The paper establishes the first tilde O(epsilon^{-1}) upper bounds and matching lower bounds for forward-KL-regularized offline contextual bandits under single-policy concentrability in both tabular and general function approximation settings.
Provable offline preference-based reinforcement learning.arXiv preprint arXiv:2305.14816
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6verdicts
UNVERDICTED 6representative citing papers
Primal-dual policy gradient algorithms achieve global non-asymptotic convergence for safe RLHF cast as infinite-horizon discounted CMDPs without fitting reward models.
Introduces robust estimators for linear Markov games in offline MARLHF that achieve O(ε^{1-o(1)}) or O(√ε) bounds on Nash or CCE gaps under uniform or unilateral coverage.
Proposes OPAC for trajectory-level offline RL achieving 𝓣O(H^{2}√(C_sa(π*)/n)) bounds with matching lower bound, plus conditions for tractability in generalized nonlinear outcome settings.
OPRIDE improves query efficiency in offline PbRL via a principled in-dataset exploration strategy and discount scheduling, outperforming prior methods with fewer queries and providing theoretical guarantees.
PEPO is a single-step pessimistic ensemble algorithm for direct preference optimization that provably avoids over-optimization by depending only on single-policy concentrability without knowing the data distribution or learning an explicit reward model.
citing papers explorer
-
Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability
The paper establishes the first tilde O(epsilon^{-1}) upper bounds and matching lower bounds for forward-KL-regularized offline contextual bandits under single-policy concentrability in both tabular and general function approximation settings.
-
Policy Gradient Primal-Dual Method for Safe Reinforcement Learning from Human Feedback
Primal-dual policy gradient algorithms achieve global non-asymptotic convergence for safe RLHF cast as infinite-horizon discounted CMDPs without fitting reward models.
-
Corruption-robust Offline Multi-agent Reinforcement Learning From Human Feedback
Introduces robust estimators for linear Markov games in offline MARLHF that achieve O(ε^{1-o(1)}) or O(√ε) bounds on Nash or CCE gaps under uniform or unilateral coverage.
-
When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning?
Proposes OPAC for trajectory-level offline RL achieving 𝓣O(H^{2}√(C_sa(π*)/n)) bounds with matching lower bound, plus conditions for tractability in generalized nonlinear outcome settings.
-
OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration
OPRIDE improves query efficiency in offline PbRL via a principled in-dataset exploration strategy and discount scheduling, outperforming prior methods with fewer queries and providing theoretical guarantees.
-
Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distribution
PEPO is a single-step pessimistic ensemble algorithm for direct preference optimization that provably avoids over-optimization by depending only on single-policy concentrability without knowing the data distribution or learning an explicit reward model.