English
Related papers

Related papers: Mirror descent actor-critic methods for entropy re…

200 papers

Actor-critic style two-time-scale algorithms are one of the most popular methods in reinforcement learning, and have seen great empirical success. However, their performance is not completely understood theoretically. In this paper, we…

Machine Learning · Computer Science 2022-02-22 Sajad Khodadadian , Thinh T. Doan , Justin Romberg , Siva Theja Maguluri

Diffusion Policy has shown great performance in robotic manipulation tasks under stochastic perturbations, due to its ability to model multimodal action distributions. Nonetheless, its reliance on a computationally expensive reverse-time…

Robotics · Computer Science 2025-11-20 Gabriel Lauzier , Alexandre Girard , François Ferland

We study the error introduced by entropy regularization in infinite-horizon discrete discounted Markov decision processes. We show that this error decreases exponentially in the inverse regularization strength, both in a weighted…

Optimization and Control · Mathematics 2025-12-16 Johannes Müller , Semih Cayci

The problem of on-line off-policy evaluation (OPE) has been actively studied in the last decade due to its importance both as a stand-alone problem and as a module in a policy improvement scheme. However, most Temporal Difference (TD) based…

Machine Learning · Statistics 2017-02-24 Assaf Hallak , Shie Mannor

We study a new two-time-scale stochastic gradient method for solving optimization problems, where the gradients are computed with the aid of an auxiliary variable under samples generated by time-varying MDPs controlled by the underlying…

Optimization and Control · Mathematics 2024-08-27 Sihan Zeng , Thinh T. Doan , Justin Romberg

Recent works in Reinforcement Learning (RL) combine model-free (Mf)-RL algorithms with model-based (Mb)-RL approaches to get the best from both: asymptotic performance of Mf-RL and high sample-efficiency of Mb-RL. Inspired by these works,…

Machine Learning · Computer Science 2021-10-26 Soumya Rani Samineni

Online safe reinforcement learning (RL) plays a key role in dynamic environments, with applications in autonomous driving, robotics, and cybersecurity. The objective is to learn optimal policies that maximize rewards while satisfying safety…

Machine Learning · Computer Science 2025-06-03 Jiahui Zhu , Kihyun Yu , Dabeen Lee , Xin Liu , Honghao Wei

Actor-critic algorithms are widely used in reinforcement learning, but are challenging to mathematically analyse due to the online arrival of non-i.i.d. data samples. The distribution of the data samples dynamically changes as the model is…

Machine Learning · Computer Science 2023-09-20 Ziheng Wang , Justin Sirignano

This paper is concerned with convergence analysis for the mirror descent (MD) method, a well-known algorithm in convex optimization. An analysis framework via integral quadratic constraints (IQCs) is constructed to analyze the convergence…

Optimization and Control · Mathematics 2022-09-12 Mengmou Li , Khaled Laib , Ioannis Lestas

Diffusion policies have achieved great success in online reinforcement learning (RL) due to their strong expressive capacity. However, the inference of diffusion policy models relies on a slow iterative sampling process, which limits their…

Machine Learning · Computer Science 2025-10-17 Tianyi Chen , Haitong Ma , Na Li , Kai Wang , Bo Dai

In the Lasry--Lions framework, Mean-Field Games (MFGs) model interactions among an infinite number of agents. However, existing algorithms either require strict monotonicity or only guarantee the convergence of averaged iterates, as in…

Computer Science and Game Theory · Computer Science 2025-10-28 Noboru Isobe , Kenshi Abe , Kaito Ariu

We revisit textbook claims that entropy must increase and show that, under time-reversal invariant microscopic dynamics, no universal trajectory-wise or statistical assertion that the coarse-grained entropy $S(t)$ is non-decreasing can…

Statistical Mechanics · Physics 2026-03-06 Ting Peng

Most of the recent successful applications of neural networks have been based on training with gradient descent updates. However, for some small networks, other mirror descent updates learn provably more efficiently when the target is…

Machine Learning · Computer Science 2020-06-24 Ehsan Amid , Manfred K. Warmuth

Consider linear ill-posed problems governed by the system $A_i x = y_i$ for $i =1, \cdots, p$, where each $A_i$ is a bounded linear operator from a Banach space $X$ to a Hilbert space $Y_i$. In case $p$ is huge, solving the problem by an…

Numerical Analysis · Mathematics 2023-05-17 Qinian Jin , Xiliang Lu , Liuying Zhang

Recent successful deep reinforcement learning algorithms, such as Trust Region Policy Optimization (TRPO) or Proximal Policy Optimization (PPO), are fundamentally variations of conservative policy iteration (CPI). These algorithms iterate…

Machine Learning · Computer Science 2020-01-27 Erinc Merdivan , Sten Hanke , Matthieu Geist

High-order accurate, $\textit{entropy stable}$ numerical methods for hyperbolic conservation laws have attracted much interest over the last decade, but only a few rigorous convergence results are available, particularly in multiple space…

Numerical Analysis · Mathematics 2019-06-13 Neelabja Chatterjee , Ulrik Skre Fjordholm

We focus on parameterized policy search for reinforcement learning over continuous action spaces. Typically, one assumes the score function associated with a policy is bounded, which fails to hold even for Gaussian policies. To properly…

Machine Learning · Computer Science 2022-02-01 Amrit Singh Bedi , Souradip Chakraborty , Anjaly Parayil , Brian Sadler , Pratap Tokekar , Alec Koppel

In this paper, we revisit the problem of using in-distribution public data to improve the privacy/utility trade-offs for differentially private (DP) model training. (Here, public data refers to auxiliary data sets that have no privacy…

Markov Decision Processes (MDPs) are a formal framework for modeling and solving sequential decision-making problems. In finite-time horizons such problems are relevant for instance for optimal stopping or specific supply chain problems,…

Optimization and Control · Mathematics 2024-05-07 Sara Klein , Simon Weissmann , Leif Döring

In this paper, we propose a novel policy iteration method, called dynamic policy programming (DPP), to estimate the optimal policy in the infinite-horizon Markov decision processes. We prove the finite-iteration and asymptotic l\infty-norm…

Machine Learning · Computer Science 2011-09-09 Mohammad Gheshlaghi Azar , Vicenc Gomez , Hilbert J. Kappen
‹ Prev 1 8 9 10 Next ›