Introducing Personal Intelligence. It's our answer to a top request: you can now personalize @GeminiApp by connecting your Google apps with a single tap. Launching as a beta in the U.S. for Pro/Ultra members, this marks our next step toward making Gemini more personal, proactive and powerful. Check it out!
Presenting world-scale inverse reinforcement learning (IRL) in Google Maps. Learn how RHIP, a new IRL algorithm, along with advances in graph compression & parallelization led to relative improvement in the quality of suggested routes in Google Maps. โ https://t.co/5X9wwWwDS3
@googlemaps Overall: 16-24% improvement in route accuracy
Personally, very excited by the potential this has for cycling and walking. These are often some of the most difficult routing problems, since its about so much more than just ETA
Our multi-year project using Inverse RL to improve route quality in @googlemaps is finally out!
Scaling was HARD. It took advancements on parallelization, graph compression, dominant eigenvector inspired initializers, and a new generalized IRL algorithm to make it possible.
Our ๐-scale Inverse RL paper is finally out! Thrilled to share this multi-year project on route recommendation.
Understanding preferences is much harder than behaviour: not just WHAT but WHY!
We address the challenge via IRL on massive scale (100s Ms states, samples, params)!
@williamwilcock@CascadeBicycle@WAbikes How so? Cycling is inversely correlated with income (see Census stats below). And sales taxes are, in general, regressive.
@zacharylipton I think this trend partly stems from the techno-optimistic โCS can do anythingโ attitude, which has benefits (like you mention) but also downsides (esp. distracting from less-shiny, non-CS solutions). e.g. Hyperloop