Uses of Interface
org.tweetyproject.machinelearning.rl.mdp.Action
Package
Description
-
Uses of Action in org.tweetyproject.machinelearning.rl.mdp
Modifier and TypeClassDescriptionclass
This class models an episode in MPDs, i.e.class
FixedPolicy<S extends State,
A extends Action> A fixed policy for MDPs, i.e., a simple map from states to actions.class
MarkovDecisionProcess<S extends State,
A extends Action> This class models a Markov Decision Process (MDP, for fixed starting and terminal states), which can be used to represent reinforcement learning scenarios.interface
A policy (map from states to actions) for Markov Decision ProcessModifier and TypeClassDescriptionclass
An action in a Markov Decision Process that is solely characterized through its name. -
Uses of Action in org.tweetyproject.machinelearning.rl.mdp.algorithms
Modifier and TypeClassDescriptionclass
IterativePolicyEvaluation<S extends State,
A extends Action> Determines utilities iteratively.class
OfflineAlgorithm<S extends State,
A extends Action> A general interface for algorithms to determine optimal policies directly from an MDPinterface
PolicyEvaluation<S extends State,
A extends Action> The `PolicyEvaluation` interface provides methods to evaluate the utility of states in a Markov Decision Process (MDP) with respect to a given policy.class
PolicyIteration<S extends State,
A extends Action> The policy iteration algorithm for determining optimal policiesclass
ValueIteration<S extends State,
A extends Action> The value iteration algorithm for determining optimal policies