conftrace_

single-policy concentrability

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

offline reinforcement learning (2) density-ratio function (1) marginalized importance sampling (1) density ratio (1) primal-dual algorithm (1) markov decision process (1) sample complexity (1) function approximation (1) augmented lagrangian (1)

Papers

Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian ICLR 2023 Offline Reinforcement Learning with Realizability and Single-policy Concentrability COLT 2022