Research Article
A Path-Planning Approach Based on Potential and Dynamic Q-Learning for Mobile Robots in Unknown Environment
Algorithm 1
Classical Q-learning pseudocode.
(1) | Initiate and in Q-table to zero | (2) | Select a starting state | (3) | for each step of episode do | (4) | while is not terminal do | (5) | Select and execute it | (6) | Receive an immediate reward | (7) | Observe the next state | (8) | Update the table entry by | (9) | | (10) | | (11) | Until is the terminal state | (12) | end while | (13) | end for | (14) | Output optimal policy |
|