English
Related papers

Related papers: Estimating Q(s,s') with Deep Deterministic Dynamic…

200 papers

Policy gradient algorithms have proven to be successful in diverse decision making and control tasks. However, these methods suffer from high sample complexity and instability issues. In this paper, we address these challenges by providing…

Machine Learning · Computer Science 2021-03-17 Yannis Flet-Berliac , Reda Ouhamma , Odalric-Ambrym Maillard , Philippe Preux

In reinforcement learning, Return, which is the weighted accumulated future rewards, and Value, which is the expected return, serve as the objective that guides the learning of the policy. In classic RL, return is defined as the…

Machine Learning · Computer Science 2020-10-27 Yufei Wang , Qiwei Ye , Tie-Yan Liu

This paper aims at presenting a new application of information geometry to reinforcement learning focusing on dynamic treatment resumes. In a standard framework of reinforcement learning, a Q-function is defined as the conditional…

Methodology · Statistics 2022-11-17 Shinto Eguchi

Q-learning is a reliable but inefficient off-policy temporal-difference method, backing up reward only one step at a time. Replacing traces, using a recency heuristic, are more efficient but less reliable. In this work, we introduce…

Machine Learning · Computer Science 2015-03-19 Mitchell Keith Bloch

Accurate state estimation is critical for optimal policy design in dynamic systems. However, obtaining true system states is often impractical or infeasible, complicating the policy learning process. This paper introduces a novel neural…

Computer Vision and Pattern Recognition · Computer Science 2025-06-09 Ashik E Rasul , Hyung-Jin Yoon

This paper studies the statistical theory of batch data reinforcement learning with function approximation. Consider the off-policy evaluation problem, which is to estimate the cumulative value of a new target policy from logged history…

Machine Learning · Computer Science 2020-02-25 Yaqi Duan , Mengdi Wang

We consider the problem of sequentially making decisions that are rewarded by "successes" and "failures" which can be predicted through an unknown relationship that depends on a partially controllable vector of attributes for each instance.…

Machine Learning · Statistics 2017-09-18 Yingfei Wang , Chu Wang , Warren Powell

While off-policy temporal difference (TD) methods have widely been used in reinforcement learning due to their efficiency and simple implementation, their Bayesian counterparts have not been utilized as frequently. One reason is that the…

Machine Learning · Computer Science 2019-10-25 Heejin Jeong , Clark Zhang , George J. Pappas , Daniel D. Lee

The current paper studies the problem of agnostic $Q$-learning with function approximation in deterministic systems where the optimal $Q$-function is approximable by a function in the class $\mathcal{F}$ with approximation error $\delta \ge…

Machine Learning · Computer Science 2020-02-18 Simon S. Du , Jason D. Lee , Gaurav Mahajan , Ruosong Wang

Developing accurate off-policy estimators is crucial for both evaluating and optimizing for new policies. The main challenge in off-policy estimation is the distribution shift between the logging policy that generates data and the target…

Machine Learning · Computer Science 2023-10-25 Noveen Sachdeva , Lequn Wang , Dawen Liang , Nathan Kallus , Julian McAuley

Diffusion models have become a popular choice for representing actor policies in behavior cloning and offline reinforcement learning. This is due to their natural ability to optimize an expressive class of distributions over a continuous…

Machine Learning · Computer Science 2025-02-17 Michael Psenka , Alejandro Escontrela , Pieter Abbeel , Yi Ma

There is growing interest in utilizing flow-based models as decision-making policies in reinforcement learning due to their high expressive capacity. However, effectively leveraging this expressivity for value maximization remains…

Machine Learning · Computer Science 2026-05-14 JaeHyeok Doo , Byeongguk Jeon , Seonghyeon Ye , Kimin Lee , Minjoon Seo

The dominant framework for off-policy multi-goal reinforcement learning involves estimating goal conditioned Q-value function. When learning to achieve multiple goals, data efficiency is intimately connected with the generalization of the…

Artificial Intelligence · Computer Science 2023-06-28 Zhang-Wei Hong , Ge Yang , Pulkit Agrawal

Model-agnostic meta-reinforcement learning requires estimating the Hessian matrix of value functions. This is challenging from an implementation perspective, as repeatedly differentiating policy gradient estimates may lead to biased Hessian…

Machine Learning · Computer Science 2021-11-04 Yunhao Tang , Tadashi Kozuno , Mark Rowland , Rémi Munos , Michal Valko

We present state advantage weighting for offline reinforcement learning (RL). In contrast to action advantage $A(s,a)$ that we commonly adopt in QSA learning, we leverage state advantage $A(s,s^\prime)$ and QSS learning for offline RL,…

Machine Learning · Computer Science 2022-11-09 Jiafei Lyu , Aicheng Gong , Le Wan , Zongqing Lu , Xiu Li

We present an algorithm for learning an approximate action-value soft Q-function in the relative entropy regularised reinforcement learning setting, for which an optimal improved policy can be recovered in closed form. We use recent…

Machine Learning · Computer Science 2019-11-06 Jonas Degrave , Abbas Abdolmaleki , Jost Tobias Springenberg , Nicolas Heess , Martin Riedmiller

In traditional reinforcement learning, an agent maximizes the reward collected during its interaction with the environment by approximating the optimal policy through the estimation of value functions. Typically, given a state s and action…

Machine Learning · Computer Science 2018-06-20 Shangda Li , Selina Bing , Steven Yang

This paper presents a model-free approximation for the Hessian of the performance of deterministic policies to use in the context of Reinforcement Learning based on Quasi-Newton steps in the policy parameters. We show that the approximate…

Machine Learning · Computer Science 2022-03-29 Arash Bahari Kordabad , Hossein Nejatbakhsh Esfahani , Wenqi Cai , Sebastien Gros

Offline reinforcement learning requires reconciling two conflicting aims: learning a policy that improves over the behavior policy that collected the dataset, while at the same time minimizing the deviation from the behavior policy so as to…

Machine Learning · Computer Science 2021-10-13 Ilya Kostrikov , Ashvin Nair , Sergey Levine

These lecture notes are derived from a graduate-level course in dynamic optimization, offering an introduction to techniques and models extensively used in management science, economics, operations research, engineering, and computer…

Optimization and Control · Mathematics 2024-10-11 Bar Light