[et_pb_section fb_built=”1″ _builder_version=”4.16″ _module_preset=”default” global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_row _builder_version=”4.16″ _module_preset=”default” background_size=”initial” background_position=”top_left” background_repeat=”repeat” global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_column type=”4_4″ _builder_version=”4.16″ _module_preset=”default” custom_padding=”|||” global_colors_info=”{}” custom_padding__hover=”|||” theme_builder_area=”post_content”][et_pb_text _builder_version=”4.16″ _module_preset=”0eb20e7f-3c16-46bb-9826-a50862b0674a” background_size=”initial” background_position=”top_left” background_repeat=”repeat” global_colors_info=”{}” theme_builder_area=”post_content”]<\/p>\n
<\/span><\/p>\n This is a Q learner object.<\/p>\n Update the Q table and return an action<\/p>\n The selected action<\/p>\n<\/dd>\n int<\/p>\n<\/dd>\n<\/dl>\n<\/dd>\n<\/dl>\n Update the state without updating the Q-table<\/p>\n s<\/strong> (int<\/em>) \u2013 The new state<\/p>\n<\/dd>\n The selected action<\/p>\n<\/dd>\n int<\/p>\n<\/dd>\n<\/dl>\n<\/dd>\n<\/dl>\n<\/dd>\n<\/dl>\n <\/span><\/p>\n <\/span><\/p>\n <\/span><\/p>\n <\/span><\/p>\n <\/span><\/p>\n convert the location to a single integer<\/p>\n pos<\/strong> (int<\/em>, <\/em>int<\/em>) \u2013 the position to discretize<\/p>\n<\/dd>\n the discretized position<\/p>\n<\/dd>\n int<\/p>\n<\/dd>\n<\/dl>\n<\/dd>\n<\/dl>\n find where the goal is in the map<\/p>\n data<\/strong> (array<\/em>) \u2013 2D array that stores the map<\/p>\n<\/dd>\n the position of the goal<\/p>\n<\/dd>\n tuple(int, int)<\/p>\n<\/dd>\n<\/dl>\n<\/dd>\n<\/dl>\n Finds where the robot is in the map<\/p>\n data<\/strong> (array<\/em>) \u2013 2D array that stores the map<\/p>\n<\/dd>\n the position of the robot<\/p>\n<\/dd>\n int, int<\/p>\n<\/dd>\n<\/dl>\n<\/dd>\n<\/dl>\n move the robot and report reward<\/p>\n the new position of the robot and the reward<\/p>\n<\/dd>\n tuple(int, int), int<\/p>\n<\/dd>\n<\/dl>\n<\/dd>\n<\/dl>\n Prints out the map<\/p>\n data<\/strong> (array<\/em>) \u2013 2D array that stores the map<\/p>\n<\/dd>\n<\/dl>\n<\/dd>\n<\/dl>\n function to test the code<\/p>\n the total reward<\/p>\n<\/dd>\n np.float64<\/p>\n<\/dd>\n<\/dl>\n<\/dd>\n<\/dl>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n <\/p>\n <\/p>\n\n
QLearner.<\/code>QLearner<\/code>(<\/span>num_states=100<\/em>, num_actions=4<\/em>, alpha=0.2<\/em>, gamma=0.9<\/em>, rar=0.5<\/em>, radr=0.99<\/em>, dyna=0<\/em>, verbose=False<\/em>)<\/span><\/dt>\n\n
\n
\n
query<\/code>(<\/span>s_prime<\/em>, r<\/em>)<\/span><\/dt>\n\n
\n
\n
querysetstate<\/code>(<\/span>s<\/em>)<\/span><\/dt>\n\n
testqlearner.py<\/span><\/span><\/h2>\n
\n
discretize<\/code>(<\/span>pos<\/em>)<\/span><\/dt>\n\n
\n
getgoalpos<\/code>(<\/span>data<\/em>)<\/span><\/dt>\n\n
\n
getrobotpos<\/code>(<\/span>data<\/em>)<\/span><\/dt>\n\n
\n
movebot<\/code>(<\/span>data<\/em>, oldpos<\/em>, a<\/em>)<\/span><\/dt>\n\n
\n
\n
printmap<\/code>(<\/span>data<\/em>)<\/span><\/dt>\n\n
\n
test<\/code>(<\/span>map<\/em>, epochs<\/em>, learner<\/em>, verbose<\/em>)<\/span><\/dt>\n\n
\n
If verbose = False your code should not generate ANY output. When we test your code, verbose will be False.<\/li>\n<\/ul>\n<\/dd>\n