ScoreMatchingRiesz improves debiased machine learning and policy effects estimation.
problem Improving debiased machine learning and policy effects estimation.
method Score matching and Riesz representer estimation.
result Estimates policy path for continuous treatments, improving interpretability.
SDM Policy accelerates inference for robotic tasks while maintaining high action quality.
problem Prolonged inference times in diffusion-based policies for high-frequency control tasks.
method Two-stage optimization: score matching and distribution matching; dual-teacher mechanism.
result 6x inference speedup with state-of-the-art action quality.
QAM uses adjoint matching to optimize continuous-action RL policies efficiently.
problem Efficient optimization of expressive diffusion or flow-matching policies with respect to a Q-function.
method QAM leverages adjoint matching to bypass the numerical instability of backpropagation through multi-step denoising processes.
result QAM consistently outperforms prior approaches on hard, sparse reward tasks in offline and offline-to-online RL.
New methods use vector search and nearest-neighbor matching for policy learning in causal inference.
problem Learning optimal policies in causal inference with limited data.
method RAG-based policy learning with vector search and nearest-neighbor matching.
result The methods bound the within-candidate choice regret and evaluate the one-step method directly as a policy.
Bayesian design improves by reducing policy training cost.
problem Double intractability in expected information gain limits policy learning.
method Score matching to isolate EIG, then train policy singly intractably.
result Reduced computational burden for policy training, allowing multiple iterations.
Q-MMR evaluates policies using reweighted rewards and moment matching.
problem Off-policy evaluation in finite-horizon MDPs.
method Q-MMR learns scalar weights for data points via a moment matching objective against a value-function discriminator class.
result Data-dependent finite-sample guarantee with a dimension-free error bound.
Proposes a new method to estimate continuous treatment policies and match treatments effectively.
problem Current methods struggle with continuous treatment policies and complex matching.
method Formulates treatment effectiveness as a parametrizable model, using deep learning for optimization.
result Significant improvement in treatment effectiveness and matching efficiency.
The study enhances financial rule matching using NLP without datasets.
problem Performing semantic matching between financial rules and policies.
method Outperforming pre-trained models with NLP techniques using free resources.
result Improved semantic matching between financial rules and policies.
A new framework for offline RL improves policy flexibility and regularity.
problem Lack of environmental interactions in offline RL leads to poor policy performance.
method Proposes a behavior-regularized implicit policy framework with modified policy-matching methods.
result The framework improves policy effectiveness and robustness beyond static datasets.
Optimistic actor-critic tackles linear MDPs with parametric policies.
problem Theoretical limitations of existing actor-critic methods for linear MDPs.
method Proposes an optimistic actor-critic framework with parametric log-linear policies and approximate Thompson sampling.
result Achieves state-of-the-art sample complexity in both on-policy and off-policy settings.
Study shows refugee matching gains are robust to different evaluation methods.
problem Stability of refugee matching gains under various evaluation methods.
method Used multiple off-policy evaluation methods including IPW and AIPW.
result Impact estimates remain consistent in magnitude and statistically significant.
Reinforcement learning improves online matching by combining expert policies.
problem Efficient decision-making in complex systems like cloud services and marketplaces.
method Combines reinforcement learning with expert policies, using advantage-based weight updates.
result The orchestrated policy converges faster and yields higher efficiency than individual experts and conventional RL.
Improved exploration in cooperative multi-agent reinforcement learning.
problem Limited expressiveness of Gaussian policies in DecSPG hinders effective exploration.
method Proposes decentralized diffusion policy learning (DDPL) with denoising diffusion probabilistic models.
result Consistently improved performance on various MARL benchmarks.
PAMA learns covariate importance for better matching in observational studies.
problem Poor performance of conventional matching methods when covariates differ in relevance.
method PAMA is a semi-supervised framework that learns covariate importance from paired data and optimizes a weighted quadratic score.
result PAMA outperforms standard methods, particularly in high-dimensional settings and under model misspecification.
GDT improves reinforcement learning by matching future state information efficiently.
problem Efficient learning of multi-task policies from trajectory data.
method Generalized Decision Transformer (GDT) for offline hindsight information matching.
result GDT enables effective offline multi-task state-marginal matching and imitation learning.
Data-driven decision-making often overestimates benefits due to the winner's curse.
problem Accurate policy evaluation in data-driven decision-making.
method Model-based policy evaluation using estimated models from data.
result Model-based methods can produce large, spurious reported benefits even when true effects are zero.
Model-based reinforcement learning approaches carry the promise of being data efficient. However, due to challenges in learning dynamics models that sufficiently match the real-world dynamics, they struggle to achieve the same asymptotic performance as model-free methods. We propose Model-Based Meta-Policy-Optimization…
Transforming sparse outcomes into dense process rewards for efficient reinforcement learning.
problem Training RL policies to maximize sparse outcomes.
method Incentivizing policy matching state-action visitations of successful episodes.
result Significantly faster RL finetuning performance.
Unified framework for imitation learning via moment matching.
problem Closing the gap between imitation and real-world performance.
method Classifying imitation learning algorithms based on reward or action-value moment matching, considering adversarial divergences.
result Derivation of bounds on policy performance for all algorithms in each class, and introduction of moment recoverability.
New RL algorithm optimizes policies with bandit feedback, matching previous bounds.
problem Optimizing policies with unknown transitions and bandit feedback.
method Optimistic Trust Region Policy Optimization (TRPO) algorithm.
result Sub-linear regret bounds for both stochastic and adversarial rewards.
Many problems at the intersection of combinatorics and computer science require solving for a permutation that optimally matches, ranks, or sorts some data. These problems usually have a task-specific, often non-differentiable objective function that data-driven algorithms can use as a learning signal. In this paper, w…
ICIL learns policies invariant to multiple environments, improving generalization.
problem Learning policies from multiple environments leads to spurious correlations.
method ICIL learns invariant feature representations and a matching imitation policy.
result ICIL policies generalize better to unseen environments.
Inspired by the seminal work on Stein Variational Inference and Stein Variational Policy Gradient, we derived a method to generate samples from the posterior variational parameter distribution by \textit{explicitly} minimizing the KL divergence to match the target distribution in an amortize fashion. Consequently, we a…
Proposes a new RL method to fine-tune flow-based models with arbitrary rewards.
problem Challenges in fine-tuning continuous flow-based generative models with arbitrary reward functions.
method Online Reward-Weighted Conditional Flow Matching with Wasserstein-2 Regularization (ORW-CFM-W2)
result Achieves optimal policy convergence with controllable trade-offs between reward maximization and diversity preservation.
Rate change calculations in the literature involve deterministic methods that measure the change in premium for a given policy. The definition of rate change as a statistical parameter is proposed to address the stochastic nature of the premium charged for a policy. It promotes the idea that rate change is a property o…
EBIL simplifies IL by estimating expert energy as reward, achieving effective performance.
problem Recovering optimal policy from expert demonstrations without reward signals.
method EBIL uses a two-stage solution: first estimating expert energy as reward, then learning policy.
result EBIL achieves effective performance and interpretable reward signals.
FlowHFT learns adaptive trading strategies from multiple models for diverse market conditions.
problem Traditional HFT models are limited by specific market conditions and cannot adapt to dynamic markets.
method FlowHFT uses flow matching policy to learn from multiple expert models and adapt to various market scenarios.
result FlowHFT consistently outperforms individual expert models in multiple market conditions.
Improving sample efficiency has been a longstanding goal in reinforcement learning. This paper proposes V R M P O \mathtt{VRMPO} VRMPO algorithm: a sample efficient policy gradient method with stochastic mirror descent. In V R M P O \mathtt{VRMPO} VRMPO , a novel variance-reduced policy gradient estimator is presented to improve sample efficiency.…
STORM-PG uses momentum for faster policy gradient updates.
problem Improving policy gradient methods for reinforcement learning.
method Introduces STORM-PG, a SARAH-based algorithm with exponential moving average.
result Achieves O ( 1 / ε 3 ) O(1/ε^3) O ( 1/ ε 3 ) sample complexity, matching best-known rate. Enhances GFlowNets with distributional approach for risk-sensitive policies.
problem Limited applicability of current GFlowNet framework in handling stochastic reward functions.
method Adopting a distributional paradigm, parameterizing each edge flow through quantile functions, and introducing a risk-sensitive learning algorithm.
result Significant improvement on benchmarks due to enhanced training algorithm, even in deterministic reward settings.
Study shows sample complexity for learning optimal policies in SSP with generative model.
problem Learning optimal policies in Stochastic Shortest Path problems.
method Derive and prove lower and upper bounds on sample complexity.
result Lower bound of Ω ( S A B ⋆ 3 / ( c min ε 2 ) ) Ω(SAB_{\star}^3/(c_{\min}ε^2)) Ω ( S A B ⋆ 3 / ( c m i n ε 2 )) samples for general case, and up to logarithmic factors for bounded hitting time condition. Second-order estimator improves continuous-time policy evaluation.
problem Estimating value surfaces from discrete data with time-inhomogeneous dynamics.
method Moment-matching coefficients for high-order generator regression.
result Second-order estimator consistently outperforms Bellman baseline.
Exploration is critical to a reinforcement learning agent's performance in its given environment. Prior exploration methods are often based on using heuristic auxiliary predictions to guide policy behavior, lacking a mathematically-grounded objective with clear properties. In contrast, we recast exploration as a proble…
A new method for learning policies from demonstrations without reinforcement.
problem Learning policies from demonstrations without access to reinforcement signals.
method Energy-based distribution matching (EDM) to learn policy parameters and state marginals.
result EDM yields consistent performance gains over existing algorithms for strictly batch imitation learning.
When performing imitation learning from expert demonstrations, distribution matching is a popular approach, in which one alternates between estimating distribution ratios and then using these ratios as rewards in a standard reinforcement learning (RL) algorithm. Traditionally, estimation of the distribution ratio requi…
Optimal vehicle repositioning policy found for shared mobility services.
problem Matching fixed supply with spatial customer demand under uncertain and correlated demand.
method Base-stock repositioning policy, asymptotic optimality, regret analysis, adaptive repositioning algorithm.
result Surrogate Optimization and Adaptive Repositioning algorithm achieves optimal regret of O ( n 2.5 T ) O(n^{2.5} \sqrt{T}) O ( n 2.5 T ) . We study the problem of estimating the expected reward of the optimal policy in the stochastic disjoint linear bandit setting. We prove that for certain settings it is possible to obtain an accurate estimate of the optimal policy value even with a number of samples that is sublinear in the number that would be required…
New technique reduces imitation learning performance gap in finite samples.
problem Imitation learning performance gap in finite samples.
method Replay estimation to reduce empirical variance in finite samples.
result Achieves optimal performance gap of $\widetilde{O} \left( \min({H^{3/2}} / {N}, {H} / {\sqrt{N}}
ight)$ .
The paper addresses statistical inference in matching markets with dependent missingness.
problem Statistical inference for two-sided matching markets with matching-induced dependence.
method Non-convex algorithm based on Grassmannian gradient descent, debiasing and projection framework.
result Near-optimal entrywise convergence rates for various matching mechanisms.
New algorithm for sequential off-policy learning improves performance over batch methods.
problem Training policies from logged interaction data in a sequential setting.
method Combines Logarithmic Smoothing with online PAC-Bayesian tools.
result Improves performance and accelerates convergence in sequential off-policy learning.
New method learns robot skills from data, matching or outperforming existing methods.
problem Learning robot skills from fixed datasets.
method Offline Reinforcement Learning via Supervised Learning using implicit models.
result Implicit models can match or outperform explicit models in acquiring robotic skills.
New algorithm reduces worst-case regret for heavy-tailed bandits.
problem Stochastic Multi-Armed Bandit problem with heavy-tailed rewards.
method Modified minimax policy MOSS with saturated empirical mean.
result Worst-case regret matching lower bound for heavy-tailed distributions.
Paper proposes FPG algorithm for unbiased off-policy PG estimation.
problem Challenges in off-policy policy gradient estimation.
method Double Fitted PG estimation (FPG) algorithm for arbitrary policy parameterization.
result Empirically, FPG significantly outperforms existing methods.
The paper analyzes the sample complexities for policy evaluation with linear function approximation.
problem Policy evaluation with linear function approximation in discounted infinite horizon Markov decision processes.
method Investigates sample complexities for two policy evaluation algorithms: TD and TDC.
result Establishes high-probability sample complexity bounds for policy evaluation algorithms.
This work extends ME-RL using diffusion models to sample optimal policies.
problem Sampling from the optimal policy trajectory distribution in ME-RL.
method Introducing Diffusion-Augmented Markov Decision Processes (DA-MDPs) to minimize reverse KL divergence.
result DA-MDPs enable seamless integration into various ME-RL methods and outperform baselines.
GPE algorithm optimizes nonparametric contextual bandits with efficient regret bounds.
problem Optimizing nonparametric contextual bandits with efficient regret bounds.
method Inspired by Policy Elimination, GPE uses oracle-efficient techniques for nonparametric classes with infinite VC-dimension.
result GPE is regret-optimal for policy classes with integrable entropy, and for larger entropy, it provides an ε \varepsilon ε -greedy algorithm with matching regret bounds. Multiagent reinforcement learning algorithms (MARL) have been demonstrated on complex tasks that require the coordination of a team of multiple agents to complete. Existing works have focused on sharing information between agents via centralized critics to stabilize learning or through communication to increase perform…
New algorithm optimally evaluates policies with linear approximations.
problem Policy evaluation with linear function approximation.
method Accelerated, variance-reduced fast temporal difference algorithm (VRFTD).
result VRFTD matches both deterministic and stochastic lower bounds.