New offline RL method handles average-reward MDPs with single-policy coverage.
problem Challenges in offline reinforcement learning due to distribution shift and non-uniform coverage.
method Develops an algorithm based on pessimistic discounted value iteration with quantile clipping.
result First fully single-policy sample complexity bound for average-reward offline RL.
Paper tackles offline RL with weak assumptions on both function classes and data coverage.
problem Achieve sample-efficient offline RL with weak assumptions on both factors.
method Simple algorithm based on primal-dual formulation of MDPs, with density-ratio function modeling dual variables.
result Polynomial sample complexity achieved under realizability and single-policy concentrability.
Paper studies offline RL with linear approx, focusing on inherent Bellman error.
problem Offline RL with linear approx, focusing on inherent Bellman error.
method Algorithm that succeeds under single-policy coverage condition, leveraging inherent Bellman error.
result Algorithm yields first known guarantee under single-policy coverage, even for linear Bellman completeness.
New methods tackle robust reinforcement learning in sparse, corrupted data.
problem Tackles robust reinforcement learning in sparse, corrupted data.
method Proposes actor-critic methods with sparse robust estimator oracles.
result First non-vacuous guarantees in high-dimensional sparse MDPs with single-policy concentrability coverage.
The paper explores learning good policies from past data in large state spaces.
problem Learning good policies from historical data in large state spaces.
method Introduces expressivity assumptions and data coverage for function approximation and algorithmic design.
result A variety of algorithms and their guarantees are presented based on assumptions and desired complexity.
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 analyzes sample complexity for offline f f f -divergence-regularized contextual bandits.
problem Lack of tight analyses for sample complexity in offline reinforcement learning.
method Novel pessimism-based analysis for reverse KL divergence, establishing i l d e O ( ε − 1 ) ilde{O}(ε^{-1}) i l d e O ( ε − 1 ) sample complexity. result Achieves i l d e O ( ε − 1 ) ilde{O}(ε^{-1}) i l d e O ( ε − 1 ) sample complexity for reverse KL divergence, surpassing existing bounds. New algorithms estimate Q-functions under partial coverage and realizability, improving offline RL guarantees.
problem Offline RL with limited exploration and assumptions about data coverage and Q-function realizability.
method Proposes minimax learning algorithms to estimate soft or vanilla Q-functions with L 2 L^2 L 2 -convergence guarantees. result PAC guarantees for offline RL under partial coverage and realizability conditions.
New offline RL algorithm with optimal sample complexity using LP and error bounds.
problem Finding optimal policies from offline data with limited coverage and function approximation.
method Developed a new LP reformulation with error bounds and constraints for offline RL.
result Achieved optimal O ( 1 / n ) O(1/\sqrt{n}) O ( 1/ n ) sample complexity under various assumptions. 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 single policy suffices for near-optimal parallel exploration in RL.
problem Quantitative effects of parallel exploration in reward-free RL.
method Using a single policy to guide exploration across all agents.
result Near-linear speedup and near-minimax optimality for linear MDPs.
Pessimistic Q-learning improves sample efficiency in offline reinforcement learning.
problem Insufficient coverage and sample scarcity in offline reinforcement learning datasets.
method Pessimistic Q-learning algorithm for offline reinforcement learning, focusing on variance reduction.
result Near-optimal sample complexity achieved with the proposed algorithm.
New algorithm fills gaps in offline data for hybrid RL, achieving similar gains without coverage assumptions.
problem Lack of provable benefits in hybrid RL with coverage assumptions.
method Warm-starting optimistic online algorithms with offline data in experience replay buffer.
result Hybrid RL gains similar to offline-only RL without coverage assumptions, demonstrating efficient exploration.
Designs a single policy for collecting data to train near-optimal policies.
problem Engineering overhead in deploying minimax procedures for stochastic linear contextual bandits.
method Designs a single stochastic policy to collect data from which a near-optimal policy can be extracted.
result The designed policy can collect data from which a near-optimal policy can be extracted.
This paper explains why distributional reinforcement learning is better than vanilla RL using small-loss bounds.
problem Understanding when and why distributional reinforcement learning (DistRL) is superior to vanilla reinforcement learning (RL).
method The paper uses small-loss bounds to explain the benefits of DistRL, proposing algorithms and proving bounds for different RL settings.
result Distributional reinforcement learning (DistRL) outperforms vanilla RL when optimal costs are small, as shown by small-loss bounds.
Paper tackles offline preference-based RL with human feedback.
problem Offline Preference-based Reinforcement Learning with preference feedback.
method Two-step approach: MLE for reward estimation and distributionally robust planning.
result First guarantee for learning any target policy with polynomial samples.
This paper is concerned with offline reinforcement learning (RL), which learns using pre-collected data without further exploration. Effective offline RL would be able to accommodate distribution shift and limited data coverage. However, prior algorithms or analyses either suffer from suboptimal sample complexities or …
New algorithm reduces offline RL sample complexity for MDPs.
problem Learning optimal policies from offline data in unknown MDPs.
method Adaptive Pessimistic Value Iteration (APVI) algorithm.
result Suboptimality bound nearly matches theoretical limits.
PS framework selects best policy from library for CSO problems.
problem Policy selection in CSO with heterogeneous performance across covariate space.
method PS framework constructs library of candidate policies and learns a meta-policy to select the best one.
result PS consistently outperforms best single policy in heterogeneous CSO problems.
FedLCB-Q learns optimal policies from federated offline data with linear speedup.
problem Learning optimal policies from offline data with federated learning.
method Federated offline RL algorithm tailored for Q-learning, using local Q-function updates and central aggregation.
result Achieves linear speedup in sample complexity with collaboration among agents.
Paper tackles RLHF with DCPPO method, proving near-optimal suboptimality.
problem Challenges in offline RLHF with limited human feedback and bounded rationality.
method DCPPO method involving three stages: MLE, reward function recovery, and pessimistic value iteration.
result DCPPO's suboptimality almost matches classical pessimistic offline RL in terms of distribution shift and dimension.
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. New method uses label-weighted conformal prediction for macro-coverage guarantees in classification.
problem Finding a balance between class-conditional and marginal coverage in long-tailed datasets.
method Label-weighted conformal prediction for macro-coverage guarantees.
result Validated prediction sets with macro-coverage guarantees on large-scale image datasets.
Hybrid RL algorithms improve offline and online RL in linear MDPs.
problem Improving RL performance without single-policy concentrability.
method Developed computationally efficient algorithms for PAC and regret-minimizing RL in linear MDPs.
result Achieved sharper error or regret bounds for linear MDPs.
A new method solves bilevel optimization problems in competitive Markov games.
problem Capturing competitive structures in RL with multiple interacting policies.
method Penalty-augmented Nikaido-Isoda descent-ascent (PANDA) method.
result PANDA converges to stationary points without convexity assumptions.
Algorithm balances learning and coverage for multi-robots over unknown fields.
problem Balancing learning and coverage for multi-robots over unknown, nonuniform sensory fields.
method DSLC algorithm that schedules learning and coverage epochs, using Gaussian Process modeling and coverage regret analysis.
result Upper bound on expected cumulative coverage regret provided for DSLC.
Improved conformal prediction for better conditional coverage of classifier predictions.
problem Achieving exact conditional coverage in finite samples for prediction sets.
method Developed a variant of conformal prediction targeting coverage conditional on confidence and trust score.
result Empirically improved conditional coverage properties compared to standard conformal prediction.
A method for a single policy to solve various tasks across diverse agent morphologies.
problem Generalizing a single policy to solve various tasks across diverse agent morphologies.
method Unified representation and behavior distillation using a morphology-task graph and Transformer architecture.
result Improves multi-task performances compared to baselines, suggesting a promising approach.
Adaptive coverage policies improve conformal prediction accuracy.
problem Fixed coverage levels in traditional conformal prediction lead to uninformative predictions.
method Optimizes adaptive coverage policy using a neural network trained on leave-one-out calibration.
result Adaptive coverage policies produce more informative and flexible prediction sets.
New metrics improve understanding of predictive system reliability.
problem Evaluating conditional coverage of predictive systems.
method Casting conditional coverage estimation as a classification problem, using excess risk of the target coverage (ERT) metrics.
result Modern classifiers provide higher statistical power for estimating conditional coverage.
Kandinsky conformal prediction expands conditional coverage guarantees.
problem Disparities in coverage guarantees across different subpopulations.
method Flexible handling of overlapping and fractional group memberships.
result Minimax-optimal high-probability conditional coverage bound.
ST-BCP narrows the coverage gap in BCP by transforming nonconformity scores.
problem The looseness in BCP's coverage guarantee due to Markov's inequality.
method Introduces a data-dependent transformation of nonconformity scores.
result Reduces the average coverage gap from 4.20% to 1.12% on benchmarks.
Improves conditional coverage of regression models using conformal prediction.
problem Lack of conditional coverage guarantees in conformal prediction methods.
method Proposes a novel algorithm to train a regression function to improve conditional coverage after split conformal prediction.
result Establishes an upper bound for miscoverage gap and proposes an end-to-end algorithm to control it.
This study uses AI to analyze financial market coverage from YouTube videos.
problem Challenges in analyzing a large number of financial market videos.
method Used Whisper model to generate text from videos, applied natural language processing.
result Highlights dynamics of financial market coverage and identifies trending topics.
Conformal methods create prediction bands that control average coverage under no assumptions besides i.i.d. data. Besides average coverage, one might also desire to control conditional coverage, that is, coverage for every new testing point. However, without strong assumptions, conditional coverage is unachievable. Giv…
TQA improves prediction intervals for time series data by adjusting quantiles for both cross-sectional and longitudinal coverage.
problem Constructing reliable prediction intervals for cross-sectional time series data.
method Temporal Quantile Adjustment (TQA) method that adjusts the quantile in Conformal Prediction to account for both cross-sectional and longitudinal coverage.
result TQA improves longitudinal coverage while preserving cross-sectional coverage, as validated through extensive experimentation.
New conformal prediction methods for long-tailed classification problems.
problem Rare classes are systematically omitted in existing conformal prediction methods.
method Introduced a new conformal score function and a new interpolation procedure.
result Smoothly trade off set size and class-conditional coverage.
New coverage conditions improve sample efficiency in online reinforcement learning.
problem Improving sample efficiency in online reinforcement learning with function approximation.
method Identifying and studying new coverage conditions for online reinforcement learning.
result Improved regret bounds achieved with new coverage conditions.
We introduce the concept of coverage risk as an error measure for density ridge estimation. The coverage risk generalizes the mean integrated square error to set estimation. We propose two risk estimators for the coverage risk and we show that we can select tuning parameters by minimizing the estimated risk. We study t…
Study robustness of split conformal prediction under adversarial attacks.
problem Ensuring distribution-free coverage guarantees in CP under adversarial conditions.
method Theoretical analysis and extensive experiments on split conformal prediction robustness.
result Prediction coverage varies with calibration-time attack strength, enabling control over coverage under adversarial tests.
New method improves conditional coverage of conformal prediction.
problem Improving conditional coverage in conformal prediction.
method Trainable transformation of conformity scores to improve conditional coverage.
result Highly adaptive to local data structure, outperforming existing methods.
Audited Conformal Prediction improves conditional coverage in pretrained models under distribution shift.
problem Uncertainty quantification for pretrained models under unknown distribution shift
method Leverages a small labeled dataset to train an audit model for marginal coverage, integrates outputs into conformal prediction framework
result Significantly higher conditional coverage than existing approaches
Pre-training improves model coverage, crucial for downstream performance.
problem Understanding why pre-training enhances model performance.
method Coverage principle, focusing on next-token prediction and model quality.
result Coverage generalizes faster than cross-entropy, improving downstream performance.
Adapts conformal prediction for missing data, ensuring valid coverage.
problem Uncertainty quantification with missing covariates.
method Proposes a reweighted conformal prediction procedure for handling missing values.
result Guaranteed Marginal Coverage and Mask-Conditional Validity for general missing data mechanisms.
Unified coverage analysis for linear off-policy evaluation in reinforcement learning.
problem Lack of a unified understanding of coverage parameters in linear off-policy evaluation.
method Developed a novel finite-sample analysis for LSTDQ algorithm, introducing feature-dynamics coverage.
result Unified understanding of coverage parameters in linear off-policy evaluation.
Study optimal policies under budget and coverage constraints.
problem Optimal policy learning with budget and coverage constraints.
method Combination of knapsack structure, affine threshold rule, linear programming relaxation, Greedy-Lagrangian (GLC), and rank-and-cut (RC) algorithms.
result GLC closely approximates the optimal solution and achieves near-optimal performance in finite samples; RC is approximately optimal under certain conditions.
Quantile regression undercovers true uncertainty, revealing a bias in high dimensions.
problem Under-coverage bias in uncertainty estimation by quantile regression.
method Theoretical study on coverage of uncertainty estimation algorithms in learning quantiles.
result Quantile regression undercovers true uncertainty, revealing a bias in high dimensions.
The paper addresses the reliability of conformal prediction under covariate shift.
problem Ensuring reliable prediction sets under covariate shift.
method Derives upper bounds on training-conditional coverage.
result Offers PAC guarantees for conformal prediction methods.