0
$\begingroup$

I am new in the field of RL. I am trying to use tabular methods, Q-Learning for solving a problem that takes a lot of time for computation, so I would like to know if there are more efficient methods for it.

Why are tabular methods are not useful in large state spaces? Maybe too many possible combinations? Could Softmax Action Selection be better than epsilon greedy?

Improve this question
$\endgroup$
1
  • $\begingroup$ Please, don't change the meaning of your question, once it's answered. "softmax action selection" and "value function approximation" are the same thing, so it seems that you changed your question. If you have another similar question, ask it in a new post! $\endgroup$
    – nbro
    May 20, 2022 at 9:41

1 Answer 1

Reset to default
1
$\begingroup$

Your question contains the answer. Use value function approximation. Tabular methods must compute a value for each state. That becomes unfeasible with large state spaces. Function approximators can genererlize, and perform well even without ever having seen every state.

Improve this answer
$\endgroup$
0

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .