Caesar AI Atlas

State–action–reward–state–action

Caesar AI Atlas Definition

State–action–reward–state–action is a reinforcement learning algorithm commonly known as SARSA. It learns a policy by updating value estimates from observed transitions that include the current state, action, reward, next state, and next action.

Other Definitions

State–action–reward–state–action Source

A reinforcement learning algorithm for learning a Markov decision process policy.

Related Terms