Phillip Isola highlights a non-mainstream AI route: RL from scratch via ultra-fast simulators

AjdDavison · x · 2026-09-15

MIT professor Phillip Isola recommends the research pursued by Joseph and team, who take a very different approach from the mainstream: they build extremely fast simulators and optimizers — so fast that reinforcement learning can be done from scratch even on hard domains. The results are described as "very cool," and retweeter AjdDavison flags it as worth watching.

Original post →

More from Research

Research channel →