240 citations · 678 across the 9 of their papers we have counts for
13 papers · 1 filter
Mitigating Negative Side Effects via Environment Shaping
Sandhya Saisubramanian, Shlomo Zilberstein
Agents operating in unstructured environments often produce negative side effects (NSE), which are difficult to identify at design time. While the agent can learn to mitigate the s…
Helpfulness as a Key Metric of Human-Robot Collaboration
Richard G. Freedman, Steven J. Levine, Brian C. Williams +1
As robotic teammates become more common in society, people will assess the robots' roles in their interactions along many dimensions. One such dimension is effectiveness: people wi…
Improving Competence for Reliable Autonomy
Connor Basich, Justin Svegliato, Kyle Hollins Wray +2
Given the complexity of real-world, unstructured domains, it is often impossible or impractical to design models that include every feature needed to handle all possible scenarios…
Learning to Optimize Autonomy in Competence-Aware Systems
Connor Basich, Justin Svegliato, Kyle Hollins Wray +3
Interest in semi-autonomous systems (SAS) is growing rapidly as a paradigm to deploy autonomous systems in domains that require occasional reliance on humans. This paradigm allows…
Responsive Planning and Recognition for Closed-Loop Interaction
Richard G. Freedman, Yi Ren Fung, Roman Ganchin +1
Many intelligent systems currently interact with others using at least one of fixed communication inputs or preset responses, resulting in rigid interaction experiences and extensi…
Minimizing the Negative Side Effects of Planning with Reduced Models
Sandhya Saisubramanian, Shlomo Zilberstein
Reduced models of large Markov decision processes accelerate planning by considering a subset of outcomes for each state-action pair. This reduction in reachable states leads to re…