Fix equation of IQL docstring

takuseno · Jun 17, 2023 · b11edfa · b11edfa
1 parent 09ade95
commit b11edfa
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/d3rlpy/algos/qlearning/iql.py b/d3rlpy/algos/qlearning/iql.py
@@ -42,7 +42,7 @@ class IQLConfig(LearnableConfig):
 
     .. math::
 
-        L_Q(\theta) = \mathbb{E}_{(s, a, r, a') \sim D}
+        L_Q(\theta) = \mathbb{E}_{(s, a, r, s') \sim D}
             [(r + \gamma V_\psi(s') - Q_\theta(s, a))^2]
 
     Finally, the policy function is trained by using advantage weighted