Regarding the output of DQN

[KitanoFumiya]

I would like to use DQN to control the field degree of freedom robot arm. However, the DQN in this library has only one output if the action space is discrete. In the case of multiple degrees of freedom, do we have to use a neural network for each joint?

[muupan]

DQN is usually applied to a discrete action space. If you want to tackle a continuous vector-valued action space, I recommend using other algorithms like the ones under https://github.com/chainer/chainerrl/tree/master/examples/mujoco/reproduction.