OpenAI Universe
51–60 of 139 posts
Re: OpenAI Universe
#52Re: OpenAI Universe
#53From my initial reading, the end user can't create environments? Is that a feature that I can expect will eventually come?
Re: OpenAI Universe
#54Re: OpenAI Universe
#55Any applications with a keyboard and mouse? Can I use emacs and have it start learning to code?
Re: OpenAI Universe
#56From my initial reading, the end user can't create environments? Is that a feature that I can expect will eventually come?
Does that mean we can't train it on new games? only preexisting ones?
I only briefly poked around because it's nearing on midnight here - maybe you can pull open the examples included and work out how to rewire them to work on new games, maybe not. Either way, I've got a particular use case I'd like to make a gym for so I'm interested in finding out.
Re: OpenAI Universe
#57Hey guys, it's Siraj. OpenAI asked me to make a promotional video for it on my Youtube channel and I gladly said yes! You can check it out here: https://www.youtube.com/watch?v=mGYU5t8MO7s
Re: OpenAI Universe
#58>other applications Any applications with a keyboard and mouse? Can I use emacs and have it start learning to code?
Re: OpenAI Universe
#59What is state of the art in reinforcement learning right now? https://arxiv.org/abs/1602.01783 Is there a way to deal with "sparse" training data (state, action, reward) triples -- sparse in "state"?
Re: OpenAI Universe
#60I just hope no self-driving vehicle is applying anything learned in GTA.
I can't recall where, but I read that Tesla or Google were actually using GTA to train their self-driving cars, because it is a spectacularly advanced simulation of driving through an urban environment, so they didn't have to build their own.