diff --git a/reinforcement_learning/ppo/ppo_agent.py b/reinforcement_learning/ppo/ppo_agent.py index 07b20791dba7dcfbea5348635f1c5e6096d90d95..f213464782ce08b8da7d0e97d1f416c069ed4482 100644 --- a/reinforcement_learning/ppo/ppo_agent.py +++ b/reinforcement_learning/ppo/ppo_agent.py @@ -43,7 +43,7 @@ class DataBuffers: class PPOModelNetwork(nn.Module): def __init__(self, state_size, action_size, hidsize1=128, hidsize2=128): - super(DeepPPONetwork, self).__init__() + super(PPOModelNetwork, self).__init__() self.fc_layer_1_val = nn.Linear(state_size, hidsize1) self.shared_network = nn.Linear(hidsize1, hidsize2) self.fc_policy_pi = nn.Linear(hidsize2, action_size)