Study contextual online pricing with biased offline data, achieving optimal regret bounds.
problem Contextual online pricing with biased offline data.
method Identify δ2 to measure data bias, use OFU policy and robust variant for unknown bias. result Achieve minimax-optimal regret bounds for contextual pricing.
The paper tackles bandit problems with biased offline data by using causal methods.
problem Improving bandit algorithms with biased offline data that includes confounding and selection biases.
method Formalizes the problem from a causal perspective, categorizes biases, and derives robust bounds for each arm.
result Causal bounds can guide the bandit agent to learn a nearly-optimal decision policy and consistently reduce asymptotic regret.
New method uses offline data to improve online bandit learning, even when distributions differ.
problem Improving online bandit learning with different offline and online distributions.
method MIN-UCB policy that adapts to offline data when informative, achieving tight regret bounds.
result MIN-UCB policy outperforms UCB policy with offline data and provides tight regret bounds.
This study simulates biases in classifiers to assess fairness.
problem Mitigating biases in predictive models to ensure fairness.
method Agent-based model (ABM) to generate synthetic datasets with controlled biases, applied to offline and online learning approaches.
result Demonstrates how biases in data affect classifier outcomes and how mitigations impact feature usage.
Online field experiments are the gold-standard way of evaluating changes to real-world interactive machine learning systems. Yet our ability to explore complex, multi-dimensional policy spaces - such as those found in recommendation and ranking problems - is often constrained by the limited number of experiments that c…
Machine learning models learn what we teach them to learn. Machine learning is at the heart of recommender systems. If a machine learning model is trained on biased data, the resulting recommender system may reflect the biases in its recommendations. Biases arise at different stages in a recommender system, from existi…
Paper tackles offline RL with limited target samples using domain adaptation.
problem Limited samples in target dataset degrade offline RL performance.
method Proposes a framework to balance target and source datasets with theoretical guarantees.
result Establishes performance bounds and optimal weight for offline RL.
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.
Method uses pseudo-samples to improve RCT data in ride-hailing pricing studies.
problem Small and biased RCT data leads to significant bias when generalizing to broader user base.
method Pseudo-sample matching to expand and match RCT data with observational data.
result 0.41% improvement in profit through pseudo-sample matching.
Algorithm learns from offline data to improve performance in target environment.
problem Learning from offline data in a target environment with unknown shifts.
method Adaptive algorithm that uses offline data to improve performance when informative.
result Algorithm provably improves performance over purely online learning when offline data are informative.
Algorithm reduces online regret by leveraging offline data in linear bandits.
problem Online regret minimization in linear bandits with offline data.
method OOPE algorithm using extended D-optimal design.
result Substantial reduction in online regret compared to prior work.
Paper tackles offline meta-reinforcement learning with a new algorithm.
problem Performing reinforcement learning on limited data from a new task.
method Meta-Actor Critic with Advantage Weighting (MACAW) algorithm.
result Achieves notable gains over prior methods on offline meta-RL benchmarks.
Q-Distribution Guided Q-Learning corrects overestimation of uncertain OOD actions in offline RL.
problem Overestimation of Q-values for out-of-distribution actions in offline reinforcement learning.
method QDQ applies a pessimistic adjustment to Q-values in uncertain OOD regions based on a consistency model.
result QDQ improves performance on the D4RL benchmark and achieves significant improvements across many tasks.
Data driven soft sensor design has recently gained immense popularity, due to advances in sensory devices, and a growing interest in data mining. While partial least squares (PLS) is traditionally used in the process literature for designing soft sensors, the statistical literature has focused on sparse learners, such …
Fine-tuning RL with offline data reduces online interactions.
problem Optimizing RL with limited online interactions and offline data.
method Developed algorithm extsc{FTPedel} for MDPs with linear structure.
result Optimally reduces the number of online interactions needed.
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.
A3RL combines online and offline RL with active sampling to improve policy learning.
problem Combining online and offline RL for sample efficiency and robustness.
method A3RL uses a confidence-aware Active Advantage Aligned (A3) sampling strategy to prioritize data from both online and offline sources.
result A3RL outperforms competing online RL techniques that use offline data.
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.
Algorithm balances online and offline data for linear bandits.
problem Online learning with an offline dataset in linear bandits.
method Proposes a linear bandit algorithm that uses offline data early and increasingly favors exploration as the horizon grows.
result Establishes regret bounds showing competitive performance with both purely online and offline solutions.
Proposes an offline active learning method for graphs.
problem Active learning on graphs where labeling is expensive.
method Two-stage biased sampling strategy considering informativeness and representativeness.
result Establishes a theoretical relationship between generalization error and number of nodes selected.
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 approach estimates propagators for trading risky assets.
problem Estimating price impact kernel from static data for optimal trading.
method Nonparametric estimation of propagator using offline reinforcement learning.
result Pessimistic trading strategy optimises execution costs under uncertainty.
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.
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.
Survey of offline RL theory and practical algorithm design challenges.
problem Optimizing return from fixed agent trajectories without additional interactions.
method Theoretical insights and practical algorithm design.
result Conditions for practical offline RL algorithms and their limitations.
Model-Based Offline Planning (MBOP) learns models from offline data to control systems directly.
problem Training RL policies from offline data without direct system interaction.
method Generates models from offline data and uses planning to control the system.
result Near-optimal policies found for simulated systems with minimal real-time interaction.
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.
The paper studies OPE with missing data, showing bias under nonignorable missingness and proposing a solution.
problem Estimating value of a target policy from logged data with missingness.
method Investigates OPE with monotone missingness, proposes an IPW value estimator, and conducts statistical inference.
result Value estimates remain unbiased under ignorable missingness but can be biased under nonignorable missingness.
Paper proposes a hybrid RL algorithm that combines offline and online data without needing reward info.
problem How to efficiently use online data to improve RL policies using only offline data.
method A three-stage hybrid RL algorithm that uses reward-agnostic exploration and model-based offline RL.
result The hybrid RL algorithm outperforms both pure offline and pure online RL in sample complexity.
This work bridges offline RL and DRL to address distributional shift.
problem Distributional shift in offline RL due to difference in state-action visitation distributions.
method Proposes offline RL algorithms using DRL framework, characterizes sample complexity under single policy concentrability.
result Demonstrates superior performance of proposed algorithms through simulations.
A new offline RL framework unifies imitation learning and vanilla offline RL.
problem Learning from expert datasets without active data collection.
method A new offline RL framework that interpolates between imitation learning and vanilla offline RL, using a weak concentrability coefficient and a lower confidence bound algorithm.
result LCB algorithm achieves a faster rate of 1/N for nearly-expert datasets, and is adaptively optimal for the entire data composition range. Paper establishes baselines for offline RL from visual observations.
problem Challenges in offline reinforcement learning from visual observations with continuous action spaces.
method Simple baselines and benchmarking tasks for offline RL from visual observations.
result Simple modifications to existing online RL algorithms outperform existing offline RL methods.
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.
Bayesian optimization for long-term outcomes using fast and slow experiments.
problem Optimizing long-term system effects with short-term misleading results.
method Combining fast and slow experiments for Bayesian optimization.
result Sequential optimization over large action spaces in a short time.
This study tackles offline RL with perturbed data sources, deriving a lower bound and proposing an optimal algorithm.
problem Understanding offline RL with multiple perturbed data sources.
method Derives an information-theoretic lower bound, proposes HetPEVI algorithm considering sample and source uncertainties.
result HetPEVI is optimal up to a polynomial factor of the horizon length and can solve offline RL tasks.
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.
Combines offline and online learning for identifying the best arm in bandits.
problem Identifying the best arm in stochastic bandits with offline data.
method Lower bound analysis and algorithm development for optimal best-arm identification.
result Developed algorithms matching lower bound on sample complexity for small δ.
MOPO optimizes offline RL by penalizing dynamics uncertainty.
problem Learning policies from offline data with distributional shift.
method Modify model-based RL to avoid distributional shift.
result MOPO outperforms model-free and standard model-based RL.
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.
PASTA optimizes assortment selection using pessimism principle.
problem Optimizing assortment selection with limited data coverage.
method Pessimistic Assortment Optimization (PASTA) based on the principle of pessimism.
result PASTA correctly identifies optimal assortment with minimal data coverage.
ORIL learns a reward function from unlabeled data to improve robot learning.
problem Leveraging unlabeled data for robot learning.
method ORIL learns a reward function from demonstrator and unlabeled trajectories, annotates data, and trains an agent via offline reinforcement learning.
result ORIL consistently outperforms BC agents on various robotic tasks.
This paper investigates the impact of pre-existing offline data on online learning, in the context of dynamic pricing. We study a single-product dynamic pricing problem over a selling horizon of T periods. The demand in each period is determined by the price of the product according to a linear demand model with unkn…
Adobe research tackles strategic recommendations using reinforcement learning.
problem Optimizing user interactions for long-term objectives in various use-cases.
method Reinforcement learning applied to modeling user behavior and decision-making.
result Practical solutions implemented for various use-cases, addressing fundamental challenges.
We introduce a simple method for nearly simultaneous computation of all moments needed for quasi maximum likelihood estimation of parameters in discretely observed stochastic differential equations commonly seen in finance. The method proposed in this papers is not restricted to any particular dynamics of the different…
New ranking algorithms improve online content delivery by learning from click data.
problem Bias in ranking systems due to production system biases.
method Proposed novel extensions of LinUCB and Linear Thompson Sampling algorithms to handle position-based click model.
result Validated the proposed algorithms through offline and online experiments.
Offline RL algorithms protect privacy while learning from sensitive data.
problem Learning sensitive data in financial, legal, and healthcare applications.
method Differential privacy guarantees for offline RL algorithms.
result Provable prevention of privacy risks with strong learning bounds.
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.
Paper tackles covariate shift in offline IL using less proficient behavior data.
problem Mitigating covariate shift in Imitation Learning with limited data coverage.
method Model-based IL from Offline Data (MILO) framework.
result MILO can combat covariate shift even with sub-optimal behavior policy data.