Getting Mario Back into the Gym: Setting up Super Mario Bros. in OpenAI’s gym
<p>It’s been a few years since I was first exposed to reinforcement learning. What got me into it was seeing <a href="https://www.youtube.com/watch?v=qv6UVOQ0F44&t=172s" rel="noopener ugc nofollow" target="_blank">this video</a> that had trained a neural network to play Mario. As someone who grew up playing Mario, seeing deep learning being applied to something I knew so well seemed to provided the perfect introduction to the topic. Sadly though, the project was written using <a href="http://torch.ch/" rel="noopener ugc nofollow" target="_blank">Torch</a>, and I was still a naive young programmer. I didn’t get too far along before the frustrations with learning lua lead me to give up, and just focus on other projects instead. Recently though, I began working with <a href="http://pytorch.org/docs/master/torch.html" rel="noopener ugc nofollow" target="_blank">PyTorch</a> that inspired me to try it again; this time in python.</p>
<p>Getting Mario up and running was far easier this time around. I was able to utilize <a href="https://openai.com/" rel="noopener ugc nofollow" target="_blank">OpenAI</a>’s <code>gym</code> package, which made the process fairly simple, but it wasn’t exactly straight forward. It required some work quick work arounds and tweaks to the <code>gym</code> environment. After I finally got it up and running, my coworkers were fascinated, and I began trouble shooting their installations. Seeing their interest, I thought I could provide instructions for how to get it set up; so that anyone can start letting their computer learn how to play Super Mario Bros.</p>
<p><a href="https://becominghuman.ai/getting-mario-back-into-the-gym-setting-up-super-mario-bros-in-openais-gym-8e39a96c1e41"><strong>Click Here</strong></a></p>