no code implementations • 13 Feb 2021 • Sandhya Saisubramanian, Shlomo Zilberstein
The human shapes the environment through minor reconfiguration actions so as to mitigate the impacts of the agent's side effects, without affecting the agent's ability to complete its assigned task.
no code implementations • 8 Feb 2021 • Sainyam Galhotra, Sandhya Saisubramanian, Shlomo Zilberstein
Empirical evaluation on three real-world datasets demonstrates the effectiveness of our approach in quickly identifying the underlying fairness and interpretability constraints, which are then used to generate fair and interpretable clusters.
no code implementations • 24 Aug 2020 • Sandhya Saisubramanian, Shlomo Zilberstein, Ece Kamar
Learning to recognize and avoid such negative side effects of an agent's actions is critical to improve the safety and reliability of autonomous systems.
1 code implementation • 17 Dec 2019 • Sandhya Saisubramanian, Sainyam Galhotra, Shlomo Zilberstein
The interpretability of the clusters is complemented by generating simple explanations denoting the feature values of the nodes in the clusters, using frequent pattern mining.
no code implementations • 22 May 2019 • Sandhya Saisubramanian, Shlomo Zilberstein
To that end, we propose planning using a portfolio of reduced models, a planning paradigm that minimizes the negative side effects of planning using reduced models by alternating between different outcome selection approaches.
no code implementations • 2 Mar 2019 • Sainyam Galhotra, Sandhya Saisubramanian, Shlomo Zilberstein
We introduce a rich model for multi-objective clustering with lexicographic ordering over objectives and a slack.
no code implementations • 18 Oct 2018 • Sandhya Saisubramanian, Kyle Hollins Wray, Luis Pineda, Shlomo Zilberstein
The framework extends the stochastic shortest path (SSP) model to dynamic environments in which it is impossible to determine the exact goal states ahead of plan execution.