0
votes
$\begingroup$

Why do we use the seed function in the 'Pendulum-v0' environment?

https://github.com/openai/gym/blob/master/gym/envs/classic_control/pendulum.py#L25

$\endgroup$
2
  • 2
    $\begingroup$ Is that a pseudorandom generator's seed? (I'm not familiar with that project) If yes, it's probably called to make a repeatable/predictable output. If you run it again, you'll get the same results, unlike true random generators, or when pseudorandom generator is started by a "random" (or current time) value. $\endgroup$
    – Nyos
    Feb 27 '19 at 2:07
  • $\begingroup$ github.com/openai/gym/blob/master/gym/envs/classic_control/… $\endgroup$ Mar 1 '19 at 13:55
1
vote
$\begingroup$

Reinforcement Learning experiments are empirical and you want to be able to reproduce your experiments. Random numbers are generated off a seed; with the seed function you are fixing the seed so the RNG function produces the same sequence of random numbers.

$\endgroup$

Not the answer you're looking for? Browse other questions tagged or ask your own question.