[HN Gopher] Speeding Up Reinforcement Learning with a New Physic...
___________________________________________________________________
Speeding Up Reinforcement Learning with a New Physics Simulation
Engine
Author : apsec112
Score : 63 points
Date : 2021-07-16 18:29 UTC (1 days ago)
(HTM) web link (ai.googleblog.com)
(TXT) w3m dump (ai.googleblog.com)
| anon_tor_12345 wrote:
| if you're wondering why lots of these differentiable pipelines
| are tasked with learning physics (and what that has to do with
| google) the answer is that this is "compute oriented
| development". by "compute oriented development" i mean that since
| google has access to unlimited compute they can use this compute
| to run physics kinematics solvers (ie pde solvers) that are then
| used to generate training data for RL models. what's the point of
| the RL model if the physics model already exists and gives you
| high fidelity simulations? well it's clearly an easy paper to
| write... but other than that, some people claim the RL models are
| faster than the physics solver. i guess that's true if you don't
| take into account the millions of hours of compute spent on the
| solvers themselves.
| nmca wrote:
| (disclaimer: work on RL, have trained models for simulated
| tasks)
|
| I'm fairly sure that people work on control because general
| algorithms for control would be very useful (e.g., robot that
| can skin a cat and drive a car by holding the steering wheel).
| Such a robot would exist in our 3d physical world, so
| simulations of of our 3d world are used for training. If this
| could be done with radically less compute, it would be.
| anon_tor_12345 wrote:
| sure but it doesn't hurt that you have infinite data too
| (i.e. the thing most other ML research is bound by). like you
| can't argue that it's not a very comfortable corner to be in
| wrt being able to publish.
| kadoban wrote:
| Sounds quite a bit like you're complaining that they
| chose/engineered a fruitful field of study. I think I'm
| missing what the problem with that is.
| velcroscientist wrote:
| Good point. This is why robotics researchers do not take deep
| RL papers seriously unless they have some real world robotics
| results. I'm looking at you, people who only show mujoco
| results and claim their algorithm is useful for robotics.
|
| Simulators are useful though for real world robotics. You can
| prototype your environment and algorithm, and also attempt
| sim2real transfer. For example, use the simulator to generate a
| lot of image data, and train image based controllers. Add
| enough domain randomization and _maybe_ your controller trained
| on the simulator can transfer to real images.
___________________________________________________________________
(page generated 2021-07-17 23:01 UTC)