Our NIPS 2017 “Learning to Run” Approach
medium.com
Our NIPS 2017 “Learning to Run” Approach
1–6 of 6 posts
Re: Our NIPS 2017 “Learning to Run” Approach
#2That simulation reminds me of the flash game 'QWOP'
Re: Our NIPS 2017 “Learning to Run” Approach
#3Re: Our NIPS 2017 “Learning to Run” Approach
#4That simulation reminds me of the flash game 'QWOP'
Had the same thought. :) I wonder if anyone has done a challenge using that game which has simpler inputs I believe?
Re: Our NIPS 2017 “Learning to Run” Approach
#5https://en.wikipedia.org/wiki/List_of_ethnic_slurs#cite_ref-...
> danjoc 39 minutes ago | undown | parent | flag | favorite | on: Our NIPS 2017 “Learning to Run” Approach
> https://en.wikipedia.org/wiki/List_of_ethnic_slurs#cite_ref-...
https://en.wikipedia.org/wiki/List_of_ethnic_slurs#cite_ref-...
Equally relevant, which is to say not relevant at all.
Re: Our NIPS 2017 “Learning to Run” Approach
#6That simulation reminds me of the flash game 'QWOP'
Had the same thought. :) I wonder if anyone has done a challenge using that game which has simpler inputs I believe?
Simplest RL algorithm (Q-learning) achieves 100m in QWOP:
https://www.youtube.com/watch?v=e27TUmMkOA0
Although it found and exploited a local maximum of "knee scraping" technique (which humans can replicate) :)