-INPUT and OUTPUT OF ATARI DQN:
In the abstract paragraph of the DQN work by DeepMind https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf it has written:
" We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is a convolutional neural network, trained with a variant of Q-learning, whose input is raw pixels and whose output is a value function estimating future rewards. "
Would you please explain the bold sections?
• Input and output refer to Q-learning or DNN?
• Why it is said that learn control policy, however DQN is composed of QL which is a value iteration and"off-policy" algorithm and it is not a policy iteration and "on-policy"?
• What is the meaning of variant type of Q-learning is vague? it is variant because approximation of Q-learning is implemented?