fix ALNS rewards and tabu diversification

PROGRESS.md

@@ -41,3 +41,21 @@ python src/experiments/run_main_comparison.py --config paper --seeds 30 --iterat
 ### Interpretation rule
 - Check whether Static > TA-Greedy > ALNS-Base > T-ALNS > T-ALNS-RRD in total cost, CES decreases, and OTDR improves.
 - If the paper trend is not reproduced, keep the generated tables and record the failed metrics honestly instead of tuning results by hand.
+
+## 2026-06-02 follow-up algorithm fidelity fix
+
+### Findings addressed
+- ALNS, T-ALNS, and T-ALNS-RRD did not distinguish `sigma_2` current-solution improvements from `sigma_3` simulated-annealing accepted non-improving moves.
+- T-ALNS diversification intensity used adaptive Tabu tenure instead of the paper's actual move-memory occupancy `|T_move| / |T_move|max`.
+
+### Changes made
+- Reward assignment now follows the paper's four levels:
+  - `reward_global_best` for new global best.
+  - `reward_improvement` for accepted moves that improve the previous current solution.
+  - `reward_accepted` for accepted non-improving moves.
+  - `reward_rejected` for rejected moves.
+- Added `MoveTabu.utilization` and changed Eq.27 diversification intensity to use actual move Tabu list occupancy.
+
+### Local validation
+- Per user instruction, no local Python tests, smoke tests, or full experiments were run.
+- Static checks only: source inspection and `git diff --check`.

t_alns_rrd_reproduction/src/alns/alns_base.py

@@ -207,6 +207,7 @@ class ALNSBase:
                 new_cost = self.cost_calc.compute_total_cost(S_new, self.ctx)
 
                 # Acceptance decision (Eq.20)
+                previous_cost = current_cost
                 if sa.accept(current_cost, new_cost):
                     S_current = S_new
                     current_cost = new_cost
@@ -216,9 +217,12 @@ class ALNSBase:
                         best_cost = new_cost
                         stall_counter = 0
                         reward = self.cfg["reward_global_best"]
-                    else:
+                    elif new_cost < previous_cost:
                         stall_counter += 1
                         reward = self.cfg["reward_improvement"]
+                    else:
+                        stall_counter += 1
+                        reward = self.cfg["reward_accepted"]
                 else:
                     reward = self.cfg["reward_rejected"]
 

t_alns_rrd_reproduction/src/rrd/t_alns_rrd.py

@@ -285,6 +285,7 @@ class TALNSRRD:
                 new_cost = self.cost_calc.compute_total_cost(S_new, self.ctx)
 
                 # Acceptance
+                previous_cost = current_cost
                 if sa.accept(current_cost, new_cost):
                     S_current = S_new
                     current_cost = new_cost
@@ -300,10 +301,14 @@ class TALNSRRD:
                         last_best_iter = iter_count
                         self.talns.move_tabu.update_tenure(found_improvement=True)
                         reward = self.cfg["reward_global_best"]
+                    elif new_cost < previous_cost:
+                        stall_counter += 1
+                        self.talns.move_tabu.update_tenure(found_improvement=True)
+                        reward = self.cfg["reward_improvement"]
                     else:
                         stall_counter += 1
                         self.talns.move_tabu.update_tenure(found_improvement=False)
-                        reward = self.cfg["reward_improvement"]
+                        reward = self.cfg["reward_accepted"]
                     accepted = True
                 else:
                     reward = self.cfg["reward_rejected"]

t_alns_rrd_reproduction/src/tabu/move_tabu.py

@@ -75,6 +75,11 @@ class MoveTabu:
         while len(self._entries) > self.tenure_max:
             self._entries.popleft()
 
+    @property
+    def utilization(self) -> float:
+        """Normalized |T_move| / |T_move|max for Eq.27 diversification."""
+        return len(self._entries) / max(self.tenure_max, 1)
+
     def update_tenure(self, found_improvement: bool):
         """Adapt tenure based on improvement (Eq.32).
 

t_alns_rrd_reproduction/src/tabu/t_alns.py

@@ -160,8 +160,9 @@ class TALNS:
         # Time since last improvement (normalized)
         time_factor = (current_iter - last_best_iter) / max(t_max, 1)
 
-        # Move Tabu utilization
-        move_factor = self.move_tabu.tenure / self.cfg["move_tabu_tenure_max"]
+        # Move Tabu utilization: Eq.27 uses actual memory occupancy |T_move|,
+        # not the adaptive tenure parameter from Eq.32.
+        move_factor = self.move_tabu.utilization
 
         # Frequency std
         freq_std = self.freq_mem.get_std_assignment_freq()
@@ -379,6 +380,7 @@ class TALNS:
                 new_cost = self.cost_calc.compute_total_cost(S_new, self.ctx)
 
                 # Acceptance decision
+                previous_cost = current_cost
                 if sa.accept(current_cost, new_cost):
                     S_current = S_new
                     current_cost = new_cost
@@ -398,10 +400,14 @@ class TALNS:
                         last_best_iter = iter_count
                         self.move_tabu.update_tenure(found_improvement=True)
                         reward = self.cfg["reward_global_best"]
+                    elif new_cost < previous_cost:
+                        stall_counter += 1
+                        self.move_tabu.update_tenure(found_improvement=True)
+                        reward = self.cfg["reward_improvement"]
                     else:
                         stall_counter += 1
                         self.move_tabu.update_tenure(found_improvement=False)
-                        reward = self.cfg["reward_improvement"]
+                        reward = self.cfg["reward_accepted"]
                     accepted = True
                 else:
                     reward = self.cfg["reward_rejected"]