Merge pull request #138 from davidmlin/patch

Correct Observation Space Description

src/overcooked_ai_py/mdp/overcooked_mdp.py

@@ -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
@@ -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