English
Related papers

Related papers: SBEED: Convergent Reinforcement Learning with Nonl…

200 papers

The \textit{Smoothed Bellman Error Embedding} algorithm~\citep{dai2018sbeed}, known as SBEED, was proposed as a provably convergent reinforcement learning algorithm with general nonlinear function approximation. It has been successfully…

Machine Learning · Computer Science 2020-07-09 Ahmed Touati , Pascal Vincent

Regularized Markov Decision Processes serve as models of sequential decision making under uncertainty wherein the decision maker has limited information processing capacity and/or aversion to model ambiguity. With functional approximation,…

Artificial Intelligence · Computer Science 2025-02-11 Jiachen Xi , Alfredo Garcia , Petar Momcilovic

We propose a unifying algorithm for non-smooth non-convex optimization. The algorithm approximates the objective function by a convex model function and finds an approximate (Bregman) proximal point of the convex model. This approximate…

Optimization and Control · Mathematics 2018-06-27 Peter Ochs , Jalal Fadili , Thomas Brox

Value function learning plays a central role in many state-of-the-art reinforcement-learning algorithms. Many popular algorithms like Q-learning do not optimize any objective function, but are fixed-point iterations of some variant of…

Machine Learning · Computer Science 2020-01-10 Yihao Feng , Lihong Li , Qiang Liu

We develop a general optimization-theoretic framework for Bregman-Variational Learning Dynamics (BVLD), a new class of operator-based updates that unify Bayesian inference, mirror descent, and proximal learning under time-varying…

Optimization and Control · Mathematics 2025-10-24 Jinho Cha , Youngchul Kim , Jungmin Shin , Jaeyoung Cho , Seon Jin Kim , Junyeol Ryu

Many recent successful (deep) reinforcement learning algorithms make use of regularization, generally based on entropy or Kullback-Leibler divergence. We propose a general theory of regularized Markov Decision Processes that generalizes…

Machine Learning · Computer Science 2019-06-05 Matthieu Geist , Bruno Scherrer , Olivier Pietquin

We study reinforcement learning methods with linear function approximation under non-Markov state and cost processes. We first consider the policy evaluation method and show that the algorithm converges under suitable ergodicity conditions…

Machine Learning · Computer Science 2026-01-05 Ali Devran Kara

We prove performance guarantees of two algorithms for approximating $Q^\star$ in batch reinforcement learning. Compared to classical iterative methods such as Fitted Q-Iteration---whose performance loss incurs quadratic dependence on…

Machine Learning · Computer Science 2020-08-25 Tengyang Xie , Nan Jiang

In reinforcement learning, the objective is almost always defined as a \emph{cumulative} function over the rewards along the process. However, there are many optimal control and reinforcement learning problems in various application fields,…

Machine Learning · Computer Science 2024-04-15 Wei Cui , Wei Yu

The problem of solving Markov decision processes under function approximation remains a fundamental challenge, even under linear function approximation settings. A key difficulty arises from a geometric mismatch: while the Bellman…

Machine Learning · Computer Science 2026-04-09 Hyukjun Yang , Han-Dong Lim , Donghwan Lee

In this paper, we set forth a new vision of reinforcement learning developed by us over the past few years, one that yields mathematically rigorous solutions to longstanding important questions that have remained unresolved: (i) how to…

Machine Learning · Computer Science 2014-05-28 Sridhar Mahadevan , Bo Liu , Philip Thomas , Will Dabney , Steve Giguere , Nicholas Jacek , Ian Gemp , Ji Liu

We introduce and analyze an algorithm for the minimization of convex functions that are the sum of differentiable terms and proximable terms composed with linear operators. The method builds upon the recently developed smoothed gap…

Optimization and Control · Mathematics 2017-06-20 Quang Van Nguyen , Olivier Fercoq , Volkan Cevher

We consider Markov Decision Problems defined over continuous state and action spaces, where an autonomous agent seeks to learn a map from its states to actions so as to maximize its long-term discounted accumulation of rewards. We address…

Machine Learning · Computer Science 2018-04-23 Alec Koppel , Ekaterina Tolstaya , Ethan Stump , Alejandro Ribeiro

We present a simple transformation of any linear program or semidefinite program into an equivalent convex optimization problem whose only constraints are linear equations. The objective function is defined on the whole space, making…

Optimization and Control · Mathematics 2014-10-07 James Renegar

We study the exploration problem with approximate linear action-value functions in episodic reinforcement learning under the notion of low inherent Bellman error, a condition normally employed to show convergence of approximate value…

Machine Learning · Computer Science 2020-06-30 Andrea Zanette , Alessandro Lazaric , Mykel Kochenderfer , Emma Brunskill

We propose an adaptive smoothing algorithm based on Nesterov's smoothing technique in \cite{Nesterov2005c} for solving "fully" nonsmooth composite convex optimization problems. Our method combines both Nesterov's accelerated proximal…

Optimization and Control · Mathematics 2016-07-05 Quoc Tran-Dinh

We propose a new self-adaptive, double-loop smoothing algorithm to solve composite, nonsmooth, and constrained convex optimization problems. Our algorithm is based on Nesterov's smoothing technique via general Bregman distance functions. It…

Optimization and Control · Mathematics 2018-08-15 Quoc Tran-Dinh , Ahmet Alacaoglu , Olivier Fercoq , Volkan Cevher

Advantage learning (AL) aims to improve the robustness of value-based reinforcement learning against estimation errors with action-gap-based regularization. Unfortunately, the method tends to be unstable in the case of function…

Machine Learning · Computer Science 2022-03-22 Yaozhong Gan , Zhe Zhang , Xiaoyang Tan

We study the safe reinforcement learning problem with nonlinear function approximation, where policy optimization is formulated as a constrained optimization problem with both the objective and the constraint being nonconvex functions. For…

Machine Learning · Computer Science 2019-10-29 Ming Yu , Zhuoran Yang , Mladen Kolar , Zhaoran Wang

It is well known that the extension of Watkins' algorithm to general function approximation settings is challenging: does the projected Bellman equation have a solution? If so, is the solution useful in the sense of generating a good…

Optimization and Control · Mathematics 2020-08-11 Prashant G. Mehta , Sean P. Meyn
‹ Prev 1 2 3 10 Next ›