English
Related papers

Related papers: Finite Sample Analysis of Two-Time-Scale Natural A…

200 papers

This paper presents an actor-critic deep reinforcement learning agent with experience replay that is stable, sample efficient, and performs remarkably well on challenging environments, including the discrete 57-game Atari domain and several…

Machine Learning · Computer Science 2017-07-11 Ziyu Wang , Victor Bapst , Nicolas Heess , Volodymyr Mnih , Remi Munos , Koray Kavukcuoglu , Nando de Freitas

The option-critic architecture (Bacon, Harb, and Precup 2017) and several variants have successfully demonstrated the use of the options framework proposed by Sutton et al (Sutton, Precup, and Singh1999) to scale learning and planning in…

Artificial Intelligence · Computer Science 2019-06-13 Elita Lobo , Scott Jordan

We propose A-Crab (Actor-Critic Regularized by Average Bellman error), a new practical algorithm for offline reinforcement learning (RL) in complex environments with insufficient data coverage. Our algorithm combines the marginalized…

Machine Learning · Computer Science 2023-10-10 Hanlin Zhu , Paria Rashidinejad , Jiantao Jiao

We prove local convergence of several notable gradient descent algorithms used in machine learning, for which standard stochastic gradient descent theory does not apply directly. This includes, first, online algorithms for recurrent models…

Dynamical Systems · Mathematics 2021-01-11 Pierre-Yves Massé , Yann Ollivier

We study online control for continuous-time linear systems with finite sampling rates, where the objective is to design an online procedure that learns under non-stochastic noise and performs comparably to a fixed optimal linear controller.…

Optimization and Control · Mathematics 2025-06-10 Jingwei Li , Jing Dong , Can Chang , Baoxiang Wang , Jingzhao Zhang

While multi-agent reinforcement learning (MARL) has produced numerous algorithms that converge to Nash or related equilibria, such equilibria are often non-unique and can exhibit widely varying efficiency. This raises a fundamental…

Computer Science and Game Theory · Computer Science 2026-01-29 Runyu Zhang , Gioele Zardini , Asuman Ozdaglar , Jeff Shamma , Na Li

We consider an online two-stage stochastic optimization with long-term constraints over a finite horizon of $T$ periods. At each period, we take the first-stage action, observe a model parameter realization and then take the second-stage…

Machine Learning · Computer Science 2024-01-03 Piao Hu , Jiashuo Jiang , Guodong Lyu , Hao Su

The two-time scale nature of SAC, which is an actor-critic algorithm, is characterised by the fact that the critic estimate has not converged for the actor at any given time, but since the critic learns faster than the actor, it ensures…

Greedy-GQ is an off-policy two timescale algorithm for optimal control in reinforcement learning. This paper develops the first finite-sample analysis for the Greedy-GQ algorithm with linear function approximation under Markovian noise. Our…

Machine Learning · Computer Science 2020-05-21 Yue Wang , Shaofeng Zou

For a given distribution, learning algorithm, and performance metric, the rate of convergence (or data-scaling law) is the asymptotic behavior of the algorithm's test performance as a function of number of train samples. Many learning…

Machine Learning · Computer Science 2021-11-10 Preetum Nakkiran

A central task of artificial intelligence is the design of artificial agents that act towards specified goals in partially observed environments. Since such environments frequently include interaction over time with other agents with their…

Computer Science and Game Theory · Computer Science 2012-05-14 Miroslav Dudik , Geoffrey Gordon

We show that offline actor-critic reinforcement learning can scale to large models - such as transformers - and follows similar scaling laws as supervised learning. We find that offline actor-critic algorithms can outperform strong,…

Policy gradient methods are among the most effective methods in challenging reinforcement learning problems with large state and/or action spaces. However, little is known about even their most basic theoretical convergence properties,…

Machine Learning · Computer Science 2020-10-16 Alekh Agarwal , Sham M. Kakade , Jason D. Lee , Gaurav Mahajan

We examine online safe multi-agent reinforcement learning using constrained Markov games in which agents compete by maximizing their expected total rewards under a constraint on expected total utilities. Our focus is confined to an episodic…

Machine Learning · Computer Science 2023-06-02 Dongsheng Ding , Xiaohan Wei , Zhuoran Yang , Zhaoran Wang , Mihailo R. Jovanović

We study the so-called two-time-scale stochastic approximation, a simulation-based approach for finding the roots of two coupled nonlinear operators. Our focus is to characterize its finite-time performance in a Markov setting, which often…

Optimization and Control · Mathematics 2021-04-06 Thinh T. Doan

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

We study policy gradient (PG) for reinforcement learning in continuous time and space under the regularized exploratory formulation developed by Wang et al. (2020). We represent the gradient of the value function with respect to a given…

Machine Learning · Computer Science 2022-07-26 Yanwei Jia , Xun Yu Zhou

Despite definite success in deep reinforcement learning problems, actor-critic algorithms are still confronted with sample inefficiency in complex environments, particularly in tasks where efficient exploration is a bottleneck. These…

Machine Learning · Computer Science 2021-02-09 Yannis Flet-Berliac , Johan Ferret , Olivier Pietquin , Philippe Preux , Matthieu Geist

In this paper we propose a recursive online algorithm for estimating the parameters of a time-varying ARCH process. The estimation is done by updating the estimator at time point $t-1$ with observations about the time point $t$ to yield an…

Statistics Theory · Mathematics 2009-09-29 Rainer Dahlhaus , Suhasini Subba Rao

Policy Dual Averaging (PDA) offers a principled Policy Mirror Descent (PMD) framework that more naturally admits value function approximation than standard PMD, enabling the use of approximate advantage (or Q-) functions while retaining…

Machine Learning · Computer Science 2026-03-12 Ji Gao , Caleb Ju , Guanghui Lan , Zhaohui Tong