Definition
State-Action-Reward-State-Action: An on-policy reinforcement learning algorithm that updates the quality (Q-value) of a state-action pair based on the *next* action taken by the current policy.
In short: State-Action-Reward-State-Action: An on-policy reinforcement learning algorithm that updates the quality (Q-value) of a state-action pair based on the *next* action taken by the current policy.