Decisions.ai
Overview
Advances in algorithmic decision-making under uncertainty, combining normative models (e.g., utility theory, stochastic optimization) with data-driven approaches (reinforcement learning, bandits) to build intelligent decision-support systems in single- and multi-agent settings.
Location
CC 402
Principal Investigators
Recent Publications
-
Collaborative Learning under Strategic Behavior: Mechanisms for Eliciting Feedback in Principal-Agent Bandit Games
Ramakrishnan K, Arpit Agarwal, Lakshmi Subramanian, Maximilian Nickel
Reinforcement Learning Conference (RLC) · 2026
-
Creator Incentives in Recommender Systems: A Cooperative Game-Theoretic Approach for Stable and Fair Collaboration in Multi-Agent Bandits
Ramakrishnan Krishnamurthy, Arpit Agarwal, Lakshminarayanan Subramanian, Maximilian Nickel
International Conference on Artificial Intelligence and Statistics (AISTATS) · 2026
-
Designing Truthful Mechanisms for Asymptotic Fair Division
Jugal Garg, Vishnu V Narayan, Yuang Eric Shen
AAAI Conference on Artificial Intelligence (AAAI) · 2026
-
Efficient Online Influence Maximization under the Independent Cascade Model with Node-Level Feedback
Arpit Agarwal, Varad Deolankar, Rohan Ghuge
International Conference on Machine Learning (ICML) · 2026
-
Learning in Repeated Stackelberg Security Games with an Unknown Set of Attacker Types
Sabil Ahmad, Ishita, Aditi Singh, Swaprava Nath
Technical Report · 2026
-
Matching Markets meet Cumulative Prospect Theory: Towards Optimal and Adversarially Robust Learning
Ananya Kunisetty, Avishek Ghosh
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD) · 2026
-
Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret
Conference on Neural Information Processing Systems (NeurIPS) · 2026
-
On-line Learning in Tree MDPs by Treating Policies as Bandit Arms
Anvay Shah, Ramsundar Anandanarayanan, Sharayu Moharir, Shivaram Kalyanakrishnan
International Conference on Autonomous Agents and Multiagent Systems (AAMAS) · 2026 · Accepted
-
Online Fair Division With Subsidy: When Do Envy-Free Allocations Exist, and at What Cost?
Pooja Kulkarni, Ruta Mehta, Vishnu V Narayan, Tomasz Ponitka
International Conference on Autonomous Agents and Multiagent Systems (AAMAS) · 2026
-
Optimal Regret for Single Index Bandits
Devdan Dey, Sujoy Bhore, Avishek Ghosh
Preprint · 2026