Reinforcement learning enables agents to learn optimal behaviors through rewards and penalties, shaping their actions based on interactions with their environment. This work addresses the challenge of enabling a mobile robot to navigate environments like factory layouts or hospital settings while avoiding collisions with static and dynamic obstacles. The robot uses three proximity sensors to detect obstacles and employs a combination of Q-learning, a value-based reinforcement learning technique, and the A* algorithm, a heuristic-based search algorithm. Q-learning is effective for various state and action spaces and is widely used in robotics, game playing, and autonomous systems. However, it struggles with large state spaces. To overcome this, we use a hybrid approach that combines Q-learning with A*, facilitating faster learning and reduced computational time. The robot is trained in a grid-based environment, taking in Q-learning’s policy learning capabilities and A*’s efficient pathfinding through heuristic search. This ensures the robot can navigate dynamic environments more effectively.