrete actions.
Attributes
cases
experience
mid
The module’s unique identifier. Methods
fit
(obs, actions[, rewards, n_init])Fit the CaseBase
and theHMM
.get_actions
([state])Retrieve the available actions for the given state. init
()Initialize the MDP model. load
(filename)Load the state of the module from file. predict_proba
(state, action)Predict the probability distribution. retrieve
(case_base, state, action[, ...])sample
([state, action])Sample from the probability distribution. save
(filename)Save the current state of the module to file. update
(experience)Update the model with the agent’s experience.