English
Related papers

Related papers: Estimation and Inference in Distributional Reinfor…

200 papers

Using offline observational data for policy evaluation and learning allows decision-makers to evaluate and learn a policy that connects characteristics and interventions. Most existing literature has focused on either discrete treatment…

Artificial Intelligence · Computer Science 2025-01-22 Cheuk Hang Leung , Yiyan Huang , Yijun Li , Qi Wu

Many Imitation and Reinforcement Learning approaches rely on the availability of expert-generated demonstrations for learning policies or value functions from data. Obtaining a reliable distribution of trajectories from motion planners is…

Robotics · Computer Science 2021-07-13 Alexander Lambert , Byron Boots

We study finite-horizon offline reinforcement learning (RL) with function approximation for both policy evaluation and policy optimization. Prior work established that statistically efficient learning is impossible for either of these…

Machine Learning · Computer Science 2025-10-07 Volodymyr Tkachuk , Csaba Szepesvári , Xiaoqi Tan

Distributional reinforcement learning algorithms have attempted to utilize estimated uncertainty for exploration, such as optimism in the face of uncertainty. However, using the estimated variance for optimistic exploration may cause biased…

Machine Learning · Computer Science 2023-12-06 Taehyun Cho , Seungyub Han , Heesoo Lee , Kyungjae Lee , Jungwoo Lee

This paper investigates the computational complexity of reinforcement learning in a novel linear function approximation regime, termed partial $q^{\pi}$-realizability. In this framework, the objective is to learn an $\epsilon$-optimal…

Artificial Intelligence · Computer Science 2025-10-31 Shayan Karimi , Xiaoqi Tan

We study periodic review stochastic inventory control in the data-driven setting where the retailer makes ordering decisions based only on historical demand observations without any knowledge of the probability distribution of the demand.…

Statistics Theory · Mathematics 2021-11-05 Xun Zhang , Zhisheng Ye , William B. Haskell

We propose a new, nonparametric approach to estimating the value function in reinforcement learning. This approach makes use of a recently developed representation of conditional distributions as functions in a reproducing kernel Hilbert…

Machine Learning · Computer Science 2012-10-19 Steffen Grünewälder , Luca Baldassarre , Massimiliano Pontil , Arthur Gretton , Guy Lever

Research in machine learning is making progress in fixing its own reproducibility crisis. Reinforcement learning (RL), in particular, faces its own set of unique challenges. Comparison of point estimates, and plots that show successful…

Machine Learning · Computer Science 2024-02-07 Ted Fujimoto , Joshua Suetterlein , Samrat Chatterjee , Auroop Ganguly

Many decision problems in science, engineering and economics are affected by uncertain parameters whose distribution is only indirectly observable through samples. The goal of data-driven decision-making is to learn a decision from finitely…

Machine Learning · Statistics 2024-11-05 Daniel Kuhn , Peyman Mohajerin Esfahani , Viet Anh Nguyen , Soroosh Shafieezadeh-Abadeh

Risk-sensitive reinforcement learning (RL) is crucial for maintaining reliable performance in high-stakes applications. While traditional RL methods aim to learn a point estimate of the random cumulative cost, distributional RL (DRL) seeks…

Machine Learning · Computer Science 2025-02-03 Minheng Xiao , Xian Yu , Lei Ying

In the field of reinforcement learning there has been recent progress towards safety and high-confidence bounds on policy performance. However, to our knowledge, no practical methods exist for determining high-confidence policy performance…

Artificial Intelligence · Computer Science 2018-06-26 Daniel S. Brown , Scott Niekum

In this paper, we propose a data-adaptive empirical likelihood-based approach for treatment effect estimation and inference, which overcomes the obstacle of the traditional empirical likelihood-based approaches in the high-dimensional…

Methodology · Statistics 2020-12-15 Wei Liang , Ying Yan

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…

Machine Learning · Computer Science 2019-12-12 Ilya Kostrikov , Ofir Nachum , Jonathan Tompson

Covariate shift, a widely used assumption in tackling {\it distributional shift} (when training and test distributions differ), focuses on scenarios where the distribution of the labels conditioned on the feature vector is the same, but the…

Machine Learning · Computer Science 2025-02-24 Deeksha Adil , Jarosław Błasiok

We propose a novel regression adjustment method designed for estimating distributional treatment effect parameters in randomized experiments. Randomized experiments have been extensively used to estimate treatment effects in various…

Econometrics · Economics 2024-07-24 Undral Byambadalai , Tatsushi Oka , Shota Yasui

We consider the classical problem of learning, with arbitrary accuracy, the natural parameters of a $k$-parameter truncated \textit{minimal} exponential family from i.i.d. samples in a computationally and statistically efficient manner. We…

Machine Learning · Computer Science 2023-09-13 Abhin Shah , Devavrat Shah , Gregory W. Wornell

The empirical distribution function assigns mass $1/n$ to each of the $n$ observations in a sample. As these are highly variable, estimation error may be reduced by replacing them with estimated observations that are asymptotically less…

Methodology · Statistics 2026-05-26 Tommaso Lando , Lorenzo Tedesco

Empirical researchers and decision-makers spanning various domains frequently seek profound insights into the long-term impacts of interventions. While the significance of long-term outcomes is undeniable, an overemphasis on them may…

Machine Learning · Computer Science 2024-09-17 Peng Wu , Ziyu Shen , Feng Xie , Zhongyao Wang , Chunchen Liu , Yan Zeng

We revisit the stochastic variance-reduced policy gradient (SVRPG) method proposed by Papini et al. (2018) for reinforcement learning. We provide an improved convergence analysis of SVRPG and show that it can find an $\epsilon$-approximate…

Machine Learning · Computer Science 2019-05-30 Pan Xu , Felicia Gao , Quanquan Gu

We consider offline reinforcement learning (RL) in $H$-horizon Markov decision processes (MDPs) under the linear $q^\pi$-realizability assumption, where the action-value function of every policy is linear with respect to a given…

Machine Learning · Computer Science 2024-05-28 Volodymyr Tkachuk , Gellért Weisz , Csaba Szepesvári