Is reinforcement learning problem adaptable to the setting when there is only one - final - reward. I am aware about problems with sparse and delayed rewards, but what about the only one reward and quite long path?
RL can be used for these cases, but, in such setting, the experience the agent receives during the trajectory does not provide much information regarding the quality of the actions.
Games can be often formulated as episodic tasks. For example, you could formulate a chess match as an episode and you could give a reward only at the end of the match. However, this will be hard for the RL to "understand" which moves have mainly contributed to the reward received. This is called the credit assignment problem.
The expression "delayed rewards" also refers to the cases where you receive only one reward at the end of the episode.