Reinforcement Learning with TensorFlow

The Q-learning approach to reinforcement learning

Q-learning is an attempt to learn the value Q(s,a) of a specific action given to the agent in a particular state. Consider a table where the number of rows represent the number of states, and the number of columns represent the number of actions. This is called a Q-table. Thus, we have to learn the value to find which action is the best for the agent in a given state.

Steps involved in Q-learning:

1. Initialize the table of Q(s,a) with uniform values (say, all zeros).

2. Observe the current state, s

3. Choose an action, a, by epsilon greedy or any other action selection policies, and take the action

4. As a result, a reward, r, is received and a new state, s', is perceived

5. Update the Q value ...