Live data from Hacker News

OpenAI Universe

universe.openai.com

51–60 of 139 posts

Re: OpenAI Universe

#52
Related but slightly off-topic, there is a great sci-fi story by Ted Chiang (the same author who made the story behind Arrival film) about humans raising AIs in an artificial world. The premise is that if we want AIs to act like humans, we must teach them like we teach humans: http://subterraneanpress.com/magazine/fall_2010/fiction_the_...

Re: OpenAI Universe

#56
post #49

From 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?

If it's true, I believe we have to wait for the OpenAI team to build new gym environments before we can train in new games.

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

#57

Hey 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

Nice video, but the jump from solving super simple 2d games, by feedback of binary win/lose conditions, to solving tasks in 3d open world simulations will require an un-imaginably gigantic leap in processing and knowledge. Additionally neural nets have already shown they are not sufficiently good enough at generalizing, and only work well at the specific tasks they were trained for. So the idea that an AI that can play GTA would also be able to 'solve' climate change is odd.

Re: OpenAI Universe

#59

What 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"?

That paper was 10 months ago. There have been many RL papers in the meantime, but sparsity is only a problem with respect to reward, not state or action, from what I can see.

Re: OpenAI Universe

#60
post #14

I 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.

What is spectacularly advanced about the police ramming me off the road as they chase another suspect?
Post reply on HN