contents.m

来自「approximate reinforcement learning」· M 代码 · 共 11 行

% System (problem) definitions for approximate RL
%
% sample_problem    - Specification for problem definition function
% sample_mdp        - Specification for MDP (Markov decision process) definition function
%
% Subdirectories:
% /nav              - Navigation system
% /doubleint        - Double integrator
% /simpleint        - Simple discrete-time integrator
% /simplewalker     - Simple passive dynamic walker