Man pages for MDPtoolbox
Markov Decision Processes Toolbox

mdp_bellman_operatorApplies the Bellman operator
mdp_checkChecks the validity of a MDP
mdp_check_square_stochasticChecks if a matrix is square and stochastic
mdp_computePpolicyPRpolicyComputes the transition matrix and the reward matrix for a...
mdp_computePRComputes a reward matrix for any form of transition and...
mdp_eval_policy_iterativeEvaluates a policy using an iterative method
mdp_eval_policy_matrixEvaluates a policy using matrix inversion and product
mdp_eval_policy_optimalityComputes sets of 'near optimal' actions for each state
mdp_eval_policy_TD_0Evaluates a policy using the TD(0) algorithm
mdp_example_forestGenerates a MDP for a simple forest management problem
mdp_example_randGenerates a random MDP problem
mdp_finite_horizonSolves finite-horizon MDP using backwards induction algorithm
mdp_LPSolves discounted MDP using linear programming algorithm
mdp_policy_iterationSolves discounted MDP using policy iteration algorithm
mdp_policy_iteration_modifiedSolves discounted MDP using modified policy iteration...
mdp_Q_learningSolves discounted MDP using the Q-learning algorithm...
mdp_relative_value_iterationSolves MDP with average reward using relative value iteration...
mdp_spanEvaluates the span of a vector
MDPtoolbox-packageMarkov Decision Processes Toolbox
mdp_value_iterationSolves discounted MDP using value iteration algorithm
mdp_value_iteration_bound_iterComputes a bound for the number of iterations for the value...
mdp_value_iterationGSSolves discounted MDP using Gauss-Seidel's value iteration...
MDPtoolbox documentation built on May 30, 2017, 5:15 a.m.