English
Related papers

Related papers: Generative Actor-Critic: An Off-policy Algorithm U…

200 papers

Many policy gradient methods are variants of Actor-Critic (AC), where a value function (critic) is learned to facilitate updating the parameterized policy (actor). The update to the actor involves a log-likelihood update weighted by the…

Machine Learning · Computer Science 2023-03-02 Samuel Neumann , Sungsu Lim , Ajin Joseph , Yangchen Pan , Adam White , Martha White

Reinforcement learning algorithms are typically geared towards optimizing the expected return of an agent. However, in many practical applications, low variance in the return is desired to ensure the reliability of an algorithm. In this…

Machine Learning · Computer Science 2021-02-04 Arushi Jain , Gandharv Patil , Ayush Jain , Khimya Khetarpal , Doina Precup

In this paper, we provide finite-sample convergence guarantees for an off-policy variant of the natural actor-critic (NAC) algorithm based on Importance Sampling. In particular, we show that the algorithm converges to a global optimal…

Machine Learning · Computer Science 2021-06-14 Sajad Khodadadian , Zaiwei Chen , Siva Theja Maguluri

Reinforcement learning (RL) is a fundamental methodology in autonomous driving systems, where generative policies exhibit considerable potential by leveraging their ability to model complex distributions to enhance exploration. However,…

Machine Learning · Computer Science 2026-03-04 Tianze Zhu , Yinuo Wang , Wenjun Zou , Tianyi Zhang , Likun Wang , Letian Tao , Feihong Zhang , Yao Lyu , Shengbo Eben Li

We develop a new class of model-free deep reinforcement learning algorithms for data-driven, learning-based control. Our Generalized Policy Improvement algorithms combine the policy improvement guarantees of on-policy methods with the…

Machine Learning · Computer Science 2024-10-15 James Queeney , Ioannis Ch. Paschalidis , Christos G. Cassandras

During recent years, deep reinforcement learning (DRL) has made successful incursions into complex decision-making applications such as robotics, autonomous driving or video games. Off-policy algorithms tend to be more sample-efficient than…

Machine Learning · Computer Science 2021-12-06 Jesus Bujalance Martin , Raphael Chekroun , Fabien Moutarde

Large language model (LLM) agents -- LLMs that dynamically interact with an environment over long horizons -- have become an increasingly important area of research, enabling automation in complex tasks involving tool-use, web browsing, and…

Machine Learning · Computer Science 2026-02-04 Joey Hong , Kang Liu , Zhan Ling , Jiecao Chen , Sergey Levine

We discuss the problem of decentralized multi-agent reinforcement learning (MARL) in this work. In our setting, the global state, action, and reward are assumed to be fully observable, while the local policy is protected as privacy by each…

Multiagent Systems · Computer Science 2021-11-02 Kuo Li , Qing-Shan Jia

Generative control policies (GCPs), such as diffusion- and flow-based control policies, have emerged as effective parameterizations for robot learning. This work introduces Off-policy Generative Policy Optimization (OGPO), a…

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

On-policy deep reinforcement learning remains a dominant paradigm for continuous control, yet standard implementations rely on Gaussian actors and relatively shallow MLP policies, often leading to brittle optimization when gradients are…

Machine Learning · Computer Science 2026-02-02 Yuexin Bian , Jie Feng , Tao Wang , Yijiang Li , Sicun Gao , Yuanyuan Shi

We present an off-policy actor-critic algorithm for Reinforcement Learning (RL) that combines ideas from gradient-free optimization via stochastic search with learned action-value function. The result is a simple procedure consisting of…

The option framework has shown great promise by automatically extracting temporally-extended sub-tasks from a long-horizon task. Methods have been proposed for concurrently learning low-level intra-option policies and high-level option…

Artificial Intelligence · Computer Science 2020-06-26 Chenghao Li , Xiaoteng Ma , Chongjie Zhang , Jun Yang , Li Xia , Qianchuan Zhao

The Soft Actor-Critic (SAC) algorithm with a Gaussian policy has become a mainstream implementation for realizing the Maximum Entropy Reinforcement Learning (MaxEnt RL) objective, which incorporates entropy maximization to encourage…

Machine Learning · Computer Science 2025-06-09 Xiaoyi Dong , Jian Cheng , Xi Sheryl Zhang

Model-free deep reinforcement learning (RL) algorithms have achieved tremendous success on a range of challenging tasks. However, safety concerns remain when these methods are deployed on real-world applications, necessitating risk-aware…

Machine Learning · Computer Science 2026-02-10 Alonso Granados , Jason Pacheco

Gaussian policies have dominated continuous control in deep reinforcement learning (RL), yet they suffer from a fundamental mismatch: their unbounded support requires ad-hoc squashing functions that distort the geometry of bounded action…

Artificial Intelligence · Computer Science 2026-01-30 Zhihao Lin

Optimization of parameterized policies for reinforcement learning (RL) is an important and challenging problem in artificial intelligence. Among the most common approaches are algorithms based on gradient ascent of a score function…

Machine Learning · Computer Science 2020-06-15 Sriram Srinivasan , Marc Lanctot , Vinicius Zambaldi , Julien Perolat , Karl Tuyls , Remi Munos , Michael Bowling

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

In this paper, we discuss the deterministic policy gradient using the Actor-Critic methods based on the linear compatible advantage function approximator, where the input spaces are continuous. When the policy is restricted by hard…

Systems and Control · Electrical Eng. & Systems 2021-04-07 Arash Bahari Kordabad , Hossein Nejatbakhsh Esfahani , Sebastien Gros

The class of deep deterministic off-policy algorithms is effectively applied to solve challenging continuous control problems. Current approaches commonly utilize random noise as an exploration method, which has several drawbacks, including…

Machine Learning · Computer Science 2024-05-07 Igor Kuznetsov