AndersonJo/dqn-pytorch

Possible issue in select_action method

Opened this issue · 0 comments

In code snippet below from select_action method, the input hidden state is taken from self.train_hidden_state.

But the output hidden state is saved in self.dqn_hidden_state. It seems the output hidden state should also go to self.train_hidden_state.

elif self.mode == 'lstm':
            action, self.dqn_hidden_state, self.dqn_cell_state = \
                self.dqn(states_variable, self.train_hidden_state, self.train_cell_state)

Is this an error or for some reason.