Sheep training flock _ improver

training/herding_env.py

@@ -63,6 +63,11 @@ class HerdingEnv(gym.Env):
     ALIGN_SHAPE = "standoff"   # "standoff" (peaks at IDEAL) | "near" (peaks at 0)
     ALIGN_GATED = True   # gate alignment on action magnitude
 
+    # Initial sheep spawn: first sheep placed anywhere; rest within CLUSTER_RADIUS
+    # of it. Set to None for legacy uniform-scatter behaviour.
+    # Cluster radius ≤ COHESION_DIST (8m) so boid cohesion keeps the flock together.
+    INIT_CLUSTER_RADIUS = 5.0
+
     def __init__(self, n_sheep: int = 1, max_steps: int = 2000,
                  render_mode: str = None, random_n_sheep: bool = False,
                  reward_cfg: dict = None):
@@ -129,12 +134,25 @@ class HerdingEnv(gym.Env):
         self.sheep_pos[:] = self.PEN_CENTER
         self.penned[:]    = True
 
+        # Spawn first sheep anywhere; subsequent sheep clustered around it
+        # so boid cohesion (active within 8m) keeps the flock together.
+        # Without clustering, sheep can start 25m apart and never coalesce —
+        # task becomes intractable for n_sheep ≥ 2.
         placed = 0
+        cluster_center = None
+        radius = self.INIT_CLUSTER_RADIUS
         while placed < self.n_sheep:
-            p = self.np_random.uniform(-12.0, 12.0, size=(2,)).astype(np.float32)
+            if placed == 0 or radius is None:
+                p = self.np_random.uniform(-12.0, 12.0, size=(2,)).astype(np.float32)
+            else:
+                offset = self.np_random.uniform(-radius, radius, size=(2,))
+                p = (cluster_center + offset).astype(np.float32)
+                p = np.clip(p, -12.0, 12.0)
             if not self._in_pen(p):
                 self.sheep_pos[placed] = p
                 self.penned[placed]    = False
+                if placed == 0:
+                    cluster_center = p.copy()
                 placed += 1
 
         # Dog: 50% of resets start already behind the flock (anti-pen side,