diff --git a/reinforcement_learning/ppo_agent.py b/reinforcement_learning/ppo_agent.py
index d467cfeb018811fdfc3b8cda0ed6a1c6519d376f..9a43affc9993151a2b7ca39f372b1410d04a570a 100644
--- a/reinforcement_learning/ppo_agent.py
+++ b/reinforcement_learning/ppo_agent.py
@@ -34,7 +34,7 @@ class EpisodeBuffers:
 
 class ActorCriticModel(nn.Module):
 
-    def __init__(self, state_size, action_size, device, hidsize1=128, hidsize2=128):
+    def __init__(self, state_size, action_size, device, hidsize1=512, hidsize2=256):
         super(ActorCriticModel, self).__init__()
         self.device = device
         self.actor = nn.Sequential(