qlearning111_Q-learning_路径规划_matlab

%clc load('maze.mat') num_of_iteration = 2000; N = 5; r = 20; gamma = 0.8; learning_rate = 0.1; actions = 4; % North, East, West, South (N, E, W, S) exploration_rate = 0.4; action_matrix = [-5 1 -1 5 ]; %maze = create_random_maze(N, r); q_matrix = construct_q_matrix(N, actions);%25*4 i = 1; reward = 0; trace_index =[]; sum_reward=0; sum_i=0; for episode = 1 : num_of_iteration initial_state = N*N; goal_state = 1; current_state = initial_state; while current_state ~= goal_state if rand < exploration_rate eliminate_inf = find(q_matrix(current_state, :) > -inf); prefered_action = eliminate_inf(randi(numel(eliminate_inf))); else [temp_value, prefered_action] = max( q_matrix(current_state,:) ); temp_value; end % receive immediate reward maze_exp_index = current_state + action_matrix(prefered_action); trace_index(i) = maze_exp_index; i = i + 1; if maze(maze_exp_index) == 1 reward = -40; else reward = -1; end q_matrix(current_state, prefered_action) = ... (1-learning_rate) * q_matrix(current_state, prefered_action)+... learning_rate * (reward + gamma * max(q_matrix(maze_exp_index,:))); % observe new state current_state = maze_exp_index ; sum_reward = sum_reward+reward; end summ_reward(episode)=sum_reward; sum_reward=0; summ_i(episode)=i; end maze; q_matrix; figure(1) plot(summ_reward(1,1:num_of_iteration)); figure(2) for k=2:num_of_iteration step_number(k)=summ_i(k)-summ_i(k-1); end plot(step_number(1,1:num_of_iteration)); % % ———————————————— % % 版权声明：本文为CSDN博主「jjx1995712」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。 % % 原文链接：https://blog.csdn.net/jjx1995712/article/details/83417954