refactor(reforcexy): remove uneeded rewarding param

Signed-off-by: Jérôme Benoit <jerome.benoit@piment-noir.org>

diff --git a/ReforceXY/reward_space_analysis/reward_space_analysis.py b/ReforceXY/reward_space_analysis/reward_space_analysis.py
index cdddc640b9ba0346f541292fe5bcf1900a2ee84e..eae0fd96a4dc5aadc84f7c83f2fbbfd095c1a258 100644 (file)
--- a/ReforceXY/reward_space_analysis/reward_space_analysis.py
+++ b/ReforceXY/reward_space_analysis/reward_space_analysis.py
@@ -353,19 +353,15 @@ def _get_exit_factor(
         return f / (1.0 + exit_linear_slope * dr)
 
     def _power_kernel(f: float, dr: float) -> float:
-        alpha = params.get("exit_power_alpha")
-        if isinstance(alpha, (int, float)) and alpha < 0.0:
-            alpha = None
-        if alpha is None:
-            tau = params.get("exit_power_tau")
-            if isinstance(tau, (int, float)):
-                tau = float(tau)
-                if 0.0 < tau <= 1.0:
-                    alpha = -math.log(tau) / _LOG_2
-        if not isinstance(alpha, (int, float)):
-            alpha = 1.0
+        tau = params.get("exit_power_tau")
+        if isinstance(tau, (int, float)):
+            tau = float(tau)
+            if 0.0 < tau <= 1.0:
+                alpha = -math.log(tau) / _LOG_2
+            else:
+                alpha = 1.0
         else:
-            alpha = float(alpha)
+            alpha = 1.0
         return f / math.pow(1.0 + dr, alpha)
 
     def _half_life_kernel(f: float, dr: float) -> float:

diff --git a/ReforceXY/user_data/freqaimodels/ReforceXY.py b/ReforceXY/user_data/freqaimodels/ReforceXY.py
index 21d3bd4234e05e800a982d62054f3d4f228cd3bc..6912281753b46d08a6d3aff83f5b167e2c987d0f 100644 (file)
--- a/ReforceXY/user_data/freqaimodels/ReforceXY.py
+++ b/ReforceXY/user_data/freqaimodels/ReforceXY.py
@@ -1419,19 +1419,15 @@ class MyRLEnv(Base5ActionRLEnv):
             return f / (1.0 + slope * dr)
 
         def _power(f: float, dr: float, p: Mapping) -> float:
-            alpha = p.get("exit_power_alpha")
-            if isinstance(alpha, (int, float)) and alpha < 0.0:
-                alpha = None
-            if alpha is None:
-                tau = p.get("exit_power_tau")
-                if isinstance(tau, (int, float)):
-                    tau = float(tau)
-                    if 0.0 < tau <= 1.0:
-                        alpha = -math.log(tau) / ReforceXY._LOG_2
-            if not isinstance(alpha, (int, float)):
-                alpha = 1.0
+            tau = p.get("exit_power_tau")
+            if isinstance(tau, (int, float)):
+                tau = float(tau)
+                if 0.0 < tau <= 1.0:
+                    alpha = -math.log(tau) / ReforceXY._LOG_2
+                else:
+                    alpha = 1.0
             else:
-                alpha = float(alpha)
+                alpha = 1.0
             return f / math.pow(1.0 + dr, alpha)
 
         def _half_life(f: float, dr: float, p: Mapping) -> float: