Search |  Contact |  SRI Home Do not follow this link, or your host will be blocked from this site. This is a spider trap. Do not follow this link, or your host will be blocked from this site. This is a spider trap. Do not follow this link, or your host will be blocked from this site. This is a spider trap.A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A ASRI International.  333 Ravenswood Avenue.  Menlo Park, CA 94025-3493. SRI International is a nonprofit corporation.

AIC Seminar Series

An Overview of CARLI: Competency Awareness for RL Agents

Melinda GervasioArtificial Intelligence Center, SRI International[Home Page]

Date:  Thursday, April 15th 2021 at 4:00pm

Location:  Zoom: https://sri.zoomgov.com/j/16028867898  (Directions)

   Abstract

A key component to building trust in machine learning systems is competency awareness. While state-of-the-art ML systems have achieved best-in-class performance on a wide variety of problems, they are generally unable to explain their task strategies, understand the limits of their competence, or provide accurate predictions of performance in novel situations. Under DARPA's Competency-Aware Machine Learning (CAML) program, we are building the Competency-Aware Reinforcement Learning through Introspection (CARLI) framework to address these challenges. Central to CARLI is the integration of a number of introspection capabilities designed to provide a comprehensive picture of an agent's competence, combined with novel calibration techniques for providing accurate performance predictions. In this talk, I will provide an overview of CARLI as we have realized it in our application domain of StarCraft II. CARLI is a collaborative effort between SRI (AIC, CSL, CVT) and Oregon State University.

   Bio for Melinda Gervasio

Melinda Gervasio, Ph.D., is a principal scientist in SRI’s Artificial Intelligence Center. She focuses on developing technology that combines human and machine intelligence.

Gervasio’s research interests include intelligent assistants, machine learning for autonomous agents, adaptive personalization, interactive machine learning, end-user programming, and intelligent training systems. As the technical lead on a number of government-funded projects, she has developed technologies for learning from demonstration, adaptive assistance, proactive decision support, and recommendation for informal learning.

Before joining SRI, Gervasio co-founded MindShadow, where she played a key technical role in developing a software platform for personalized, content-based recommendation. She was also a research scientist at the Institute for the Study of Learning and Expertise, where she worked on adaptive personalization.

Gervasio has a Ph.D. in computer science from the University of Illinois at Urbana-Champaign and a B.S. in computer science from the University of the Philippines Diliman.

–>

   Note for Visitors to SRI

Photography or broadcast of the event is prohibited unless specifically authorized by SRI. Reporters must coordinate with SRI 24 hours in advance before attending.
Please arrive at least 10 minutes early as you will need to sign in by following instructions by the lobby phone at Building E (or call Wilma Lenz at 650 859 4904, or Eunice Tseng at 650 859 2799). SRI is located at 333 Ravenswood Avenue in Menlo Park. Visitors may park in the parking lots off Fourth Street. Detailed directions to SRI, as well as maps, are available from the Visiting AIC web page. There are two entrances to SRI International located on Ravenswood Ave. Please check the Building E entrance signage.

SRI International
©2021 SRI International 333 Ravenswood Avenue, Menlo Park, CA 94025-3493
SRI International is an independent, nonprofit corporation. Privacy policy