English
Related papers

Related papers: Multi Pseudo Q-learning Based Deterministic Policy…

200 papers

We propose a novel independent and payoff-based learning framework for stochastic games that is model-free, game-agnostic, and gradient-free. The learning dynamics follow a best-response-type actor-critic architecture, where agents update…

Machine Learning · Computer Science 2026-02-03 Ahmed Said Donmez , Yuksel Arslantas , Muhammed O. Sayin

This paper develops a policy learning method for tuning a pre-trained policy to adapt to additional tasks without altering the original task. A method named Adaptive Policy Gradient (APG) is proposed in this paper, which combines Bellman's…

Machine Learning · Computer Science 2025-09-29 Wenjian Hao , Zehui Lu , Zihao Liang , Tianyu Zhou , Shaoshuai Mou

Autonomous Ground Vehicles (AGVs) are essential tools for a wide range of applications stemming from their ability to operate in hazardous environments with minimal human operator input. Effective motion planning is paramount for successful…

Robotics · Computer Science 2023-09-04 Shathushan Sivashangaran , Azim Eskandarian

In state of the art model-free off-policy deep reinforcement learning, a replay memory is used to store past experience and derive all network updates. Even if both state and action spaces are continuous, the replay memory only holds a…

Machine Learning · Computer Science 2020-07-16 Sabrina Hoppe , Marc Toussaint

This paper introduces Q-learning with gradient target tracking, a novel reinforcement learning framework that provides a learned continuous target update mechanism as an alternative to the conventional hard update paradigm. In the standard…

Machine Learning · Computer Science 2025-07-21 Bum Geun Park , Taeho Lee , Donghwan Lee

In this paper, a new offline actor-critic learning algorithm is introduced: Sampled Policy Gradient (SPG). SPG samples in the action space to calculate an approximated policy gradient by using the critic to evaluate the samples. This…

Artificial Intelligence · Computer Science 2018-09-18 Anton Orell Wiehe , Nil Stolt Ansó , Madalina M. Drugan , Marco A. Wiering

Optimizing dynamic risk with stochastic policies is challenging in both policy updates and value learning. The former typically requires transition perturbation, while the latter may rely on model-based approaches. To address these…

Machine Learning · Computer Science 2026-05-11 Yudong Luo , Erick Delage

Actor-critic algorithms learn an explicit policy (actor), and an accompanying value function (critic). The actor performs actions in the environment, while the critic evaluates the actor's current policy. However, despite their stability…

Artificial Intelligence · Computer Science 2019-02-08 Hélène Plisnier , Denis Steckelmacher , Diederik M. Roijers , Ann Nowé

The conservation of hydrological resources involves continuously monitoring their contamination. A multi-agent system composed of autonomous surface vehicles is proposed in this paper to efficiently monitor the water quality. To achieve a…

Artificial Intelligence · Computer Science 2024-01-10 Samuel Yanes Luis , Dmitriy Shutin , Juan Marchal Gómez , Daniel Gutiérrez Reina , Sergio Toral Marín

While deep reinforcement learning has achieved tremendous successes in various applications, most existing works only focus on maximizing the expected value of total return and thus ignore its inherent stochasticity. Such stochasticity is…

Machine Learning · Computer Science 2023-09-19 Han Zhong , Xun Deng , Ethan X. Fang , Zhuoran Yang , Zhaoran Wang , Runze Li

Policy gradient (PG) methods are successful approaches to deal with continuous reinforcement learning (RL) problems. They learn stochastic parametric (hyper)policies by either exploring in the space of actions or in the space of parameters.…

Machine Learning · Computer Science 2024-05-31 Alessandro Montenegro , Marco Mussi , Alberto Maria Metelli , Matteo Papini

This work describes a technique for active rejection of multiple independent and time-correlated stochastic disturbances for a nonlinear flexible inverted pendulum with cart system with uncertain model parameters. The control law is…

Systems and Control · Electrical Eng. & Systems 2024-04-09 Vincent W. Hill

Multi-objective optimization models that encode ordered sequential constraints provide a solution to model various challenging problems including encoding preferences, modeling a curriculum, and enforcing measures of safety. A recently…

Artificial Intelligence · Computer Science 2022-09-16 Kyle Hollins Wray , Stas Tiomkin , Mykel J. Kochenderfer , Pieter Abbeel

We study an emerging problem named "grasping the invisible" in robotic manipulation, in which a robot is tasked to grasp an initially invisible target object via a sequence of pushing and grasping actions. In this problem, pushes are needed…

Robotics · Computer Science 2020-01-30 Yang Yang , Hengyue Liang , Changhyun Choi

Policies learned via continuous actor-critic methods often exhibit erratic, high-frequency oscillations, making them unsuitable for physical deployment. Current approaches attempt to enforce smoothness by directly regularizing the policy's…

Machine Learning · Computer Science 2026-02-02 Jeong Woon Lee , Kyoleen Kwak , Daeho Kim , Hyoseok Hwang

Policy gradient methods are powerful reinforcement learning algorithms and have been demonstrated to solve many complex tasks. However, these methods are also data-inefficient, afflicted with high variance gradient estimates, and frequently…

Machine Learning · Computer Science 2019-05-15 Andreas Doerr , Michael Volpp , Marc Toussaint , Sebastian Trimpe , Christian Daniel

Effective offline RL methods require properly handling out-of-distribution actions. Implicit Q-learning (IQL) addresses this by training a Q-function using only dataset actions through a modified Bellman backup. However, it is unclear which…

Machine Learning · Computer Science 2023-05-23 Philippe Hansen-Estruch , Ilya Kostrikov , Michael Janner , Jakub Grudzien Kuba , Sergey Levine

We focus on developing efficient and reliable policy optimization strategies for robot learning with real-world data. In recent years, policy gradient methods have emerged as a promising paradigm for training control policies in simulation.…

Machine Learning · Computer Science 2023-11-07 Tyler Westenbroek , Jacob Levy , David Fridovich-Keil

We propose a new algorithm, Mean Actor-Critic (MAC), for discrete-action continuous-state reinforcement learning. MAC is a policy gradient algorithm that uses the agent's explicit representation of all action values to estimate the gradient…

Multiple autonomous underwater vehicles (multi-AUV) can cooperatively accomplish tasks that a single AUV cannot complete. Recently, multi-agent reinforcement learning has been introduced to control of multi-AUV. However, designing efficient…

Robotics · Computer Science 2024-01-23 Zheng Fang , Tianhao Chen , Dong Jiang , Zheng Zhang , Guangliang Li