New estimator GMIPS reduces variance in ranking policy evaluation.
problem High variance in off-policy evaluation for ranking policies.
method GMIPS estimator with user behavior model on ranking embedding spaces.
result GMIPS achieves lowest MSE and balances bias-variance trade-off.
Simplifies complex RL policies by ranking important decisions.
problem Complexity in RL policies makes them hard to analyze and interpret.
method Statistical fault localisation to rank states and prune unimportant decisions.
result Pruned policies can perform similarly to original policies, improving interpretability.
AdaRL improves robust RL by adaptively adjusting policy complexity.
problem Handling epistemic uncertainty in environment dynamics.
method Bi-level optimization framework with adaptive rank adjustment.
result AdaRL outperforms existing methods on MuJoCo benchmarks.
Optimizes biomolecular simulations by ranking adaptive sampling policies.
problem Efficiently sampling biomolecular systems to capture complex dynamical behaviors.
method Metric-driven ranking of adaptive sampling policies to identify the optimal policy for each round.
result Different adaptive sampling policies lead to faster convergence and improved sampling performance.
A new estimator reduces bias and variance in ranking policy evaluation.
problem Estimating ranking policies using logged data in recommender systems.
method Cascade Doubly Robust estimator based on the cascade assumption.
result The estimator reduces bias and variance compared to existing methods.
Conventional Learning-to-Rank (LTR) methods optimize the utility of the rankings to the users, but they are oblivious to their impact on the ranked items. However, there has been a growing understanding that the latter is important to consider for a wide range of ranking applications (e.g. online marketplaces, job plac…
Paper presents a rank-1 approximation method for natural policy gradients in deep RL.
problem Computing natural gradients requires inverting the Fisher Information Matrix, which is computationally expensive.
method Develops a rank-1 approximation to the inverse Fisher Information Matrix for efficient natural policy optimization.
result The rank-1 approximation converges faster and has similar sample complexity to stochastic policy gradient methods.
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.
New algorithm tackles dynamic query routing to multiple embedding models.
problem Dynamic query routing to multiple embedding models under adversarial conditions.
method Formalized as adversarial contextual linear bandit with low-rank experts, proposed HPG algorithm.
result HPG algorithm achieves linearized policy regret of i l d e O ( s M T ) ilde{\mathcal O}(s\sqrt{M T}) i l d e O ( s M T ) . While implicit feedback (e.g., clicks, dwell times, etc.) is an abundant and attractive source of data for learning to rank, it can produce unfair ranking policies for both exogenous and endogenous reasons. Exogenous reasons typically manifest themselves as biases in the training data, which then get reflected in the l…
Sample inefficiency is a long-lasting problem in reinforcement learning (RL). The state-of-the-art estimates the optimal action values while it usually involves an extensive search over the state-action space and unstable optimization. Towards the sample-efficient RL, we propose ranking policy gradient (RPG), a policy …
Framework for optimizing search engine rankings using observational data.
problem Optimizing ranking policies for search engines using limited observational data.
method Formulated expected reward optimization problem, estimated context value distribution, trained ranking policy via Bayesian inference.
result Demonstrated trade-offs in ranking policies trained on empirical reward estimates.
Under a Bayesian framework, we formulate the fully sequential sampling and selection decision in statistical ranking and selection as a stochastic control problem, and derive the associated Bellman equation. Using value function approximation, we derive an approximately optimal allocation policy. We show that this poli…
Efficient algorithms for low-rank bandits using subspace recovery.
problem Contextual bandits with low-rank reward matrices.
method Spectral methods for subspace recovery, reformulating as linear bandits.
result Nearly optimal policy evaluation and best policy identification, minimax guarantees for regret minimization.
Novel algorithm for Markov decision processes using rank-one approximation.
problem Solving planning and learning problems of Markov decision processes.
method Policy iteration with rank-one approximation of transition probability matrix.
result The proposed algorithm consistently outperforms first-order algorithms and their accelerated versions.
Meta-AAD uses deep reinforcement learning to improve anomaly detection by selecting the most informative instances.
problem High false-positive rate in anomaly detection, especially in high-stake applications.
method Meta-AAD leverages deep reinforcement learning to train a meta-policy for query selection, optimizing the number of discovered anomalies.
result Meta-AAD significantly outperforms state-of-the-art re-ranking strategies and unsupervised baselines on 24 benchmark datasets.
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.
Study multi-task learning with low-rank representation in stochastic linear bandits.
problem Transfer learning across multiple linear bandit tasks with shared low-dimensional representation.
method Proposes a greedy policy with trace norm regularization to implicitly learn a low-rank representation without knowing the rank.
result Upper bound on multi-task regret of N d T ( T + d ) r \sqrt{NdT(T+d)r} N d T ( T + d ) r , showing benefit over independent task solving. Framework ranks sectors influenced by Indian Union Budgets.
problem Real-time analysis of budgetary impacts on sector-specific equity performance.
method Fine-tuned embeddings and language models for sector identification and performance ranking.
result 0.997 NDCG score in predicting sector ranks based on post-budget performances.
The paper sorts big data by revealed preferences, improving consumer and policy decisions.
problem Sorting diverse consumer preferences for big data objects like colleges.
method Endogenous weighting of revealed preferences, considering spillover effects.
result Consistent steady-state solution to counterbalance equilibrium.
Proposes a new method to optimize treatment allocation with budget constraints.
problem Optimizing treatment allocation with budget constraints in marketing.
method Learning to rank for profit maximization.
result Learning to rank can maximize the area under a policy's incremental profit curve.
Optimizes COVID-19 testing policy using a Multi-Armed Bandit approach.
problem Balancing discovery of positive cases with population surveillance.
method Risk scoring and random sampling based on Multi-Armed Bandit theory.
result Effective prioritization captures 65-92% of positive cases with varying testing capacity.
Motivated by recommendation problems in music streaming platforms, we propose a nonstationary stochastic bandit model in which the expected reward of an arm depends on the number of rounds that have passed since the arm was last pulled. After proving that finding an optimal policy is NP-hard even when all model paramet…
A fair policy for hiring candidates from different groups is proposed in a linear contextual bandit problem.
problem Selecting candidates from different sensitive groups in a fair manner.
method A greedy policy that constructs a ridge regression estimate and computes relative rank using empirical cumulative distribution function.
result The greedy policy achieves fair pseudo-regret of order d T \sqrt{dT} d T after T T T rounds, satisfying demographic parity. Reduces variance in noisy social outcomes to improve policy evaluation and optimization.
problem Improving access to opportunity through personalized treatment decisions.
method Data-driven dimensionality-reduction using reduced rank regression to denoise multiple outcomes.
result Improves estimation error in policy evaluation and optimization, including on real-world data.
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 risk-aware RL approach using RDEU and Wasserstein ball for robust performance.
problem Optimizing risk-aware performance criteria in uncertain environments.
method Rank dependent expected utility (RDEU) for risk assessment, Wasserstein ball for robustness, actor/agent framework.
result Explicit policy gradient formulae for robust optimization.
Rank aggregation based on pairwise comparisons over a set of items has a wide range of applications. Although considerable research has been devoted to the development of rank aggregation algorithms, one basic question is how to efficiently collect a large amount of high-quality pairwise comparisons for the ranking pur…
New framework learns policies for partially observable systems.
problem Learning policies in partially observable dynamical systems.
method Partially Observable Bilinear Actor-Critic framework.
result Algorithm can learn against optimal policies in certain cases.
New algorithm for fair ranking in contextual bandits with concave rewards.
problem Fair ranking in recommendation systems.
method Geometric interpretation of CBCR as optimization, Frank-Wolfe analyses.
result First algorithm with provably vanishing regret for CBCR.
Ranking metrics are a family of metrics largely used to evaluate recommender systems. However they typically suffer from the fact the reward is affected by the order in which recommended items are displayed to the user. A classical way to overcome this position bias is to uniformly shuffle a proportion of the recommend…
This paper studies the evaluation of policies that recommend an ordered set of items (e.g., a ranking) based on some context---a common scenario in web search, ads, and recommendation. We build on techniques from combinatorial bandits to introduce a new practical estimator that uses logged data to estimate a policy's p…
Many web systems rank and present a list of items to users, from recommender systems to search and advertising. An important problem in practice is to evaluate new ranking policies offline and optimize them before they are deployed. We address this problem by proposing evaluation algorithms for estimating the expected …
Scalable model for slate recommendation learns reward probabilities.
problem Scalable personalized slate recommendation in large action spaces.
method Probabilistic Rank and Reward (PRR) model combining reward, interaction, and rank.
result PRR outperforms existing methods and is scalable to large action spaces.
A new method reduces variance in training early-stage rankers for large-scale search systems.
problem Training early-stage rankers for large-scale search systems is challenging due to exploding variance in policy gradient methods.
method Proposes credit-assigned policy gradient (CA-PG) to mitigate variance in training early-stage rankers.
result CA-PG significantly reduces variance in training early-stage rankers compared to vanilla policy gradient.
ADPO optimizes relative advantage in reinforcement learning from human feedback.
problem Optimizing policy alignment in reinforcement learning from human preferences.
method ADPO explicitly parameterizes the optimal structure through anchored logits, decoupling response quality from prior popularity.
result Empirically, ADPO achieves state-of-the-art performance on reasoning tasks, outperforming GRPO by 30.9 percent.
Study evaluates new models using human feedback from another model.
problem Evaluate a new model using human feedback collected for another model.
method Formalize problem, propose model-based and model-free estimators, analyze unbiasedness, and empirically evaluate.
result Proposed estimators can predict absolute values, rank, and optimize evaluated policies.
LoCo-RLHF models diverse human feedback with contextual information.
problem Heterogeneous human feedback from diverse contexts and preferences.
method Low-rank contextual preference model, PRS policy.
result LoCo-RLHF achieves tighter sub-optimality gap than existing methods.
Algorithm POLO learns low-rank MDPs with adversarial changes in full-info feedback.
problem Learning low-rank MDPs with adversarial changes and unknown transition probabilities.
method Policy optimization-based algorithm POLO with regret guarantee.
result POLO achieves sublinear regret guarantee with no dependence on state space size.
Paper improves sample complexity for reward-free RL in low-rank MDPs.
problem Reward-free RL in low-rank MDPs with unknown representation and weights.
method Proposes a novel model-based algorithm RAFFLE with improved sample complexity.
result RAFFLE achieves ε ε ε -optimal policy and accurate system identification with significantly fewer samples. A new method predicts stock ranking uncertainty to improve trading performance during regime shifts.
problem Ranking models fail during regime shifts, leading to suboptimal performance.
method Adapting DEUP to rankers, predicting rank displacement and uncertainty, and proposing a two-level deployment policy.
result The two-level deployment policy improves risk-adjusted performance and indicates DEUP adds value mainly as a tail-risk guard.
Algorithm finds ε-equilibrium policies for multi-agent Markov games with hidden low-rank structure.
problem Designing efficient algorithms for multi-agent Markov games with unknown representation and hidden low-rank structure.
method Model-based and model-free approaches using representation learning to construct an effective representation from data.
result Achieves poly ( H , d , A , 1 / ε ) (H,d,A,1/\varepsilon) ( H , d , A , 1/ ε ) sample complexity for both model-based and model-free approaches. The paper improves PCS approximation for ranking and selection under limited simulation budgets.
problem Improving finite sample performance in Ranking and Selection.
method Develops a Bahadur-Rao type expansion for PCS, proposes a novel FCBA policy.
result FCBA policy achieves superior PCS performance compared to traditional methods.
Proposes a new sampling policy for ranking and selection problems.
problem Improving ranking and selection in adaptive sampling policies.
method Annealed entropic allocation, using soft-min weights and saddlepoint corrections.
result Consistently competitive performance in various settings.
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 …
Opioid overdose rates have reached an epidemic level and state-level policy innovations have followed suit in an effort to prevent overdose deaths. State-level drug law is a set of policies that may reinforce or undermine each other, and analysts have a limited set of tools for handling the policy collinearity using st…
The study categorizes reward errors in reinforcement learning, finding some can be beneficial.
problem Training language models with imperfect proxy rewards.
method Theoretical analysis of policy gradient optimization and categorization of reward errors.
result Reward errors can be benign or even beneficial, preventing policy from stalling.
This work shows how to use simulators to learn efficient exploration in real-world RL.
problem Sample complexity of real-world reinforcement learning.
method Coupling exploratory policies learned in simulators with practical approaches.
result Polynomial sample complexity in real world, exponential improvement over direct sim2real transfer.