agent targets and agent start positions are always on seperate tracks

examples/flatland_2_0_example.py

@@ -28,9 +28,9 @@ speed_ration_map = {1.: 1.,  # Fast passenger train
                     1. / 3.: 0.,  # Slow commuter train
                     1. / 4.: 0.}  # Slow freight train
 
-env = RailEnv(width=100,
-              height=100,
-              rail_generator=sparse_rail_generator(num_cities=20,  # Number of cities in map (where train stations are)
+env = RailEnv(width=50,
+              height=50,
+              rail_generator=sparse_rail_generator(num_cities=10,  # Number of cities in map (where train stations are)
                                                    seed=10,  # Random seed
                                                    grid_mode=False,
                                                    max_inter_city_rails=2,

flatland/envs/schedule_generators.py

 """Schedule generators (railway undertaking, "EVU")."""
+import random
 import warnings
 from typing import Tuple, List, Callable, Mapping, Optional, Any
 
@@ -74,11 +75,13 @@ def sparse_schedule_generator(speed_ratio_map: Mapping[float, float] = None) ->
             # Set target for agent
             start_city = agent_start_targets_nodes[agent_idx][0]
             target_city = agent_start_targets_nodes[agent_idx][1]
+            start = random.choice(train_stations[start_city])
+            target = random.choice(train_stations[target_city])
+            while start[1] % 2 != 0:
+                start = random.choice(train_stations[start_city])
+            while target[1] % 2 != 1:
+                target = random.choice(train_stations[start_city])
 
-            start_city_idx = np.random.randint(len(train_stations[start_city]))
-            start = train_stations[start_city][start_city_idx]
-            target_station_idx = np.random.randint(len(train_stations[target_city]))
-            target = train_stations[target_city][target_station_idx]
             agent_orientation = (agent_start_targets_nodes[agent_idx][2] + 2 * start[1]) % 4
             if not rail.check_path_exists(start[0], agent_orientation, target[0]):
                 agent_orientation = (agent_orientation + 2) % 4