Skip to content
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

Correct Observation Space Description #138

Merged
merged 2 commits into from
Apr 11, 2024
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions src/overcooked_ai_py/mdp/overcooked_mdp.py
Original file line number Diff line number Diff line change
Expand Up @@ -2594,10 +2594,9 @@ def featurize_state(self, overcooked_state, mlam, num_pots=2, **kwargs):

[player_i_features, other_player_features player_i_dist_to_other_players, player_i_position]

player_{i}_features (length num_pots*10 + 24):
player_{i}_features (length num_pots*10 + 28):
pi_orientation: length 4 one-hot-encoding of direction currently facing
pi_obj: length 4 one-hot-encoding of object currently being held (all 0s if no object held)
pi_wall_{j}: {0, 1} boolean value of whether player i has wall immediately in direction j
pi_closest_{onion|tomato|dish|soup|serving|empty_counter}: (dx, dy) where dx = x dist to item, dy = y dist to item. (0, 0) if item is currently held
pi_cloest_soup_n_{onions|tomatoes}: int value for number of this ingredient in closest soup
pi_closest_pot_{j}_exists: {0, 1} depending on whether jth closest pot found. If 0, then all other pot features are 0. Note: can
Expand All @@ -2606,6 +2605,7 @@ def featurize_state(self, overcooked_state, mlam, num_pots=2, **kwargs):
pi_closest_pot_{j}_{num_onions|num_tomatoes}: int value for number of this ingredient in jth closest pot
pi_closest_pot_{j}_cook_time: int value for seconds remaining on soup. -1 if no soup is cooking
pi_closest_pot_{j}: (dx, dy) to jth closest pot from player i location
pi_wall: length 4 boolean value of whether player i has wall in each direction

other_player_features (length (num_players - 1)*(num_pots*10 + 24)):
ordered concatenation of player_{j}_features for j != i
Expand Down
Loading