mlpy.learners.online.rl.RLDTLearner¶
-
class
mlpy.learners.online.rl.
RLDTLearner
(planner, max_steps=None, filename=None, profile=False)[source]¶ Bases:
mlpy.learners.online.rl.RLLearner
Performs reinforcement learning using decision trees.
Reinforcement learning using decision trees (RL-DT) use decision trees to build the transition and reward models as described by Todd Hester and Peter Stone [R3].
Parameters: planner : IPlanner
The planner to use to determine the best action.
max_steps : int, optional
The maximum number of steps in an iteration. Default is 100.
filename : str, optional
The name of the file to save the learner state to after each iteration. If None is given, the learner state is not saved. Default is None.
profile : bool, optional
Turn on profiling at which point profiling data is collected and saved to a text file. Default is False.
References
[R3] (1, 2) Hester, Todd, and Peter Stone. “Generalized model learning for reinforcement learning in factored domains.” Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems-Volume 2. International Foundation for Autonomous Agents and Multiagent Systems, 2009. Attributes
mid
The module’s unique identifier. type
This learner is of type online. Methods
choose_action
(state)Choose the next action execute
(experience)Execute learning specific updates. learn
([experience])Learn a policy from the experience. load
(filename)Load the state of the module from file. reset
(t, **kwargs)Reset reinforcement learner. save
(filename)Save the learners state.