Timezone: »

Interactive Learning from Activity Description
Khanh Nguyen · Dipendra Misra · Robert Schapire · Miro Dudik · Patrick Shafto

Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual #None

We present a novel interactive learning protocol that enables training request-fulfilling agents by verbally describing their activities. Unlike imitation learning (IL), our protocol allows the teaching agent to provide feedback in a language that is most appropriate for them. Compared with reward in reinforcement learning (RL), the description feedback is richer and allows for improved sample complexity. We develop a probabilistic framework and an algorithm that practically implements our protocol. Empirical results in two challenging request-fulfilling problems demonstrate the strengths of our approach: compared with RL baselines, it is more sample-efficient; compared with IL baselines, it achieves competitive success rates without requiring the teaching agent to be able to demonstrate the desired behavior using the learning agent’s actions. Apart from empirical evaluation, we also provide theoretical guarantees for our algorithm under certain assumptions about the teacher and the environment.

Author Information

Khanh Nguyen (University of Maryland)
Dipendra Misra (Microsoft)
Robert Schapire (Microsoft Research)
Miro Dudik (Microsoft Research)
Miro Dudik

Miroslav Dudík is a Senior Principal Researcher in machine learning at Microsoft Research, NYC. His research focuses on combining theoretical and applied aspects of machine learning, statistics, convex optimization, and algorithms. Most recently he has worked on contextual bandits, reinforcement learning, and algorithmic fairness. He received his PhD from Princeton in 2007. He is a co-creator of the Fairlearn toolkit for assessing and improving the fairness of machine learning models and of the Maxentpackage for modeling species distributions, which is used by biologists around the world to design national parks, model the impacts of climate change, and discover new species.

Patrick Shafto (Rutgers University-Newark)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors