The Ray RLlib "Getting Started" page says to run the following:
pip install "ray[rllib]" tensorflowrllib
train --algo DQN --env CartPole-v1
and then says "Running the above will return one of the checkpoints that get generated during training, as well as a command that you can use to evaluate the trained algorithm."
However, after 3 hours the command was still running even though training seemed complete judging from the Tensorboard visualization.
Is this command supposed to eventually stop? What does it mean to "return one of the checkpoints"? Does it mean to print that information?
