From the 2 of 32 linked papers with an AI index.
32 papers
Hypergradient-based Bilevel Reinforcement Learning with Improved Sample Complexity
Naman Saxena, Mudit Gaur, Vaneet Aggarwal
Bilevel reinforcement learning (RL) is an important framework within the literature of RL that can be used to formalize various categories of problems, such as meta-learning, hiera…
Hierarchical Multilevel Monte Carlo for Order-Optimal Neural Actor-Critic in Average-Reward CMDPs
Ankur Naskar, Vaneet Aggarwal
The paper proposes a hierarchical Multilevel Monte Carlo neural critic to reduce bias and cost in actor‑critic reinforcement learning for average‑reward constrained Markov decision…
Efficient Q-Learning and Actor-Critic Methods for Robust Average-Reward Reinforcement Learning
Yang Xu, Swetha Ganesh, Vaneet Aggarwal
The paper develops and analyzes model‑free Q‑learning and actor‑critic algorithms that provably learn robust policies for infinite‑horizon average‑reward MDPs under various uncerta…
Discrete State Diffusion Models: A Sample Complexity Perspective
Aadithya Srikanth, Mudit Gaur, Vaneet Aggarwal
Diffusion models have demonstrated remarkable performance in generating high-dimensional samples across domains such as vision, language, and the sciences. Although continuous-stat…
Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking
Yang Xu, Jiefu Zhang, Haixiang Sun +3
Adaptive prompt and program search makes LLM evaluation selection-sensitive. Once benchmark items are reused inside tuning, the observed winner's score need not estimate the fresh-…
Persistent-Transient Policy Evaluation for Markov Chains via Minimal Peripheral Quotients
Yang Xu, Vaneet Aggarwal
We study fixed-policy evaluation for finite Markov chains that may be reducible and periodic. Classical evaluation methods with gain and bias decomposition are not always diagnosti…