activity
20182021
most citedA Bayesian Account of Measures of Interpretability in Human-AI Interaction

8 citations · 8 across the 2 of their papers we have counts for

collaborators

7 papers

cs.AI2021

Planning for Proactive Assistance in Environments with Partial Observability

Anagha Kulkarni, Siddharth Srivastava, Subbarao Kambhampati

This paper addresses the problem of synthesizing the behavior of an AI agent that provides proactive task assistance to a human in settings like factory floors where they may coexi…

cs.AI2021

A Unifying Bayesian Formulation of Measures of Interpretability in Human-AI

Sarath Sreedharan, Anagha Kulkarni, David E. Smith +1

Existing approaches for generating human-aware agent behaviors have considered different measures of interpretability in isolation. Further, these measures have been studied under…

cs.AI20208 cited

A Bayesian Account of Measures of Interpretability in Human-AI Interaction

Sarath Sreedharan, Anagha Kulkarni, Tathagata Chakraborti +2

Existing approaches for the design of interpretable agent behavior consider different measures of interpretability in isolation. In this paper we posit that, in the design and depl…

cs.AI2020

Designing Environments Conducive to Interpretable Robot Behavior

Anagha Kulkarni, Sarath Sreedharan, Sarah Keren +3

Designing robots capable of generating interpretable behavior is a prerequisite for achieving effective human-robot collaboration. This means that the robots need to be capable of…

cs.AI2019

Signaling Friends and Head-Faking Enemies Simultaneously: Balancing Goal Obfuscation and Goal Legibility

Anagha Kulkarni, Siddharth Srivastava, Subbarao Kambhampati

In order to be useful in the real world, AI agents need to plan and act in the presence of others, who may include adversarial and cooperative entities. In this paper, we consider…

cs.AI2018

Explicability? Legibility? Predictability? Transparency? Privacy? Security? The Emerging Landscape of Interpretable Agent Behavior

Tathagata Chakraborti, Anagha Kulkarni, Sarath Sreedharan +2

There has been significant interest of late in generating behavior of agents that is interpretable to the human (observer) in the loop. However, the work in this area has typically…