Recent findings reveal that even simple pricing algorithms can make things more expensive.

YouTube video by Plamadiso - Platforms, Markets & Digital Society

At a superficial level, the idea of maximum likelihood must be prehistoric: early hunters and gatherers may not have used the words ``method of maximum likelihood'' to describe their choice of where a...

Owen Oertell*, Wenhao Zhao*, Gokul Swamy, Zhiwei Steven Wu, Kiante Brantley, Jason Lee, Wen Sun

YouTube video by Gokul Swamy

YouTube video by Gokul Swamy

Website for AFIL course.

We consider the problem of imitation learning under misspecification: settings where the learner is fundamentally unable to replicate expert behavior everywhere. This is often true in practice due to ...

We present a general theoretical framework for designing efficient algorithms for interactive imitation learning. We leverage this framework to derive novel inverse reinforcement learning ...

Inverse reinforcement learning approaches reduce the problem of imitation learning to repeatedly solving a computationally expensive reinforcement learning problem. We prove and empirically validate t...

We consider the problem of imitation learning under misspecification: settings where the learner is fundamentally unable to replicate expert behavior everywhere. This is often true in practice due to ...

YouTube video by Gokul Swamy

From a first-principles perspective, it may seem odd that the strongest results in foundation model fine-tuning (FT) are achieved via a relatively complex, two-stage training procedure. Specifically, ...