English
Related papers

Related papers: Finite-time analysis of single-timescale actor-cri…

200 papers

Actor-critic (AC) methods are ubiquitous in reinforcement learning. Although it is understood that AC methods are closely related to policy gradient (PG), their precise connection has not been fully characterized previously. In this paper,…

Artificial Intelligence · Computer Science 2021-06-15 Junfeng Wen , Saurabh Kumar , Ramki Gummadi , Dale Schuurmans

Multi-agent reinforcement learning (MARL) methods have achieved state-of-the-art results on a range of multi-agent tasks. Yet, MARL algorithms typically require significantly more environment interactions than their single-agent…

Systems and Control · Electrical Eng. & Systems 2026-03-17 Tom Danino , Nahum Shimkin

We introduce a sequence-conditioned critic for Soft Actor--Critic (SAC) that models trajectory context with a lightweight Transformer and trains on aggregated $N$-step targets. Unlike prior approaches that (i) score state--action pairs in…

Machine Learning · Computer Science 2025-09-30 Dong Tian , Onur Celik , Gerhard Neumann

It is well known that conventional simulation algorithms are inefficient for the statistical description of macroscopic systems exactly at the critical point due to the divergence of the corresponding relaxation time (critical slowing…

Computational Physics · Physics 2008-11-26 N. G. Antoniou , F. K. Diakonos , E. N. Saridakis , G. A. Tsolias

In this work, we propose to apply trust region optimization to deep reinforcement learning using a recently proposed Kronecker-factored approximation to the curvature. We extend the framework of natural policy gradient and propose to…

Machine Learning · Computer Science 2017-08-21 Yuhuai Wu , Elman Mansimov , Shun Liao , Roger Grosse , Jimmy Ba

We present the first provably convergent two-timescale off-policy actor-critic algorithm (COF-PAC) with function approximation. Key to COF-PAC is the introduction of a new critic, the emphasis critic, which is trained via Gradient Emphasis…

Machine Learning · Computer Science 2020-11-25 Shangtong Zhang , Bo Liu , Hengshuai Yao , Shimon Whiteson

Temporal difference (TD) learning algorithms with neural network function parameterization have well-established empirical success in many practical large-scale reinforcement learning tasks. However, theoretical understanding of these…

Machine Learning · Computer Science 2024-05-08 Zhifa Ke , Zaiwen Wen , Junyu Zhang

We study the policy evaluation problem in multi-agent reinforcement learning where a group of agents, with jointly observed states and private local actions and rewards, collaborate to learn the value function of a given policy via local…

Optimization and Control · Mathematics 2021-11-08 Dongsheng Ding , Xiaohan Wei , Zhuoran Yang , Zhaoran Wang , Mihailo R. Jovanović

In value-based reinforcement learning methods such as deep Q-learning, function approximation errors are known to lead to overestimated value estimates and suboptimal policies. We show that this problem persists in an actor-critic setting…

Artificial Intelligence · Computer Science 2018-10-23 Scott Fujimoto , Herke van Hoof , David Meger

Deep reinforcement learning (RL) has proven a powerful technique in many sequential decision making domains. However, Robotics poses many challenges for RL, most notably training on a physical system can be expensive and dangerous, which…

Robotics · Computer Science 2017-10-19 Lerrel Pinto , Marcin Andrychowicz , Peter Welinder , Wojciech Zaremba , Pieter Abbeel

We address the discounted reward setting in reinforcement learning (RL). To mitigate the value approximation challenges in policy gradient methods, actor-critic approaches have been developed and are known to converge to stationary points…

Machine Learning · Computer Science 2026-05-15 Sanjeev Manivannan , Shuban V

We introduce a new method for online parameter estimation in stochastic interacting particle systems, based on continuous observation of a small number of particles from the system. Our method recursively updates the model parameters using…

Statistics Theory · Mathematics 2026-02-25 Louis Sharrock , Nikolas Kantas , Grigorios A. Pavliotis

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

This paper develops a unified and computationally efficient method for change-point estimation along the time dimension in a non-stationary spatio-temporal process. By modeling a non-stationary spatio-temporal process as a piecewise…

Methodology · Statistics 2023-10-09 Zifeng Zhao , Ting Fung Ma , Wai Leong Ng , Chun Yip Yau

Recent success in cooperative multi-agent reinforcement learning (MARL) relies on centralized training and policy sharing. Centralized training eliminates the issue of non-stationarity MARL yet induces large communication costs, and policy…

Multiagent Systems · Computer Science 2022-04-04 Dingyang Chen , Yile Li , Qi Zhang

Human-computer interactive systems that rely on machine learning are becoming paramount to the lives of millions of people who use digital assistants on a daily basis. Yet, further advances are limited by the availability of data and the…

Machine Learning · Computer Science 2020-04-29 Katya Kudashkina , Valliappa Chockalingam , Graham W. Taylor , Michael Bowling

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

We consider an improper reinforcement learning setting where a learner is given $M$ base controllers for an unknown Markov decision process, and wishes to combine them optimally to produce a potentially new controller that can outperform…

Machine Learning · Computer Science 2022-07-20 Mohammadi Zaki , Avinash Mohan , Aditya Gopalan , Shie Mannor

Actor-critic methods constitute a central paradigm in reinforcement learning (RL), coupling policy evaluation with policy improvement. While effective across many domains, these methods rely on separate actor and critic networks, which…

Machine Learning · Computer Science 2025-09-26 Donghyeon Ki , Hee-Jun Ahn , Kyungyoon Kim , Byung-Jun Lee

Many sequential decision-making problems need optimization of different objectives which possibly conflict with each other. The conventional way to deal with a multi-task problem is to establish a scalar objective function based on a linear…

Machine Learning · Computer Science 2023-02-28 Mohsen Amidzadeh