New answers tagged

0

It's not true that finite horizon MDP can't use a discount factor. Any discount factor $\gamma \leq 1$ is fine for finite horizon. Whether or not cartpole is a finite or infinite horizon depends on the environment implementation. The default environment in openai gym uses $T=200$ as the horizon. This is customizable, and most papers I see which use cartpole ...


Top 50 recent answers are included