Get the latest tech news
Contrastive Representations for Temporal Reasoning
Official website of Contrastive Representations for Temporal Reasoning (CRTR)
In classical AI, perception relies on learning spatial representations, while planning—temporal reasoning over action sequences—is typically achieved through search. In particular, for the Rubik’s Cube, CRTR learns representations that generalize across all initial states and allow solving the puzzle much faster than BestFS—though with longer solutions. To our knowledge, this is the first demonstration of efficiently solving arbitrary Cube states using only learned representations, without hand-crafted search heuristics.
Or read this on Hacker News