文件名称:MDPtoolbox
介绍说明--下载内容均来自于网络,请自行研究使用
MDP代码,动态规划,基于马尔可夫决策过程,可以实现全局最优。-MDP code, dynamic programming, Markov decision process, we can achieve the global optimum
(系统自动生成,下载前可以参看下载内容)
下载文件列表
MDPtoolbox\mdp_bellman_operator.m
..........\mdp_example_rand.m
..........\mdp_eval_policy_optimality.m
..........\README
..........\mdp_value_iterationGS.m
..........\mdp_eval_policy_matrix.m
..........\mdp_check.m
..........\documentation\mdp_eval_policy_TD_0.html
..........\.............\mdp_value_iteration_bound_iter.html
..........\.............\QuickStart.pdf
..........\.............\mdp_computePR.html
..........\.............\mdp_policy_iteration.html
..........\.............\mdp_check_square_stochastic.html
..........\.............\index_category.html
..........\.............\mdp_eval_policy_iterative.html
..........\.............\mdp_value_iteration.html
..........\.............\mdp_check.html
..........\.............\mdp_Q_learning.html
..........\.............\DOCUMENTATION.html
..........\.............\mdp_LP.html
..........\.............\mdp_computePpolicyPRpolicy.html
..........\.............\mdp_verbose_silent.html
..........\.............\mdp_relative_value_iteration.html
..........\.............\arrow.gif
..........\.............\mdp_bellman_operator.html
..........\.............\mdp_value_iterationGS.html
..........\.............\mdp_eval_policy_optimality.html
..........\.............\index_alphabetic.html
..........\.............\mdp_span.html
..........\.............\mdp_eval_policy_matrix.html
..........\.............\mdp_example_forest.html
..........\.............\mdp_finite_horizon.html
..........\.............\mdp_policy_iteration_modified.html
..........\.............\mdp_example_rand.html
..........\.............\meandiscrepancy.jpg
..........\mdp_relative_value_iteration.m
..........\mdp_eval_policy_TD_0.m
..........\AUTHORS
..........\mdp_value_iteration_bound_iter.m
..........\mdp_computePR.m
..........\mdp_eval_policy_iterative.m
..........\mdp_computePpolicyPRpolicy.m
..........\mdp_check_square_stochastic.m
..........\mdp_LP.m
..........\mdp_silent.m
..........\mdp_example_forest.m
..........\mdp_verbose.m
..........\mdp_finite_horizon.m
..........\mdp_policy_iteration.m
..........\mdp_span.m
..........\COPYING
..........\mdp_Q_learning.m
..........\mdp_policy_iteration_modified.m
..........\mdp_value_iteration.m
license.txt