Solving The Lunar Lander Problem under Uncertainty using Reinforcement Learning
This paper explores the application and robustness of existing reinforcement learning techniques for the Lunar Lander problem, providing an incremental comparison for researchers working on control problems under uncertainty.
This paper applies Sarsa and Deep Q-Learning to the LunarLander-v2 environment, achieving average rewards of 170+ and 200+ respectively. The study further demonstrates the robustness of these techniques by introducing additional uncertainty, where both agents still achieve positive average rewards of 100+.
Reinforcement Learning (RL) is an area of machine learning concerned with enabling an agent to navigate an environment with uncertainty in order to maximize some notion of cumulative long-term reward. In this paper, we implement and analyze two different RL techniques, Sarsa and Deep QLearning, on OpenAI Gym's LunarLander-v2 environment. We then introduce additional uncertainty to the original problem to test the robustness of the mentioned techniques. With our best models, we are able to achieve average rewards of 170+ with the Sarsa agent and 200+ with the Deep Q-Learning agent on the original problem. We also show that these techniques are able to overcome the additional uncertainities and achieve positive average rewards of 100+ with both agents. We then perform a comparative analysis of the two techniques to conclude which agent peforms better.