Kishan Panaganti

Distributionally Robust Cooperative Multi-agent Reinforcement Learning with Value Factorization

On the Evolution of Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation

Tractable Multi-Agent Reinforcement Learning through Behavioral Economics

Robust LLM Alignment via Distributionally Robust Direct Preference Optimization

Risk-Averse Total-Reward Reinforcement Learning

Efficient Policy Optimization in Robust Constrained MDPs with Iteration Complexity Guarantees

Online Robust Reinforcement Learning Through Monte-Carlo Planning