For a school project, I would like to investigate a paper on either reinforcement learning or computer vision. I am particularly interested in DQN, RNNs, CNNs or LSTMs. I would eventually like to implement any of these. However, I also need to take into account the computing resources required to train and analyse any of these algorithms. I understand that, in computer vision, the data sets can be quite large, but I am not so sure regarding the resources needed to implement and train a typical state-of-the-art RL algorithm (like DQN).

Would a "standard PC" be able to run any of these algorithms decently to achieve some sort of analysis/results?

  • 2
    $\begingroup$ Short answer: yes, state of the art with many many layers probably not but enough to tinker and learn and make a project. $\endgroup$ Apr 10, 2018 at 16:09
  • 1
    $\begingroup$ How do you plan to implement it? using some language from scratch, using python and some of the deep learning packages like Tensorflow? I am not an expert at all, but my standard PC seems not good enough to install and run Tensroflow, for instance. $\endgroup$ Apr 12, 2018 at 11:53
  • 1
    $\begingroup$ I believe I will be using Python along with a few packages. However, as it's my first time trying these algorithms I have no advice to give you. After trying it out I'll try and remember to get back to you. $\endgroup$
    – Wizard
    Apr 12, 2018 at 13:56

1 Answer 1


It might be hard to implement deep reinforcement learning algorithms, especially considering your previous experience and the computing resources you have. They require almost the same (even more) GPU power. Deep reinforcement learning algorithms use deep neural networks for learning the optimal policy. Even if you are given appropriate resources, it would be tough to replicate the results of the paper, if you are a novice.


You must log in to answer this question.

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