Earlier quoted context omitted.
The skeleton is not exactly good marketing.
I was going to suggest that they hook the AI up to QWOP.
But this task is strictly harder and more general than QWOP .
Reinforcement learning with musculoskeletal models
11–20 of 27 posts
Re: Reinforcement learning with musculoskeletal models
#12Like literally 3 hours ago I was searching for software that can simulate skeletons and joints to investigate the exact effects of jiu jitsu joint locks, optimal fulcrum points etc. Could this be used or adapted for that? Anyone here ever used it?
I’ve also been searching for something like this, wondering if it could be applied to horse racing simulation.
Re: Reinforcement learning with musculoskeletal models
#13Like literally 3 hours ago I was searching for software that can simulate skeletons and joints to investigate the exact effects of jiu jitsu joint locks, optimal fulcrum points etc. Could this be used or adapted for that? Anyone here ever used it?
I've participated in the NIPS "Learning to run" competition last year. It only computes motion in one direction (forward-backward, the model can't go left or right). What turned me off was the fact that object collision was handled poorly. You can't see a model that actually makes effort to avoid obstacles, instead all top solutions go through objects.
Re: Reinforcement learning with musculoskeletal models
#14Re: Reinforcement learning with musculoskeletal models
#15Re: Reinforcement learning with musculoskeletal models
#16Earlier quoted context omitted.
The skeleton is not exactly good marketing.
I was going to suggest that they hook the AI up to QWOP.
I was curious if anyone had tried to train an AI to play QWOP. Of course they have: https://www.youtube.com/watch?v=e27TUmMkOA0 (among others)
I wonder if you could get a better result by including other factors in the reward function, like trying to maintain a slight forward lean.
Re: Reinforcement learning with musculoskeletal models
#17Like literally 3 hours ago I was searching for software that can simulate skeletons and joints to investigate the exact effects of jiu jitsu joint locks, optimal fulcrum points etc. Could this be used or adapted for that? Anyone here ever used it?
I've participated in the NIPS "Learning to run" competition last year. It only computes motion in one direction (forward-backward, the model can't go left or right). What turned me off was the fact that object collision was handled poorly. You can't see a model that actually makes effort to avoid obstacles, instead all top solutions go through objects.
So all 'joints' only move in 2d, am I getting that right?
Re: Reinforcement learning with musculoskeletal models
#18Like literally 3 hours ago I was searching for software that can simulate skeletons and joints to investigate the exact effects of jiu jitsu joint locks, optimal fulcrum points etc. Could this be used or adapted for that? Anyone here ever used it?
I've participated in the NIPS "Learning to run" competition last year. It only computes motion in one direction (forward-backward, the model can't go left or right). What turned me off was the fact that object collision was handled poorly. You can't see a model that actually makes effort to avoid obstacles, instead all top solutions go through objects.
That's only one-side of the story. It is actually a very accurate contact model. The problem is that it's also computationally expensive and therefore we reduce the stiffness of objects to make it faster. It's basically a trade-off between the accuracy and speed.
In gaming engines you have speed and it looks good, but then it's impossible to generalize for real-life applications (because the contact is inaccurate).
Re: Reinforcement learning with musculoskeletal models
#19Earlier quoted context omitted.
I've participated in the NIPS "Learning to run" competition last year. It only computes motion in one direction (forward-backward, the model can't go left or right). What turned me off was the fact that object collision was handled poorly. You can't see a model that actually makes effort to avoid obstacles, instead all top solutions go through objects.
So all 'joints' only move in 2d, am I getting that right?
In the 2017 challenge yes. This year we are using a 3d model.
Re: Reinforcement learning with musculoskeletal models
#20Like literally 3 hours ago I was searching for software that can simulate skeletons and joints to investigate the exact effects of jiu jitsu joint locks, optimal fulcrum points etc. Could this be used or adapted for that? Anyone here ever used it?
I’ve also been searching for something like this, wondering if it could be applied to horse racing simulation.
Absolutely, however, you will need to construct a muscle model for horses. The human model is a result of decades of research, MRIs etc.