robotics_project_Q-Learning
For a mobile robot generally, the essential goal has defined a strategy that allows it to reach the goal from the starting point without collisions and an optimal path to its destination. In our project we aim and seek through experimentation to make our robot evolve in the right direction in its environment: avoidance of obstacles, recognition of the path to move easily from one point to another in the environment, and in particular, execute the scripts by varying the parameters alpha, gamma, epsilon and the number of episodes in order to see for which combination of these values there is optimization of the path and minimization of the number of steps (steps) for each episode and let's increase them cumulative rewards for our robot.
