Dqn nonframe state

[kargarisaac]

• Add dqn for non-frame state spaces
• Add loading and evaluation code for the trained model

[kargarisaac]

Example_9 file contains using dqn for cartpole with a custom model and evaluation function.

[petrikvladimir]

Thank you! That explains why DQN did not work for my tasks. Your pull request is, however, quite complicated. Wouldn't just changing
self.replay_buffer = ReplayCls(**replay_kwargs) into
self.replay_buffer = ReplayCls(**replay_kwargs) if self.ReplayBufferCls is None else self.ReplayBufferCls(**replay_kwargs) in the DQN algorithm solve that issue?

[kargarisaac]

@petrikvladimir It does if you set the class as input. I just added the same settings as the atari env for non-atari envs to do it automatically.

[Adithya-MN]

@astooke, is there any issue with this merge? This would really be a useful functionality to have officially