Saturday, October 31, 202631 min read
Courses · Reinforcement Learning
The value of a state is an average you can solve for
On a slippery 4×4 grid, 20,000 episodes and one linear solve put cell 13 at about −2, and the discount turns out to be needed only by a policy that never ends.
Daily · Feature
Swapping the model moves AstaBench’s overall score twice as far on average as swapping the loop
On Ai2’s science-agent benchmark, a specialized agent takes most of its lead from one category, where its sub-agent Asta Panda adds 25.3 points to the same model at 15.9 times the reported cost.
Daily · Daily Brief
Judge bars DOJ from threatening California election officials days before the vote
The Ninth Circuit also refused 2-1 to set aside the ballots of more than 20,000 Californians the Justice Department calls noncitizens.