docs(ReforceXY): document efficiency coefficient min_range guard

diff --git a/ReforceXY/reward_space_analysis/README.md b/ReforceXY/reward_space_analysis/README.md
index 1f5956c25a00fdce2a488774f805f242cb4b60a3..62b583716d65bc38ffd6874485a6a69690b2ef7a 100644 (file)
--- a/ReforceXY/reward_space_analysis/README.md
+++ b/ReforceXY/reward_space_analysis/README.md
@@ -270,8 +270,11 @@ Let `pnl_target = profit_aim · risk_reward_ratio`,
 **Formula:**
 
 Let `max_u = max_unrealized_profit`, `min_u = min_unrealized_profit`,
-`range = max_u - min_u`, `ratio = (pnl - min_u)/range`. Then:
+`range = max_u - min_u`, `ratio = (pnl - min_u)/range`,
+`min_range = max(1e-6, 0.01 · pnl_target)`. Then:
 
+- If `range < min_range`: `efficiency_coefficient = 1` (guard against division
+  explosion)
 - If `pnl > 0`:
   `efficiency_coefficient = 1 + efficiency_weight · (ratio - efficiency_center)`
 - If `pnl < 0`: