New answers tagged


It's an important feature, and you drop it at the risk of the agent failing to learn successfully. The difference between the TD target without the terminal flag $$G_t = R_{t+1} + \gamma \text{max}_{a'} Q(S_{t+1}, a')$$ and with the terminal flag applied to $S_{t+1} = S_T$ $$G_t = R_{t+1}$$ is important whenever $Q(S_{T}, a')$ might be evaluated as non-zero. ...

Top 50 recent answers are included