Showing stat.MLShow all
2 papers · 1 filter
stat.ML2026
Is In-Context Reinforcement Learning A Posterior Sampler? An Empirical Study
Weiqin Chen, Xinlong Du, Gesualdo Scutari +1
In-context reinforcement learning (ICRL) exploits the impressive in-context learning ability of large language models to zero-shot generalize to new, unseen tasks at inference time…
stat.ML2022
Offline Estimation of Controlled Markov Chains: Minimaxity and Sample Complexity
Imon Banerjee, Harsha Honnappa, Vinayak Rao
In this work, we study a natural nonparametric estimator of the transition probability matrices of a finite controlled Markov chain. We consider an offline setting with a fixed dat…