I've seen a single paper on the topic of adapting fully recurrent networks to a reinforcement learning setting, but according to google scholar its had no citations and no code has been released implementing the algorithm it describes. Before I go out and roll my own implementation of this algorithm, I just wanted to check that a less obscure algorithm wasn't out there (hopefully with an open-source implementation).

If there isn't a more noteworthy algorithm of this sort, then a secondary question would be why not? Is the some research showing that recurrent architectures don't buy you anything when used for reinforcement learning? Perhaps extending temporal differencing to such an architecture results in intractable computational complexity?

  • $\begingroup$ The following paper uses REINFORCE to train an RNN. I don't know if there is code available. Recurrent Models of Visual Attention: arxiv.org/abs/1406.6247 $\endgroup$ – capybaralet Mar 9 '15 at 20:09
  • 1
    $\begingroup$ I don't know any open-sourced implementation, but I'm 99.9% sure someone must have combined them in some model, probably in an NLP application. You're talking about two of the hottest algorithms out there right now. $\endgroup$ – horaceT Jun 3 '16 at 4:46

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.