Wesley Liao
UPDATE:
AI was able to surpass the World Record in my new video:
https://youtu.be/82sTpO_EpEc
AI bot learns to play QWOP like a human and achieves a top 10 speedrun (1m 8s). Trained using Reinforcement Learning and Imitation Learning.
Github repo:
https://github.com/Wesleyliao/QWOP-RL
Papers mentioned:
– Sample Efficient Actor-Critic with Experience Replay
https://arxiv.org/pdf/1611.01224.pdf
– Deep Q-learning from Demonstrations
https://arxiv.org/pdf/1704.03732.pdf
Kurodo’s channel:
https://www.youtube.com/channel/UCLxJfj_Dq8Ks89tUVR3z7ug
QWOP speedrun leaderboard:
https://www.speedrun.com/qwop
Source
Right away I'm not such a fan of the fact that you had to demonstrate a stride and then it used that. It feels like it limits the possibilities only to that which humans can already achieve.
A more general purpose AI might take longer to train, but it would have been able to discover special movies on its own. They usually find glitches in the physics engine and exploit those in a way no human can.
Great video and thanks of the upload and explanation!
It's frustrating to even watch someone play this game.
Ok, but why is the runner dude wearing a leotard?
when I use my left hand:
2000 Game Devs: Let's Create fun games.
2021 ML/AI: Let's not have nice things, shall we?
did you try training for 20 hours without pretraining? i’m curious how much the extra 12 hours of training helped compared to pretraining
we live in a strange time where we know flash games from childhood and are intelligent enough to program ai to accomplish what we couldn’t lol
That's normally what I look like on the way home from the pub!
Fajne
Machine can calculate but never Will understand. So simple.
Omg this is amazing
I believe the biggest problem for AI in this instance was the lack of Kurodial arteries, therefore restricting the bandwith.
Well, this reinforces my confidence that computers will never take over the world.
If THAT guy was chasing after me… I'd take his lunch money and then look for his brother.
Blast from the past. I remember being in high school when this game was at the height of its popularity. Almost every computer in the lab during lunch had this on it.
I was very excited to see the final result with 65 hours.. but it turns out it was what we've already seen, what a disappointment
Special Olympics!
May I ask what the reward is? The speed, or something like height of weight center?
Ah, Semi-Supervised Learning. That is how machine learning really needs to be done.
Or really…
– A combination of Supervised Learning, Semi-Supervised Learning, and Unsupervised Learning
– Redundancies to prevent it from just always taking the laziest path.
– Hard-coded rules manually put in by a human.
– Humans always kept in the loop, along with Non-AI redundancies.
– Everything done in a safe and controlled environment, instead of a live deployment where it's possible for the AI to do real damage.
You should look into Deep Transfer Learning as well.
How to train a machine to complete a difficult game for you: Learn it yourself first and teach it.
RIP VANGELIS!
"I'm human …" [citation needed] "…and know how to use legs." [citation needed]
this game should be an ultimate AI algorithm benchmark tester, I knew about the game since it first came out and didn't know much about programming until recently so a lot made sense easily once I got the proper vocabulary understood