In: Computer Science
Answer)
1) Q Learning:
Q learning is defined to be a model-free reinforcement learning algorithm and the goal is to provide the policy that can say an agent about the actions taken under the circumstances which don't require the environmental model and there are stochastic transition and rewards with which the problems are handled.
2) As in reinforcement learning, every action which is being performed by the agent gets the rewards received by the Agent and all the state are in between the initial state as well as the terminal state hence in a similar manner the Q learning is also having a goal where one gets to learn the policy which states to an agent of what action is to be performed under what action.
3) As Q learning finds the policy which is optimal in a way which maximizes the expected value of the total reward to any or all the successive steps from that of the current step. It also helps in identifying the optimal selection policy.
It is mostly being used for coping with the problems where the number of the possible states as well as action scale faster and where an exact solution is no longer feasible.
4) Example:
Playing of the atari game, Robot being a part of the automobile industry etc
Hope this answer helps.
If you find the answer useful please hit like.
Thanks