-
Notifications
You must be signed in to change notification settings - Fork 6
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Maze Goal Generator #13
Conversation
gym_maze/maze.py
Outdated
PATH_MAPPING = 0 | ||
WALL_MAPPING = 1 | ||
REWARD_MAPPING = 9 | ||
|
||
STATE_ONE_STEP = 0 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
What does those states mean?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
They describe states of the goal generator. They are not really used right now, mostly for debugging or future use.
@@ -174,3 +183,27 @@ def get_possible_neighbour_cords(pos_x, pos_y) -> tuple: | |||
nw = (pos_x - 1, pos_y - 1) | |||
|
|||
return n, ne, e, se, s, sw, w, nw | |||
|
|||
def get_goal_state(self, current_x, current_y): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
What is this function returning? I assume some goal perception? How to interpret this?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It returns perception of the next goal state. It is used in Action Planning phase.
Please get rid of non-used code (it should only contain one that is necessary to run). Also, there are no tests of that functionality. |
Added goal generator for Maze environment