Comparison of Reinforcement Learning algorithms applied to the Cart Pole problem
This work addresses control challenges for complex systems like robotics, but it is incremental as it builds on existing RL methods applied to a benchmark problem.
The paper tackled the problem of controlling the nonlinear cartpole system without prior dynamics knowledge by comparing reinforcement learning algorithms like temporal-difference and policy gradient actor-critic against a standard LQR solution, and proposed integrating RL with swing-up controllers, achieving results such as comparisons with LQR but without specific numerical gains.
Designing optimal controllers continues to be challenging as systems are becoming complex and are inherently nonlinear. The principal advantage of reinforcement learning (RL) is its ability to learn from the interaction with the environment and provide optimal control strategy. In this paper, RL is explored in the context of control of the benchmark cartpole dynamical system with no prior knowledge of the dynamics. RL algorithms such as temporal-difference, policy gradient actor-critic, and value function approximation are compared in this context with the standard LQR solution. Further, we propose a novel approach to integrate RL and swing-up controllers.