Tag SARSA

Understanding SARSA: Finite-Sample Analysis and Its Impact on Reinforcement Learning

Machine Learning reinforcement learning SARSA function approximation

In the world of reinforcement learning, few algorithms have gained as much attention as SARSA (State-Action-Reward-State-Action). This on-policy algorithm is designed to learn optimal policies in Markov decision processes (MDPs). The recent research conducted by Shaofeng Zou, Tengyu Xu, and… Continue Reading →

Theme by Anders Noren — Up ↑

Tag SARSA

Understanding SARSA: Finite-Sample Analysis and Its Impact on Reinforcement Learning

STAY IN THE LOOP