why duelingDQN does not have obversation size?

[WuMing757]

I thought DuelingDQN is similar to DQN and they have same inputs. But the implementation of DuelingDQN in q_functions does not have the obs_size variable, which confuses me. How does it know the dimension of inputs? Besides, I got an Error when I replace DQN with DuelingDQN: RuntimeError: Expected 4-dimensional input for 4-dimensional weight [32, 2, 8, 8], but got 2-dimensional input of size [1, 2] instead

[WuMing757]

I tried it in the train_dqn_gym.py. https://github.com/pfnet/pfrl/blob/master/examples/gym/train_dqn_gym.py

[muupan]

The DuelingDQN class under pfrl.q_functions is designed for Atari games. To use a dueling network architecture for other tasks, you can implement a model similar to the DuelingDQN class and pass it to the DQN agent.

[WuMing757]

The DuelingDQN class under pfrl.q_functions is designed for Atari games. To use a dueling network architecture for other tasks, you can implement a model similar to the DuelingDQN class and pass it to the DQN agent.

Thank you ~