No article text was recorded for this version.
single-policy concentrability
Version 1 of 161 papers78 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Pessimism meets VCG: Learning Dynamic Mechanism Design via Offline Reinforcement Learning
- Blog: Towards Instance-Optimal Offline Reinforcement Learning with Pessimism
- Blog: Policy learning “without” overlap: pessimism and generalized empirical Bernstein’s inequality
- Blog: Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity
- Blog: Is Pessimism Provably Efficient for Offline RL?
- Blog: Provably Good Batch Off-Policy Reinforcement Learning Without Great Exploration
- Blog: Offline Neural Contextual Bandits: Pessimism, Optimization and Generalization
- Blog: Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimism
- Blog: Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity
- Blog: On Gap-dependent Bounds for Offline Reinforcement Learning
- Blog: Is Pessimism Provably Efficient for Offline RL?
- Blog: Offline Learning for Combinatorial Multi-armed Bandits
- Blog: Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage
- Blog: Offline Neural Contextual Bandits: Pessimism, Optimization and Generalization
- Blog: Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian
- Blog: Offline Primal-Dual Reinforcement Learning for Linear MDPs
- Blog: Sequential Off-Policy Learning with Logarithmic Smoothing
- Blog: Bridging Distributionally Robust Learning and Offline RL: An Approach to Mitigate Distribution Shift and Partial Data Coverage
- Blog: Imitation from Arbitrary Experience: A Dual Unification of Reinforcement and Imitation Learning Methods
- Blog: Revisiting the Linear-Programming Framework for Offline RL with General Function Approximation
- Blog: Offline Learning in Markov Games with General Function Approximation
- Blog: Offline Reinforcement Learning with Realizability and Single-policy Concentrability
- Blog: On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation
- Blog: Importance-Weighted Offline Learning Done Right
- Blog: PASTA: Pessimistic Assortment Optimization
- Blog: Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL
- Blog: Optimal Estimation of Policy Gradient via Double Fitted Iteration
- Blog: Model-based Reinforcement Learning for Confounded POMDPs
- Blog: Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning
- Blog: The Efficacy of Pessimism in Asynchronous Q-Learning
- Blog: A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO
- Blog: Policy learning "without" overlap: Pessimism and generalized empirical Bernstein's inequality
- Blog: Mitigating Covariate Shift in Imitation Learning via Offline Data With Partial Coverage
- Blog: Data-Efficient Policy Evaluation Through Behavior Policy Search
- Blog: On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation
- Blog: Robust Offline Reinforcement Learning for Non-Markovian Decision Processes
- Blog: Greedy Sampling Is Provably Efficient for RLHF
- Blog: A Natural Extension To Online Algorithms For Hybrid RL With Limited Coverage
- Blog: Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization
- Blog: Pessimism meets VCG: Learning Dynamic Mechanism Design via Offline Reinforcement Learning
- Blog: Functional Critic Modeling for Provably Convergent Off-Policy Actor-Critic
- Blog: A Primal-Dual Algorithm for Offline Constrained Reinforcement Learning with Linear MDPs
- Blog: Is Pessimism Provably Efficient for Offline RL?
- Blog: Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning
- Blog: Provably Efficient Offline Goal-Conditioned Reinforcement Learning with General Function Approximation and Single-Policy Concentrability
- Blog: Offline Actor-Critic for Average Reward MDPs
- Blog: Offline Learning in Markov Games with General Function Approximation
- Blog: Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning
- Blog: Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data
- Blog: Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity
- Blog: The Importance of Pessimism in Fixed-Dataset Policy Optimization
- Blog: Offline RL of the Underlying MDP from Heterogeneous Data Sources
- Blog: Hybrid Reinforcement Learning in Adversarial Markov Decision Processes
- Blog: A Primal-Dual-Critic Algorithm for Offline Constrained Reinforcement Learning
- Blog: Offline RL via Feature-Occupancy Gradient Ascent
- Blog: The Role of Inherent Bellman Error in Offline Reinforcement Learning with Linear Function Approximation
- Blog: Provably Good Batch Reinforcement Learning Without Great Exploration
- Blog: Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism
- Blog: The In-Sample Softmax for Offline Reinforcement Learning
- Blog: Settling the sample complexity of model-based offline reinforcement learning
Showing 60 of 61 papers.
History & citation
Current · Permanent link
- This direction split from Offline Reinforcement Learning with Single Policy Concentrability (89% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_single_policy_concentrability_ed7ed8c1,
title = {single-policy concentrability},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/single-policy-concentrability/rdr_ed7ed8c1afd9472d9dc063dd8d7419aa},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_single_policy_concentrability_ed7ed8c1_v1,
title = {single-policy concentrability},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/single-policy-concentrability/rdr_ed7ed8c1afd9472d9dc063dd8d7419aa/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}