R. Srikant

Finite‑Time Bounds for Distributionally Robust TD Learning with Linear Function Approximation

Primal-Dual Direct Preference Optimization for Constrained LLM Alignment

Global Convergence of Policy Gradient in Average Reward MDPs

Scalable Policy-Based RL Algorithms for POMDPs

Reinforcement Learning with Segment Feedback

Reinforcement Learning with Segment Feedback