3
$\begingroup$

I have an environment that is computationally heavy (takes several seconds to get a reward and next state). This limits reinforcement capability, due to poor sampling of the problem. There is any strategy that could be used to address the problem (e.g. If I can use the environment in parallel, then I could use a multi-agent approach)

Improve this question
$\endgroup$
2
  • $\begingroup$ Mltiple environments, installing some form of reward shaping or prior knowledge into the problem? $\endgroup$
    – FourierFlux
    Commented Sep 22, 2020 at 18:28
  • $\begingroup$ @FourierFlux In terms of multiple environments - then how you would integrate them? Average updates like in A3C alg. ? $\endgroup$
    – Daniel Wiczew
    Commented Sep 23, 2020 at 14:53

1 Answer 1

Reset to default
0
$\begingroup$

You could use Ray RLlib. It has support for parallel environments, even over multiple GPUs and compute nodes.

Improve this answer
$\endgroup$

You must log in to answer this question.

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