Издательство: | Bookvika publishing |
ISBN: | 978-5-5118-0226-8 |
High Quality Content by WIKIPEDIA articles! SARSA (State-Action-Reward-State-Action) is an algorithm for learning a Markov decision process policy, used in the reinforcement learning area of machine learning. It was introduced in the technical note "Online Q-Learning using Connectionist Systems" by Rummery Niranjan (1994) where the alternative name SARSA was only mentioned as a footnote.