Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

155309464618 · Jun 202019922001200920172026
48 results for online policy evaluation

Paper develops robust policy evaluation for reinforcement learning with outlier and heavy-tailed rewards.

problem Outlier contamination and heavy-tailed rewards in reinforcement learning.
method Develops a fully online robust policy evaluation procedure and efficient statistical inference.
result Establishes the Bahadur-type representation of the estimator and develops an online inference procedure.

Optimistic NPG improves policy optimization in online RL with efficient sample complexity.

problem Limited theoretical understanding of policy optimization, especially in online RL.
method Combines natural policy gradient with optimistic policy evaluation.
result Achieves optimal dimension dependence sample complexity for learning near-optimal policies.

New framework for evaluating ad auctions using stochastic modeling.

problem Challenges in evaluating deterministic ad auctions.
method Repurposed bid landscape model to approximate propensity scores, enabling robust OPE estimators.
result Remarkable alignment with online A/B test results, achieving 92% MDA in CTR prediction.

We introduce Bayesian least-squares policy iteration (BLSPI), an off-policy, model-free, policy iteration algorithm that uses the Bayesian least-squares temporal-difference (BLSTD) learning algorithm to evaluate policies. An online variant of BLSPI has been also proposed, called randomised BLSPI (RBLSPI), that improves…

2019-04-06abs ↗pdf ↗

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.

Unified Bayesian framework for efficient off-policy evaluation and learning in large action spaces.

problem Efficient off-policy evaluation and learning in systems with correlated actions.
method Unified Bayesian framework with structured priors and sDM approach.
result sDM leverages action correlations without compromising computational efficiency.

This paper unifies two types of statistical methods for estimating treatment effects.

problem Isolating online A/B-tests and off-policy evaluation.
method Establishes formal equivalence between online Difference-in-Means and off-policy Inverse Propensity Scoring methods.
result Standard online methods are mathematically equivalent to off-policy methods with optimal control variates.

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.

We consider a context-based dynamic pricing problem of online products, which have low sales. Sales data from Alibaba, a major global online retailer, illustrate the prevalence of low-sale products. For these products, existing single-product dynamic pricing algorithms do not work well due to insufficient data samples.…

2019-02-17abs ↗pdf ↗

The paper introduces SuccessProbaMax to optimize policy success probability in online advertising.

problem Optimizing policy success probability in online advertising systems.
method SuccessProbaMax algorithm that optimizes for the probability of success rather than expected value.
result SuccessProbaMax outperforms conventional algorithms in terms of success rate.

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.

Before A/B testing online a new version of a recommender system, it is usual to perform some offline evaluations on historical data. We focus on evaluation methods that compute an estimator of the potential uplift in revenue that could generate this new technology. It helps to iterate faster and to avoid losing money b…

2018-01-22abs ↗pdf ↗

New complexity measure helps in agnostic reinforcement learning with or without access to MDP dynamics.

problem Understanding the number of rounds needed to learn an ε-suboptimal policy in unknown MDPs.
method Introducing spanning capacity as a new complexity measure and developing POPLER algorithm.
result There is a separation between generative and online access models for agnostic learnability.

Paper proposes a new dynamic pricing method with always-valid online statistical learning.

problem Designing dynamic pricing policies that adapt to online uncertainty and maintain validity.
method Regularized online statistical learning with theoretical guarantees and three major advantages.
result Proposed OORMLP pricing policy secures logarithmic regret in decision horizon.

This work explains why online imitation learning improves faster than theory predicts.

problem Online imitation learning's empirical policy improvement speed exceeds theoretical predictions.
method The authors analyze online imitation learning with a convex, smooth, and non-negative loss function, proving policy improvement in expectation and high probability.
result Adopting a sufficiently expressive policy class in online IL increases both policy improvement speed and performance bias.

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.

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.

Sample efficiency is critical in solving real-world reinforcement learning problems, where agent-environment interactions can be costly. Imitation learning from expert advice has proved to be an effective strategy for reducing the number of interactions required to train a policy. Online imitation learning, which inter…

2018-06-12abs ↗pdf ↗

The paper tackles robust reinforcement learning with performance guarantees.

problem Finding a robust policy for RMDP with state space uncertainties.
method Proposes RLSPI algorithm for learning optimal robust policy with performance bounds.
result Demonstrates the performance of RLSPI on standard benchmark problems.

New methods improve off-policy evaluation for survival outcomes with censoring.

problem Systematic underestimation of policy performance due to censoring bias in survival outcomes.
method Proposes IPCW-IPS and IPCW-DR to handle censoring bias in survival outcomes.
result The proposed methods are unbiased and achieve double robustness.

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.

New method learns decisions from collective preferences without individual covariates.

problem Making decisions online without individual covariates.
method Collaborative filtering, matrix completion bandit, ε-greedy policy, online gradient descent, inverse propensity weighting.
result Method outperforms benchmarks and reveals new discoveries.

Value aggregation is a general framework for solving imitation learning problems. Based on the idea of data aggregation, it generates a policy sequence by iteratively interleaving policy optimization and evaluation in an online learning setting. While the existence of a good policy in the policy sequence can be guarant…

2018-01-22abs ↗pdf ↗

This paper bridges offline and online RL by studying policy finetuning with a reference policy.

problem Sample-efficient reinforcement learning in online and offline settings.
method Design of policy finetuning algorithms and analysis of sample complexity.
result Theoretical analysis shows that the optimal policy finetuning algorithm is either offline reduction or purely online RL.

This paper formalises the problem of online algorithm selection in the context of Reinforcement Learning. The setup is as follows: given an episodic task and a finite number of off-policy RL algorithms, a meta-algorithm has to decide which RL algorithm is in control during the next episode so as to maximize the expecte…

2017-01-30abs ↗pdf ↗

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.

It is well known that the historical logs are used for evaluating and learning policies in interactive systems, e.g. recommendation, search, and online advertising. Since direct online policy learning usually harms user experiences, it is more crucial to apply off-policy learning in real-world applications instead. Tho…

2019-07-23abs ↗pdf ↗

AIPS improves ranking policy evaluation by adapting to diverse user behavior.

problem Inaccurate Off-Policy Evaluation of ranking policies due to high variance under diverse user behavior.
method Developed Adaptive IPS (AIPS) that adapts to different user behaviors and minimizes MSE.
result AIPS achieves minimum variance among unbiased estimators and provides significant empirical accuracy improvement.

This work establishes always-valid risk bounds for online matrix completion.

problem Challenges in establishing always-valid concentration inequalities for online matrix completion.
method Combines non-asymptotic martingale concentration and regularized low-rank matrix regression.
result Establishes always-valid risk bound process for online matrix completion.