Hi Arun,
Arthur Juliani

Thanks for clearing on that!I would really appreciate if you could suggest any link/paper for this type of task.I understand games like Atari make use of image frames for learning.In Cartpole, we have list of 4 values as an observation rather than the images.So how can DQN be used in this scenario?

One clap, two clap, three clap, forty?

By clapping more or less, you can signal to us which stories really stand out.