| Interface | Description |
|---|---|
| ActionsFunction<S,A extends Action> |
An interface for MDP action functions.
|
| MarkovDecisionProcess<S,A extends Action> |
Artificial Intelligence A Modern Approach (3rd Edition): page 647.
A sequential decision problem for a fully observable, stochastic environment with a Markovian transition model and additive rewards is called a Markov decision process, or MDP, and consists of a set of states (with an initial state s0; a set ACTIONS(s) of actions in each state; a transition model P(s' | s, a); and a reward function R(s). Note: Some definitions of MDPs allow the reward to depend on the action and outcome too, so the reward function is R(s, a, s'). |
| Policy<S,A extends Action> |
Artificial Intelligence A Modern Approach (3rd Edition): page 647.
A solution to a Markov decision process is called a policy. |
| PolicyEvaluation<S,A extends Action> |
Artificial Intelligence A Modern Approach (3rd Edition): page 656.
Given a policy πi, calculate Ui=Uπi, the utility of each state if πi were to be executed. |
| RewardFunction<S> |
An interface for MDP reward functions.
|
| TransitionProbabilityFunction<S,A extends Action> |
An interface for MDP transition probability functions.
|