Study minimax-optimal rates for offline decision-making with function approximation.
problem Statistical complexity of offline decision-making with function approximation.
method Near minimax-optimal rates for stochastic contextual bandits and Markov decision processes, using pseudo-dimension and behavior policy.
result Established performance limits and new characterization of behavior policy.
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.
This tutorial reviews offline RL methods and challenges in deep learning.
problem Extracting optimal policies from large datasets without online data.
method Review of existing offline RL algorithms and potential solutions.
result Challenges and open problems in modern deep RL methods.
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.
New algorithms improve decision-making with limited offline data.
problem Using limited offline data to cluster users for better decision-making.
method Proposed two algorithms: Off-C2LUB and Off-CLUB to address data insufficiency.
result Both algorithms outperform existing methods under limited offline user data.
New algorithms use offline data to improve online decision-making with latent states.
problem Accelerating online sequential decision-making with latent states in offline data.
method Design end-to-end latent bandit algorithms for linear latent contextual bandits, learning latent subspace offline and using it online.
result Proves minimax optimal regret guarantees for online algorithms and practical efficiency.
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.
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.
Meta-KeL learns kernels from offline data to improve sequential decision-making.
problem Adaptive confidence sets for prediction functions in sequential decision-making tasks.
method Meta-KeL: meta-learning a kernel from offline data; structured sparsity estimator for unknown kernel combinations.
result Valid confidence sets that become as tight as those given the true unknown kernel with increasing offline data.
In data-limited settings, stochastic policies can outperform deterministic ones in bandit problems.
problem Making reliable decisions with limited data in bandit problems.
method Designing TRUST, an algorithm that uses localization laws and relative pessimism.
result TRUST achieves comparable sample complexity to LCB on minimax problems but is significantly lower on few-sample problems.
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.
Interactive IL beats BC by state-wise annotation cost.
problem Behavior Cloning struggles with annotation cost in sequential decision making.
method Proved Stagger and Warm Stagger algorithms to outperform BC.
result Interactive and hybrid IL methods outperform BC with state-wise annotation.
Paper tackles sample-efficient offline RL, proposing data diversity and unified algorithms.
problem Sample-efficient learning from historical data for sequential decision-making.
method Proposes data diversity and unifies three offline RL algorithm classes: VS, RO, and PS.
result Comparable sample efficiency for VS, RO, and PS algorithms under standard assumptions.
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.
Efficient offline reinforcement learning with neural networks using differentiable function approximation.
problem Statistical efficiency of offline reinforcement learning with function approximators.
method Pessimistic fitted Q-learning (PFQL) and differentiable function approximation.
result Provably efficient offline reinforcement learning with differentiable function approximation.
New approach uses autoregressive models to explore and quantify uncertainty in decision-making.
problem Quantifying and exploring uncertainty in online decision-making.
method Reformulates uncertainty as missing future outcomes, training autoregressive models for next-outcome prediction.
result Establishes a reduction from online learning to offline next-outcome prediction, controlling Bayesian regret by sequence prediction loss.
Paper analyzes sample complexity of offline MABs with KL regularization.
problem Optimizing sample complexity for offline decision-making with KL-regularized metrics.
method Sharp analysis of KL-PCB, providing upper and lower bounds.
result Characterizes sample complexity for offline MABs with KL regularization.
Offline RL struggles with sample efficiency due to fundamental barriers.
problem Sample efficiency in offline RL with value function approximation.
method Analyzes the necessity of distributional and representational assumptions.
result Even with concentrability and realizability, sample complexity is polynomial in state space size.
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.
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.
New offline RL algorithms tackle partial data coverage with optimal performance and practicality.
problem Partial data coverage in offline RL datasets.
method Augmented Lagrangian method applied to MIS formulation for optimal offline RL.
result Statistically optimal offline RL with practical performance, eliminating conservatism.
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 \mathcal{C} C -mixing data. result Explicit efficiency of deep adversarial offline RL frameworks demonstrated with two converging error components.
Interpole learns transparent decision-making policies from data.
problem Understanding human decision-making in opaque environments.
method Interpole combines belief-update and belief-action mapping estimation.
result Interpole provides interpretable models of decision-making behavior.
MoMA improves model-based RL by using unrestricted policy classes.
problem Limited sample efficiency and generalizability in model-based offline RL.
method Model-based mirror ascent algorithm with general function approximations.
result Theoretical guarantees and practical implementation of MoMA.
New algorithm learns optimal policies in strategic MDPs with private types.
problem Optimal policy learning in strategic MDPs with private types and information asymmetry.
method PLAN algorithm using instrumental variable regression and pessimism principle.
result PLAN achieves near-optimal policy with 1 / K 1 / \sqrt{K} 1/ K optimality. New findings explain why online methods outperform offline methods in noisy expert feedback settings.
problem The challenge of learning from imperfect expert feedback in sequential decision-making systems.
method Introduced a noisy expert model and a novel variant of on-policy distillation (OPD) to address the gap between offline and online imitation learning.
result Online interaction with a noisy expert via OPD enables polynomial dependence on the horizon, unlike offline methods which require exponential growth in sample complexity.
Transforms offline greedy algorithms to online algorithms for combinatorial problems.
problem Online decision-making in time-varying combinatorial environments.
method General framework using Blackwell approachability and Bandit Blackwell approachability.
result Achieves O ( T ) O(\sqrt{T}) O ( T ) regret in full information setting and O ( T 2 / 3 ) O(T^{2/3}) O ( T 2/3 ) regret in bandit setting. Study human-machine interaction with private info using offline RL.
problem Confounding bias and distributional mismatch in offline RL for human-guided interaction.
method Developed a novel identification result and OPE method to address confounding bias, and used pessimism to tackle distributional mismatch.
result Policy pair converges to optimal one at satisfactory rate under mild assumptions.
Simplifies BCQ to match and outperform state-of-the-art in offline RL benchmarks.
problem Sample efficiency in offline reinforcement learning.
method Introduces EMaQ, a novel backup operator for offline RL.
result EMaQ matches and outperforms prior state-of-the-art in offline RL benchmarks.
Bridges uplift modeling and sequential decision-making with online budget allocation.
problem Treatment allocation under budget constraints in digital advertising.
method Budget-Constrained Causal Bandits (BCCB) integrates learning, exploration, and budget pacing.
result Data-efficiency crossover: BCCB operates effectively from the first user, 3-5x lower performance variance.
Study risk-sensitive RL in offline settings, improving efficiency and accuracy.
problem Efficiently derive near-optimal policies for risk-sensitive RL using offline data.
method Introduced two provably sample-efficient algorithms for risk-sensitive offline RL in linear MDPs.
result First provably efficient risk-sensitive offline RL algorithms.
New algorithm reduces online decision-making regret with efficient LP re-solving and parallel first-order method.
problem Worse regret guarantees and high computational cost of LP-based OLP algorithms.
method Combines LP-based and first-order OLP methods, re-solving LP subproblems periodically and using parallel first-order method.
result Achieves O ( log ( T / f ) + f ) \mathscr{O}(\log (T/f) + \sqrt{f}) O ( log ( T / f ) + f ) regret, balancing computational efficiency and superior regret guarantee. Proposes a method to learn from historical data for personalized decision-making.
problem Sample hunger in sequential decision-making algorithms for personalized medicine.
method Identifiable latent bandit framework using nonlinear independent component analysis.
result Optimal decision-making with shorter exploration time than classical bandits.
Behavior cloning can achieve horizon-independent sample complexity in offline imitation learning.
problem Sample complexity in imitation learning increases with problem horizon.
method New analysis of behavior cloning with logarithmic loss.
result Behavior cloning can achieve linear dependence on horizon in offline IL under dense rewards.
A framework identifies worst-case decision points in safety-critical scenarios, improving risk assessment by 10 hours.
problem Identifying worst-case outcomes in safety-critical decision-making under uncertainty.
method Explicitly estimating distributions of expected return to identify dead-ends, tuning based on risk tolerance.
result Significantly improves risk assessment, providing indications 10 hours earlier and increasing detection by 20%.
Unified LP framework for offline reward learning from human demonstrations and feedback.
problem Reward learning from human demonstrations and feedback with robustness and sample efficiency.
method A novel linear programming framework for offline reward learning.
result Unified LP framework achieves better performance compared to MLE.
Unified framework for constrained online decision-making.
problem Sequential decisions under stage-wise feasibility constraints.
method Upper counterfactual confidence bounds and generalized eluder dimension.
result Principled foundation for constrained sequential decision-making.
An online decision-making algorithm using stochastic gradient descent for big data.
problem Efficiently updating decision rules in online decision making with big data.
method Stochastic gradient descent for online updates, asymptotic normality of estimators.
result Asymptotic normality of parameter and value estimators, enabling statistical inference.
Bayesian method estimates dynamics from near-optimal trajectories.
problem Estimating dynamics from near-optimal expert trajectories in reinforcement learning.
method Constraint-based Bayesian approach integrating expert near-optimality.
result Significant improvements in decision-making and transfer success.
Improved fast rates for decision making with forward-KL regularization in contextual bandits.
problem Improving fast rates for decision making with forward-KL regularization in contextual bandits.
method Streamlined analysis of forward-KL-regularized offline CBs, exploiting the pessimism principle and convex-analytical pipeline.
result First i l d e O ( ε − 1 ) ilde{O}(ε^{-1}) i l d e O ( ε − 1 ) upper bounds in tabular and general function approximation settings. Paper tackles robust reinforcement learning with minimal data.
problem Learning robust policies from limited data in uncertain environments.
method Distributionally robust formulation, model-based algorithm combining value iteration and pessimism.
result Proves near-optimal sample complexity for robust offline RL.
Improves BC policies by generating new plausible trajectories.
problem Sub-optimal data quality in BC leads to poor policy performance.
method Trajectory Stitching (TS) generates new plausible transitions.
result TS significantly improves behavioural policies over original data.
Paper tackles robust decision-making from multiple sites with shared structure.
problem Learning robust sequential decisions from heterogeneous multi-site datasets.
method Group-Robust MDPs with d-rectangular uncertainty sets, feature-wise worst-case aggregation, and cluster-level pooling.
result Proves suboptimality bound for robust planning policy under robust partial coverage assumption.
Study optimal pricing and inventory control in dynamic settings with censored demand.
problem Optimal pricing and inventory control in dynamic settings with censored demand.
method Approximate optimal policy via high-order MDP, propose novel algorithms for solving Bellman equations.
result Established finite-sample regret bounds and demonstrated efficacy through numerical experiments.
POLAR optimizes treatment strategies in dynamic settings with statistical guarantees.
problem Optimizing sequential decisions in dynamic treatment regimes with robustness and statistical guarantees.
method Pessimistic model-based approach estimating transition dynamics and incorporating uncertainty penalties.
result Offers statistical and computational guarantees, including finite-sample bounds on policy suboptimality.
New method improves decision-making accuracy without complex calculations.
problem Improving decision-making accuracy in machine learning.
method Introducing a new measure called calibration decision loss ( C D L K \mathsf{CDL}_K CDL K ) for structured families of post-processing functions. result Proves upper and lower bounds for natural classes K K K of post-processing functions. The (contextual) multi-armed bandit problem (MAB) provides a formalization of sequential decision-making which has many applications. However, validly evaluating MAB policies is challenging; we either resort to simulations which inherently include debatable assumptions, or we resort to expensive field trials. Recently …
Improves RL from historical data by stitching trajectories.
problem Lack of high-quality data for offline RL.
method Trajectory Stitching (TS) to augment historical data with synthetic actions.
result Improves RL policy performance over baseline.