English
Related papers

Related papers: Refined Analysis of Entropy-Regularized Actor-Crit…

200 papers

Asymmetric actor-critic methods are widely used in partially observable reinforcement learning, but typically assume full state observability to condition the critic during training, which is often unrealistic in practice. We introduce the…

Machine Learning · Computer Science 2026-02-06 Daniel Ebi , Gaspard Lambrechts , Damien Ernst , Klemens Böhm

Bandit algorithms are widely used in sequential decision problems to maximize the cumulative reward. One potential application is mobile health, where the goal is to promote the user's health through personalized interventions based on user…

Machine Learning · Statistics 2022-08-23 Gi-Soo Kim , Hyun-Joon Yang , Jane P. Kim

We study the problem of off-policy critic evaluation in several variants of value-based off-policy actor-critic algorithms. Off-policy actor-critic algorithms require an off-policy critic evaluation step, to estimate the value of the new…

Machine Learning · Computer Science 2019-12-12 Riashat Islam , Raihan Seraj , Samin Yeasar Arnob , Doina Precup

This paper introduces the Active-Importance-Sampling Actor-Critic (AISAC) algorithm, an extension of the Actor-Critic framework for reducing variance in policy gradient estimation. AISAC optimizes the behavior policy to minimize gradient…

Machine Learning · Computer Science 2026-05-11 Majid Molaei , Gabor Paczolay , Matteo Papini , Alberto Maria Metelli , Marcello Restelli

Despite the popularity of the actor-critic method and the practical needs of collaborative policy training, existing works typically either overlook environmental heterogeneity or give up personalization altogether by training a single…

Machine Learning · Computer Science 2026-05-15 Leo Muxing Wang , Pengkun Yang , Lili Su

Recent advancements in off-policy Reinforcement Learning (RL) have significantly improved sample efficiency, primarily due to the incorporation of various forms of regularization that enable more gradient update steps than traditional…

Machine Learning · Computer Science 2024-06-21 Michal Nauman , Michał Bortkiewicz , Piotr Miłoś , Tomasz Trzciński , Mateusz Ostaszewski , Marek Cygan

Deterministic-policy actor-critic algorithms for continuous control improve the actor by plugging its actions into the critic and ascending the action-value gradient, which is obtained by chaining the actor's Jacobian matrix with the…

Artificial Intelligence · Computer Science 2020-10-23 Pierluca D'Oro , Wojciech Jaśkowski

\Ac{MPC} and \ac{RL} are two powerful control strategies with, arguably, complementary advantages. In this work, we show how actor-critic \ac{RL} techniques can be leveraged to improve the performance of \ac{MPC}. The \ac{RL} critic is used…

Systems and Control · Electrical Eng. & Systems 2024-06-07 Rudolf Reiter , Andrea Ghezzi , Katrin Baumgärtner , Jasper Hoffmann , Robert D. McAllister , Moritz Diehl

A reliable critic is central to on-policy actor-critic learning. But it becomes challenging to learn a reliable critic in a multi-agent sparse reward scenario due to two factors: 1) The joint action space grows exponentially with the number…

Machine Learning · Computer Science 2023-04-21 Kinal Mehta , Anuj Mahajan , Pawan Kumar

Regularization is a core component of recent Reinforcement Learning (RL) algorithms. Mirror Descent Value Iteration (MDVI) uses both Kullback-Leibler divergence and entropy as regularizers in its value and policy updates. Despite its…

Machine Learning · Computer Science 2026-01-09 Ryo Iwaki

Policy gradient algorithms typically combine discounted future rewards with an estimated value function, to compute the direction and magnitude of parameter updates. However, for most Reinforcement Learning tasks, humans can provide…

Machine Learning · Computer Science 2019-04-09 Ishan Durugkar , Matthew Hausknecht , Adith Swaminathan , Patrick MacAlpine

Soft Actor Critic (SAC) algorithms show remarkable performance in complex simulated environments. A key element of SAC networks is entropy regularization, which prevents the SAC actor from optimizing against fine grained features,…

Machine Learning · Computer Science 2020-06-23 Miguel Campo , Zhengxing Chen , Luke Kung , Kittipat Virochsiri , Jianyu Wang

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

Having a perfect model to compute the optimal policy is often infeasible in reinforcement learning. It is important in high-stakes domains to quantify and manage risk induced by model uncertainties. Entropic risk measure is an exponential…

Machine Learning · Computer Science 2020-06-23 Reazul Hasan Russel , Bahram Behzadian , Marek Petrik

The hierarchical interaction between the actor and critic in actor-critic based reinforcement learning algorithms naturally lends itself to a game-theoretic interpretation. We adopt this viewpoint and model the actor and critic interaction…

Machine Learning · Computer Science 2021-09-28 Liyuan Zheng , Tanner Fiez , Zane Alumbaugh , Benjamin Chasnov , Lillian J. Ratliff

Model-free off-policy actor-critic methods are an efficient solution to complex continuous control tasks. However, these algorithms rely on a number of design tricks and hyperparameters, making their application to new domains difficult and…

Machine Learning · Computer Science 2021-10-26 Jake Grigsby , Jin Yong Yoo , Yanjun Qi

Reinforcement Learning (RL) techniques have drawn great attention in many challenging tasks, but their performance deteriorates dramatically when applied to real-world problems. Various methods, such as domain randomization, have been…

Machine Learning · Computer Science 2022-08-05 Wangyang Yue , Yuan Zhou , Xiaochuan Zhang , Yuchen Hua , Zhiyuan Wang , Guang Kou

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

Although actor-critic methods have been successful in practice, their theoretical analyses have several limitations. Specifically, existing theoretical work either sidesteps the exploration problem by making strong assumptions or analyzes…

Machine Learning · Computer Science 2026-04-02 Max Qiushi Lin , Reza Asad , Kevin Tan , Haque Ishfaq , Csaba Szepesvari , Sharan Vaswani

We consider a version of actor-critic which uses proportional step-sizes and only one critic update with a single sample from the stationary distribution per actor step. We provide an analysis of this method using the small-gain theorem.…

Optimization and Control · Mathematics 2023-05-26 Alex Olshevsky , Bahman Gharesifard