Paper tackles efficient evaluation of natural stochastic policies in offline RL.
problem Efficiency issues in evaluating natural stochastic policies due to unknown evaluation policy.
method Derive efficiency bounds for tilting and modified treatment policies, propose nonparametric estimators.
result Proposed estimators attain efficiency bounds under lax conditions and enjoy partial double robustness.
Paper addresses offline policy evaluation in RL, achieving near-optimal bounds for various policy classes.
problem Evaluate all policies in a class simultaneously for offline RL.
method Uniform convergence in OPE for various policy classes, achieving optimal episode complexity.
result Achieves optimal episode complexity of O(H^3/d_mε^2) for identifying ε-optimal policies.
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.
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 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.
Paper tackles policy selection with logged data and limited online interactions.
problem Safe evaluation and deployment of offline reinforcement learning policies.
method Active offline policy selection combining logged data with online interaction.
result Improves upon state-of-the-art OPE estimates and pure online policy evaluation.
Paper tackles offline SSP with value iteration for policy evaluation and learning.
problem Goal-oriented RL with offline data and cost minimization.
method Simple value iteration algorithms for OPE and offline policy learning.
result Strong instance-dependent bounds implying near-minimax optimal worst-case bounds.
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.
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.
BCRL learns a Bellman complete representation for offline RL policy evaluation.
problem Learning a Q-function efficiently from offline data.
method BCRL learns a linear Bellman complete representation directly from data, enabling efficient OPE.
result BCRL achieves competitive OPE error and outperforms FQE in certain scenarios.
New method efficiently evaluates policies using trajectory data.
problem Statistically efficient policy evaluation with limited data.
method Trajectory-based approach for policy evaluation.
result Improved sample complexity for policy evaluation.
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.
Develops a support-aware framework for reserve-policy selection in advertising markets.
problem Log-based reserve-price evaluation risks weak support and subgroup harm.
method Support-aware offline decision framework converting logged evidence into certified policies.
result Preserves the best gate-passing policy while eliminating only policies with certified regret.
One-step policy improvement outperforms iterative RL methods on D4RL.
problem Improving offline RL without off-policy evaluation.
method One-step constrained/regularized policy improvement using on-policy Q estimates.
result One-step algorithm outperforms iterative algorithms on D4RL benchmark.
Offline RL policies should adapt to unknown aspects of the environment.
problem Uncertainty in offline RL datasets leads to suboptimal policies.
method Adaptive policies that consider all transitions seen so far, solving an implicit POMDP.
result Optimal adaptive policies improve offline RL performance.
Benchmarking off-policy evaluation methods for complex policies.
problem Lack of comprehensive benchmarks for off-policy evaluation methods.
method Collection of challenging high-dimensional control tasks and datasets.
result Standardized measure of progress for OPE methods.
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.
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.
Reinforcement learning is well suited for optimizing policies of recommender systems. Current solutions mostly focus on model-free approaches, which require frequent interactions with the real environment, and thus are expensive in model learning. Offline evaluation methods, such as importance sampling, can alleviate s…
New insights on offline RL with state aggregation and trajectory data.
problem Understanding sample complexity in offline policy evaluation.
method Analyzing concentrability coefficient in aggregated Markov Transition Model.
result Sample complexity depends on concentrability coefficient in aggregated model.
A new method combines online and offline learning to tackle contextual bandits with missing action support.
problem Learning optimal policies with logged data when the logging policy has deficient support.
method Hybrid approach using online exploration to exploit supported actions and offline learning to avoid unnecessary explorations.
result Determines an optimal policy with theoretical guarantees using minimal online explorations.
The paper proposes autoregressive models for better offline RL.
problem Offline RL policy evaluation and optimization challenges.
method Autoregressive dynamics models for sequential state and reward prediction.
result Autoregressive models outperform standard methods in log-likelihood and RL tasks.
New method tackles safe reinforcement learning from offline data.
problem Learn optimal policies from fixed data while adhering to safety constraints.
method Combines offline RL with online optimization to minimize cumulative cost.
result Proves approximate optimality of the approach under certain conditions.
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 …
PyCFRL helps ensure fair reinforcement learning policies from offline data.
problem Ensuring fairness in reinforcement learning policies for disadvantaged groups.
method Sequential data preprocessing to learn counterfactually fair policies.
result PyCFRL implements a novel algorithm for fair RL policy learning.
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.
ESRL uses uncertainty quantification to learn safe, optimal policies in offline RL.
problem Challenges in interpreting and measuring uncertainty of learned policies in offline RL.
method Expert-Supervised Reinforcement Learning (ESRL) framework that uses hypothesis testing and posterior distributions.
result The framework can learn safe and optimal policies with theoretical guarantees and independent sample efficiency.
Paper tackles policy selection in offline RL without hyperparameters.
problem Selecting between policies and value functions in offline RL.
method Designs hyperparameter-free algorithms based on BVFT for policy selection.
result Demonstrates effectiveness in discrete-action benchmarks like Atari.
Offline RL with pre-trained features amplifies errors even under mild shifts.
problem Sample-efficient offline RL with pre-trained features under mild distribution shift.
method Empirical study of offline RL with pre-trained neural representations.
result Substantial error amplification occurs even with pre-trained features, requiring stronger conditions for successful 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.
A new policy switching technique improves offline RL performance.
problem Challenges in adapting off-policy algorithms to different datasets and tasks.
method Combines off-policy RL and BC, using epistemic uncertainty for policy switching.
result Outperforms individual algorithms and state-of-the-art methods on benchmarks.
This work improves policy evaluation and selection using logarithmic smoothing for pessimistic off-policy estimation.
problem Offline evaluation and selection of policies from past data.
method Develops novel concentration bounds and a logarithmically smoothed estimator (LS) for improved policy selection and learning.
result The logarithmically smoothed estimator (LS) provides tighter bounds and better policy selection and learning.
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.
We review basic concepts of convex duality, focusing on the very general and supremely useful Fenchel-Rockafellar duality. We summarize how this duality may be applied to a variety of reinforcement learning (RL) settings, including policy evaluation or optimization, online or offline learning, and discounted or undisco…
Offline RL tackles resource-constrained online deployment with improved policy transfer.
problem Training policies with limited online features using a rich offline dataset.
method Introduce a policy transfer algorithm that first trains a teacher agent with full offline features and then transfers knowledge to a student agent with limited online features.
result Consistent improvement in performance over baseline methods on resource-constrained datasets.
Oracle-efficient algorithm for offline RL with partial data coverage.
problem Offline reinforcement learning with partial data coverage and constraints.
method PDOCRL, a primal-dual algorithm with decomposed linear-programming formulation.
result Near-optimal, near-feasible policy with \(\widetilde{\mathcal O}(ε^{-2})\) sample guarantee.
BOMS enhances offline MBRL by improving model selection with Bayesian optimization.
problem Inaccurate model selection in offline MBRL due to distribution shift.
method Proposes BOMS, an active model selection framework using Bayesian optimization.
result Improves model selection with only a small amount of online interaction.
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.
HAMBO estimates policy performance by hallucinating worst-case trajectories, providing valid lower bounds.
problem Conservative off-policy evaluation of policies in real-world applications.
method HAMBO hallucinates worst-case trajectories based on learned model uncertainty.
result Valid lower bounds on policy performance, converging to true expected return under regular conditions.
We present and prove properties of a new offline policy evaluator for an exploration learning setting which is superior to previous evaluators. In particular, it simultaneously and correctly incorporates techniques from importance weighting, doubly robust evaluation, and nonstationary policy evaluation approaches. In a…
The paper tackles personalized policy learning from diverse data sources in a federated setting.
problem Learning personalized decision policies from observational bandit feedback across multiple heterogeneous data sources.
method Introduces a novel regret analysis for distinguishing global and local regret, and presents a federated policy learning algorithm using local policies trained with doubly robust offline policy evaluation strategies.
result Establishes finite-sample upper bounds on global and local regret, characterizing them by source heterogeneity and distribution shift.
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.
A novel approach for safe offline RL using latent safety constraints.
problem Balancing safety constraints and reward maximization in offline RL.
method Conditional Variational Autoencoders for latent safety modeling, Constrained Reward-Return Maximization.
result Our approach maintains safety compliance while optimizing rewards, outperforming existing methods.
Study optimal offline RL with uncertainty sets and distribution shifts.
problem Optimal offline reinforcement learning with limited data.
method Construct uncertainty sets and distribution shifts, solve robust Markov decision process.
result Least conservative estimator for unknown true distribution.
Study off-policy evaluation and learning in dynamic pricing with context.
problem Dynamic personalized pricing and operations management problems with high-dimensional user types.
method Formalize causal structure, leverage single time-step evaluation, estimate marginal MDP.
result Improved out-of-sample policy performance in dynamic and capacitated pricing.
New method for robust policy evaluation in offline reinforcement learning with sequentially exogenous unobserved confounders.
problem Offline reinforcement learning in domains with unobserved confounders.
method Orthogonalized robust fitted-Q-iteration with closed-form solutions and bias-correction.
result Effective in simulations and real-world data, improving robustness and computational ease.
Hybrid RL algorithm combines offline and online data for robust and efficient policy learning.
problem Combining robust on-policy methods with efficient offline data for hybrid RL.
method Integrates off-policy training on offline data into on-policy NPG framework.
result Achieves state-of-the-art theoretical guarantees and maintains on-policy NPG guarantees.