A Comparison of Reward Functions in Q-Learning Applied to a Cart Position Problem
This work addresses reward function selection for control tasks in reinforcement learning, but it is incremental as it applies known methods to a specific problem.
The paper tackled the cart position problem by comparing three reward functions in Q-learning, finding that a discontinuous reward function providing non-zero rewards only within a specific distance from the target position yielded the best results.
Growing advancements in reinforcement learning has led to advancements in control theory. Reinforcement learning has effectively solved the inverted pendulum problem and more recently the double inverted pendulum problem. In reinforcement learning, our agents learn by interacting with the control system with the goal of maximizing rewards. In this paper, we explore three such reward functions in the cart position problem. This paper concludes that a discontinuous reward function that gives non-zero rewards to agents only if they are within a given distance from the desired position gives the best results.