New framework converts offline to online estimation using black-box offline estimators.
problem Convert offline estimation algorithms to online estimation algorithms.
method Oracle-Efficient Online Estimation (OEOE) framework.
result Achieves near-optimal online estimation error via black-box offline estimators.
Framework reduces contextual bandit learning to offline regression with near-optimal regret.
problem Efficient learning with large action spaces and complex reward functions.
method Offline Estimation to Decisions (OE2D) algorithm that minimizes regret with near-optimal oracle calls.
result Near-optimal regret for contextual bandits with large action spaces and O(log(T)) offline oracle calls. Paper tackles robust offline RL with heavy-tailed rewards.
problem Real-world applications often encounter heavy-tailed rewards, challenging offline RL.
method Proposes ROAM and ROOM algorithms using median-of-means method for robust off-policy evaluation and OPO.
result Demonstrates superior performance on heavy-tailed reward datasets compared to existing methods.
OE2D framework reduces contextual bandits to offline regression for near-optimal regret.
problem Efficiently learning contextual bandits with large action spaces and complex reward functions.
method Offline Estimation to Decisions (OE2D) algorithm that reduces contextual bandits to offline regression.
result Near-optimal regret for contextual bandits with large action spaces and O(logT) calls to an offline regression oracle. Efficient algorithm for CMDPs reduces to offline density estimation.
problem Offline learning for CMDPs with horizon H.
method Reduction to offline density estimation, layerwise exploration-exploitation tradeoff.
result First efficient and near-optimal reduction from CMDPs to offline density estimation.
New methods for evaluating and optimizing policies in offline RL with unobserved confounders.
problem Evaluating and optimizing policies in the presence of unobserved confounders.
method Characterized settings and algorithms for consistent value estimates and lower bounds, with sample complexity guarantees.
result Proved local convergence guarantees for offline policy improvement.
This work characterizes conditions for offline policy evaluation in reinforcement learning.
problem Understanding when classical methods succeed in offline policy evaluation for linear function approximation.
method Control-theoretic and linear-algebraic conditions for classical methods (FQI and LSTD).
result A precise hierarchy of regimes under which these estimators succeed, and a complete picture of their behavior.
OPERA blends multiple OPE estimators to evaluate new policies offline.
problem Lack of reliable offline policy evaluation methods for new policies.
method Adaptive blending of multiple OPE estimators without explicit selection.
result Consistent and reliable policy evaluation framework for offline RL.
Paper offers a fast convergence theory for offline decision making.
problem Offline decision making problems, including reinforcement learning and off-policy evaluation.
method Introduces a framework (DMOF) and algorithm (EDD) with a fast convergence guarantee.
result Demonstrates a fast convergence guarantee with a lower bound complement.
RORL improves offline RL robustness with conservative smoothing.
problem Distribution shift and robustness issues in offline RL.
method RORL introduces regularization and conservative smoothing for robustness.
result RORL achieves state-of-the-art performance and robustness to adversarial perturbations.
Anchor-TS uses median anchoring to improve online decision-making from offline data with distribution shift.
problem Improving online decision-making from offline data with distribution shift.
method Sample-Mean Anchored Thompson Sampling (Anchor-TS) with median anchoring.
result Anchor-TS safely leverages offline data to accelerate online learning and reduces regret.
A new method, Count-MORL, improves offline reinforcement learning by using state-action frequency.
problem Improving offline reinforcement learning performance.
method Integrates count-based conservatism into model-based offline reinforcement learning.
result The learned policy is near-optimal and outperforms existing methods.
New method finds unseen states for RL, improving performance.
problem Offline RL struggles with unseen states and actions.
method Value-informed state perturbations and filtering.
result Improved performance in offline RL tasks.
New Bellman error estimator improves offline model selection performance.
problem Selecting the best policy from logged data using mean squared Bellman error.
method Developed a more accurate estimator of MSBE and analyzed conditions for successful OMS.
result New estimator achieves impressive offline model selection performance on diverse tasks.
Study shows offline RL under Q⋆-approximation and partial coverage is harder than previously thought.
problem Theoretical limits of offline reinforcement learning under Q⋆-approximation and partial coverage. method Introduced a decision-estimation framework to decompose offline RL complexity into decision and value estimation errors.
result Answered the open question by proving sample inefficiency under partial coverage is not guaranteed by Q⋆-realizability and Bellman completeness. New algorithms estimate Q-functions under partial coverage and realizability, improving offline RL guarantees.
problem Offline RL with limited exploration and assumptions about data coverage and Q-function realizability.
method Proposes minimax learning algorithms to estimate soft or vanilla Q-functions with L2-convergence guarantees. result PAC guarantees for offline RL under partial coverage and realizability conditions.
Paper develops neural network approximation for pessimistic offline RL with theoretical guarantees.
problem Challenges in offline reinforcement learning with deep neural networks and data dependence.
method Establishes estimation error for pessimistic offline RL using neural network approximation with C-mixing data. result Explicit efficiency of deep adversarial offline RL frameworks demonstrated with two converging error components.
Study nonparametric estimator for Markov chain transition matrices in offline setting.
problem Estimating transition matrices of finite controlled Markov chains from logged data.
method Developed sample complexity bounds and conditions for minimaxity.
result Achieving certain statistical risk requires balancing mixing properties and sample size.
Enhances causal estimation using unlabeled offline ICU data.
problem Assessing unmeasured physiological variables in new ICU patients.
method Three-stage approach: non-causal and causal estimators, causal filter, and prediction for new patients.
result Enhanced causal estimation for new ICU patients using offline data.
Develops a method to efficiently use offline data for RL policy optimization.
problem Lack of online data for offline RL in mobile health applications.
method Advantage learning framework using optimal Q-estimators.
result New policy converges faster than existing methods.
Paper tackles offline preference-based RL with human feedback.
problem Offline Preference-based Reinforcement Learning with preference feedback.
method Two-step approach: MLE for reward estimation and distributionally robust planning.
result First guarantee for learning any target policy with polynomial samples.
New method selects best offline RL policies from logged data.
problem Hyperparameter selection challenges offline RL.
method Offline hyperparameter selection for RL algorithms.
result Reliable ranking and selection of policies across hyperparameters.
A new algorithm improves offline reinforcement learning robustness.
problem Finding optimal policies in perturbed environments from offline data.
method Doubly Pessimistic Model-based Policy Optimization (P^2MPO) framework.
result Proves sample efficiency with robust partial coverage data.
Off-policy reinforcement learning (RL) using a fixed offline dataset of logged interactions is an important consideration in real world applications. This paper studies offline RL using the DQN replay dataset comprising the entire replay experience of a DQN agent on 60 Atari 2600 games. We demonstrate that recent off-p…
PDCA algorithm learns policies for RL with constraints using a primal-dual approach.
problem Offline constrained reinforcement learning with general function approximation.
method Primal-Dual-Critic Algorithm (PDCA) using a primal-dual approach.
result PDCA finds a near saddle point of the Lagrangian, nearly optimal for constrained RL.
Pessimistic Q-learning improves sample efficiency in offline reinforcement learning.
problem Insufficient coverage and sample scarcity in offline reinforcement learning datasets.
method Pessimistic Q-learning algorithm for offline reinforcement learning, focusing on variance reduction.
result Near-optimal sample complexity achieved with the proposed algorithm.
MOReL learns offline RL policies using pessimistic MDPs.
problem Offline RL's data efficiency and velocity.
method Two-step process: learn P-MDP and near-optimal policy in it.
result MOReL is minimax optimal and matches state-of-the-art results.
A simple approach to offline RL without additional complexity.
problem Learning from a fixed dataset of actions with value estimation errors.
method Adding a behavior cloning term to the policy update of an online RL algorithm and normalizing the data.
result Matches the performance of state-of-the-art offline RL algorithms with minimal changes.
The paper tackles reward-relevance in offline RL with sparse decision dynamics.
problem Offline reinforcement learning with sparse decision dynamics and estimation sparsity.
method Reward-filtered least-squares policy evaluation using thresholded lasso.
result The method provides theoretical guarantees with sample complexity dependent on sparse component size.
New algorithm tackles confounding in offline RL for partially observable MDPs.
problem Confounding in offline reinforcement learning for partially observable MDPs.
method P3O algorithm using proximal causal inference and pessimistic confidence regions.
result Achieves n−1/2-suboptimality for offline RL in POMDPs with confounded data. New methods tackle robust reinforcement learning in sparse, corrupted data.
problem Tackles robust reinforcement learning in sparse, corrupted data.
method Proposes actor-critic methods with sparse robust estimator oracles.
result First non-vacuous guarantees in high-dimensional sparse MDPs with single-policy concentrability coverage.
This paper improves offline contextual bandits using distributional robustness.
problem Improving offline contextual bandits with robustness.
method Extends Distributionally Robust Optimization (DRO) for offline contextual bandits, introducing a convex reformulation of Counterfactual Risk Minimization.
result Automatic calibration of asymptotic confidence intervals for policy optimization.
GenDICE estimates stationary values from offline data.
problem Estimating stationary values from limited offline data.
method Ratio correction based on stationary distribution properties, variational divergence minimization.
result Consistent estimation of stationary values possible in offline settings.
This paper explores how IV methods can improve Q-function estimates in offline policy evaluation.
problem Confounding in estimating Q-function using reinforcement learning.
method Integrates IV techniques into offline policy evaluation (OPE) to improve Q-function estimates.
result State-of-the-art OPE methods are closely matched in performance by some IV methods.
Develops a method to evaluate OPE robustness to hyperparameters and policies.
problem Difficulty in selecting and tuning OPE estimators due to limited experimental evaluations.
method Introduces IEOE (Interpretable Evaluation for Offline Evaluation) to assess robustness.
result Demonstrates improved evaluation of OPE estimators' reliability.
Paper proposes a policy gradient method for confounded POMDPs.
problem Estimating policy gradients for confounded POMDPs with continuous state and observation spaces.
method Developed a novel identification result to estimate policy gradients using offline data, solved conditional moment restrictions, and applied min-max learning with function approximation.
result Showed global convergence of the proposed algorithm in finding the optimal policy.
Meta-agent learns effective exploration from offline data.
problem Design a meta-agent to quickly maximize reward in unseen tasks.
method Bayesian RL approach with adaptive neural belief estimate.
result Meta-agent learns effective exploration behavior from diverse tasks.
CASP selects reliable policies for two-stage recommender systems by considering both value and support.
problem The selection of a generator in two-stage recommender systems affects both the policy value and the data support used to estimate it.
method CASP combines doubly robust value estimation with a support-burden penalty.
result CASP selects lower-burden policies when estimated value and support credibility are in tension.
Study efficient offline RL in Markov games with general models.
problem Learn approximate equilibria from offline data in Markov games.
method Use Bellman-consistent pessimism for interval estimation and optimize gap relaxation.
result First framework for sample-efficient offline learning in Markov games, handling all equilibria.
New offline RL study shows exponential sample requirement for accurate policy evaluation.
problem Understanding statistical limits of offline RL with linear function approximation.
method Analyzes necessary representational and distributional conditions for sample-efficient offline reinforcement learning.
result Even with realizability and good feature coverage, offline RL requires exponential samples for accurate policy evaluation.
Investigates offline RL in factorisable action spaces, overcoming overestimation bias.
problem Overestimation bias in value estimates for unseen state-action pairs.
method Value-decomposition approach in DecQN, adapted for factorised discrete action spaces.
result Demonstrates the effectiveness of factorised approach in offline RL.
Study tight offline learning bounds for linear MDPs using variance information.
problem Understanding statistical limits with linear function representations in offline reinforcement learning.
method Variance-aware pessimistic value iteration (VAPVI) that reweights Bellman residuals based on estimated variances.
result Improved offline learning bounds expressed in terms of system quantities.
New OPE estimator improves offline policy evaluation for large action spaces.
problem Existing OPE estimators fail with large action spaces, leading to extreme bias and variance.
method Proposes a new estimator using marginalized importance weights and action embeddings.
result Empirical performance improvement enables reliable OPE even with many actions.
A new method calibrates value predictions in offline RL to improve reliability.
problem Difficulty in long-horizon value prediction in offline reinforcement learning.
method Bellman calibration, a weak reliability criterion, and Iterated Bellman Calibration.
result Finite-sample guarantees show that Bellman calibration error is controlled at nonparametric rates.
This paper sets communication complexity bounds for distributed RL.
problem Establishing minimum communication requirements for distributed RL.
method Information-theoretic lower bounds and algorithm development.
result Developed algorithms achieving optimal risk up to logarithmic factors.
GradientDICE improves offline estimation for reinforcement learning policies.
problem Estimating density ratios between target policy and sampling distributions in reinforcement learning.
method GradientDICE reparameterizes the optimization problem to avoid nonlinearity, ensuring convergence and consistency.
result GradientDICE is provably convergent and eliminates the need for nonlinearity in parameterization.
New method for estimating and optimizing MDPs without stationarity.
problem Challenges in offline contextual MDP estimation without stationarity.
method Introduces a new adaptive estimation and cost optimization approach for contextual MDPs.
result First robust, theoretically backed method for offline contextual MDP estimation.
Study optimal product assortment using historical data, proving item coverage suffices.
problem Offline assortment optimization under MNL model with limited historical data.
method Pessimistic Rank-Breaking (PRB) algorithm combining rank-breaking and pessimistic estimation.
result Optimal item coverage is both sufficient and necessary for efficient offline learning.