English
Related papers

Related papers: TD-Regularized Actor-Critic Methods

200 papers

In current model-free reinforcement learning (RL) algorithms, stability criteria based on sampling methods are commonly utilized to guide policy optimization. However, these criteria only guarantee the infinite-time convergence of the…

Robotics · Computer Science 2023-10-16 Shengjie Wang , Fengbo Lan , Xiang Zheng , Yuxue Cao , Oluwatosin Oseni , Haotian Xu , Tao Zhang , Yang Gao

Dynamic Reinforcement Learning (Dynamic RL), proposed in this paper, directly controls system dynamics, instead of the actor (action-generating neural network) outputs at each moment, bringing about a major qualitative shift in…

Machine Learning · Computer Science 2025-02-17 Katsunari Shibata

Deep reinforcement learning (RL) methods have significant potential for dialogue policy optimisation. However, they suffer from a poor performance in the early stages of learning. This is especially problematic for on-line learning with…

Computation and Language · Computer Science 2017-07-06 Pei-Hao Su , Pawel Budzianowski , Stefan Ultes , Milica Gasic , Steve Young

We prove the stability and global convergence of a coupled actor-critic gradient flow for infinite-horizon and entropy-regularised Markov decision processes (MDPs) in continuous state and action space with linear function approximation…

Optimization and Control · Mathematics 2025-10-17 Denis Zorba , David Šiška , Lukasz Szpruch

Actor-critic methods have achieved state-of-the-art performance in various challenging tasks. However, theoretical understandings of their performance remain elusive and challenging. Existing studies mostly focus on practically uncommon…

Machine Learning · Computer Science 2025-05-09 Xuyang Chen , Jingliang Duan , Lin Zhao

This paper introduces a novel reinforcement learning (RL) strategy designed to facilitate rapid autonomy transfer by utilizing pre-trained critic value functions from multiple environments. Unlike traditional methods that require extensive…

Flow-based generative models have shown remarkable success in text-to-image generation, yet fine-tuning them with intermediate feedback remains challenging, especially for continuous-time flow matching models. Most existing approaches…

Machine Learning · Computer Science 2025-10-22 Jiajun Fan , Chaoran Cheng , Shuaike Shen , Xiangxin Zhou , Ge Liu

Adversarial training (AT) has proven to be one of the most effective ways to defend Deep Neural Networks (DNNs) against adversarial attacks. However, the phenomenon of robust overfitting, i.e., the robustness will drop sharply at a certain…

Machine Learning · Computer Science 2022-05-25 Shudong Zhang , Haichang Gao , Tianwei Zhang , Yunyi Zhou , Zihui Wu

To improve policy robustness of deep reinforcement learning agents, a line of recent works focus on producing disturbances of the environment. Existing approaches of the literature to generate meaningful disturbances of the environment are…

Machine Learning · Computer Science 2022-10-04 Lucas Schott , Hatem Hajri , Sylvain Lamprier

We develop a new policy gradient and actor-critic algorithm for solving mean-field control problems within a continuous time reinforcement learning setting. Our approach leverages a gradient-based representation of the value function,…

Machine Learning · Statistics 2023-09-11 Huyên Pham , Xavier Warin

We propose a single time-scale actor-critic algorithm to solve the linear quadratic regulator (LQR) problem. A least squares temporal difference (LSTD) method is applied to the critic and a natural policy gradient method is used for the…

Optimization and Control · Mathematics 2022-06-07 Mo Zhou , Jianfeng Lu

In reinforcement learning, the TD($\lambda$) algorithm is a fundamental policy evaluation method with an efficient online implementation that is suitable for large-scale problems. One practical drawback of TD($\lambda$) is its sensitivity…

Machine Learning · Statistics 2014-12-23 Aviv Tamar , Panos Toulis , Shie Mannor , Edoardo M. Airoldi

When developing reinforcement learning agents, the standard approach is to train an agent to converge to a fixed policy that is as close to optimal as possible for a single fixed reward function. If different agent behaviour is required in…

Multiagent Systems · Computer Science 2021-01-29 David O'Callaghan , Patrick Mannion

In order to tackle the difficulty associated with the ill-posed nature of the image registration problem, regularization is often used to constrain the solution space. For most learning-based registration approaches, the regularization…

Computer Vision and Pattern Recognition · Computer Science 2022-03-03 Zhe Xu , Jie Luo , Donghuan Lu , Jiangpeng Yan , Sarah Frisken , Jayender Jagadeesan , William Wells , Xiu Li , Yefeng Zheng , Raymond Tong

Generalizability and stability are two key objectives for operating reinforcement learning (RL) agents in the real world. Designing RL algorithms that optimize these objectives can be a costly and painstaking process. This paper presents…

Machine Learning · Computer Science 2023-04-26 Juan Jose Garau-Luis , Yingjie Miao , John D. Co-Reyes , Aaron Parisi , Jie Tan , Esteban Real , Aleksandra Faust

Policy evaluation algorithms are essential to reinforcement learning due to their ability to predict the performance of a policy. However, there are two long-standing issues lying in this prediction problem that need to be tackled:…

Machine Learning · Computer Science 2021-12-30 Daoming Lyu , Bo Liu , Matthieu Geist , Wen Dong , Saad Biaz , Qi Wang

In a broad class of reinforcement learning applications, stochastic rewards have heavy-tailed distributions, which lead to infinite second-order moments for stochastic (semi)gradients in policy evaluation and direct policy optimization. In…

Machine Learning · Computer Science 2023-06-21 Semih Cayci , Atilla Eryilmaz

We present a non-asymptotic convergence analysis of $Q$-learning and actor-critic algorithms for robust average-reward Markov Decision Processes (MDPs) under contamination, total-variation (TV) distance, and Wasserstein uncertainty sets. A…

Machine Learning · Computer Science 2025-12-11 Yang Xu , Swetha Ganesh , Vaneet Aggarwal

Deep learning regularization techniques, such as dropout, layer normalization, or weight decay, are widely adopted in the construction of modern artificial neural networks, often resulting in more robust training processes and improved…

Machine Learning · Computer Science 2024-11-22 Denis Tarasov , Anja Surina , Caglar Gulcehre

We introduce a reinforcement learning method for a class of non-Markov systems; our approach extends the actor-critic framework given by Rose et al. [New J. Phys. 23 013013 (2021)] for obtaining scaled cumulant generating functions…

Statistical Mechanics · Physics 2026-03-09 Venkata D. Pamulaparthy , Rosemary J. Harris