If I understand you correctly, you are asking if wind turbines can operate with the wind blowing from behind them?
Wind turbine's are designed and built with wind coming in front of them. I am unaware of any designs that would work from both directions (horizontal axis wind turbines of course).
Wake effects are studied extensively and automated systems exist that will optimize the turbines' yaw direction to maximize power output (and / or keeping loads in check) of the entire plant instead of just a single turbine.
What's novel here is the effect the counter-clockwise rotation has on the power output of the down stream turbines... I think it hasn't really been a point to research as the costs of blades, maintenance, etc... are assumed to far outweigh the potential gains.
Something else to keep in mind is that it's not as pleasant to look at a park full of turbines spinning in different directions.
I was super excited when I read the headline and saw that deepmind published the article. I was hoping for something along the lines of applying reinforcement learning on the turbine or park level to optimize power output. Finding the optimal pitch angles, better yawing algorithms (yaw misalignemnts are one of the most common causes of underperforming wind turbines), or finding optimal yaw directions for the entire wind park (downwind wake effects can have a negative impact on other turbines)...
Unfortunately this is really only about predicting wind speeds to then forecast power output. IIRC, grid codes in some countries are starting to require 24 hour, 15 minute interval forecasts for renewables? I've also seen this feature being advertised by other companies over the years as well, although I don't recall seeing any numbers on accuracy for any of the models.
Wind turbine's are designed and built with wind coming in front of them. I am unaware of any designs that would work from both directions (horizontal axis wind turbines of course).