English
Related papers

Related papers: Revisiting stochastic off-policy action-value grad…

200 papers

We propose two policy gradient algorithms for solving the problem of control in an off-policy reinforcement learning (RL) context. Both algorithms incorporate a smoothed functional (SF) based gradient estimation scheme. The first algorithm…

Machine Learning · Computer Science 2024-06-25 Nithia Vijayan , Prashanth L. A

Reinforcement learning (RL) algorithms have been successfully applied to a range of challenging sequential decision making and control tasks. In this paper, we classify RL into direct and indirect RL according to how they seek the optimal…

Machine Learning · Computer Science 2021-05-12 Yang Guan , Shengbo Eben Li , Jingliang Duan , Jie Li , Yangang Ren , Qi Sun , Bo Cheng

Off-policy deep reinforcement learning (RL) algorithms are incapable of learning solely from batch offline data without online interactions with the environment, due to the phenomenon known as \textit{extrapolation error}. This is often due…

Machine Learning · Computer Science 2019-12-03 Riashat Islam , Komal K. Teru , Deepak Sharma , Joelle Pineau

Designing off-policy reinforcement learning algorithms is typically a very challenging task, because a desirable iteration update often involves an expectation over an on-policy distribution. Prior off-policy actor-critic (AC) algorithms…

Machine Learning · Computer Science 2021-07-20 Tengyu Xu , Zhuoran Yang , Zhaoran Wang , Yingbin Liang

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

Developing accurate off-policy estimators is crucial for both evaluating and optimizing for new policies. The main challenge in off-policy estimation is the distribution shift between the logging policy that generates data and the target…

Machine Learning · Computer Science 2023-10-25 Noveen Sachdeva , Lequn Wang , Dawen Liang , Nathan Kallus , Julian McAuley

With the increasing pace of automation, modern robotic systems need to act in stochastic, non-stationary, partially observable environments. A range of algorithms for finding parameterized policies that optimize for long-term average…

Machine Learning · Computer Science 2019-09-04 David Nass , Boris Belousov , Jan Peters

Policy gradient methods have enjoyed great success in deep reinforcement learning but suffer from high variance of gradient estimates. The high variance problem is particularly exasperated in problems with long horizons or high-dimensional…

Machine Learning · Computer Science 2018-03-21 Cathy Wu , Aravind Rajeswaran , Yan Duan , Vikash Kumar , Alexandre M Bayen , Sham Kakade , Igor Mordatch , Pieter Abbeel

Constrained Reinforcement Learning (CRL) addresses sequential decision-making problems where agents are required to achieve goals by maximizing the expected return while meeting domain-specific constraints. In this setting, policy-based…

Machine Learning · Computer Science 2025-06-09 Alessandro Montenegro , Leonardo Cesani , Marco Mussi , Matteo Papini , Alberto Maria Metelli

Continuous-time Markov decision processes are an important class of models in a wide range of applications, ranging from cyber-physical systems to synthetic biology. A central problem is how to devise a policy to control the system in order…

Systems and Control · Computer Science 2016-06-01 Ezio Bartocci , Luca Bortolussi , Tomǎš Brázdil , Dimitrios Milios , Guido Sanguinetti

We consider policy gradient methods for stochastic optimal control problem in continuous time. In particular, we analyze the gradient flow for the control, viewed as a continuous time limit of the policy gradient method. We prove the global…

Optimization and Control · Mathematics 2025-04-15 Mo Zhou , Jianfeng Lu

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

We propose expected policy gradients (EPG), which unify stochastic policy gradients (SPG) and deterministic policy gradients (DPG) for reinforcement learning. Inspired by expected sarsa, EPG integrates across the action when estimating the…

Machine Learning · Statistics 2018-04-17 Kamil Ciosek , Shimon Whiteson

In the framework of Markov Decision Processes, off-policy learning, that is the problem of learning a linear approximation of the value function of some fixed policy from one trajectory possibly generated by some other policy. We briefly…

Artificial Intelligence · Computer Science 2013-04-16 Matthieu Geist , Bruno Scherrer

Monotonic policy improvement and off-policy learning are two main desirable properties for reinforcement learning algorithms. In this paper, by lower bounding the performance difference of two policies, we show that the monotonic policy…

Artificial Intelligence · Computer Science 2017-11-02 Ryo Iwaki , Minoru Asada

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

Most prior approaches to offline reinforcement learning (RL) have taken an iterative actor-critic approach involving off-policy evaluation. In this paper we show that simply doing one step of constrained/regularized policy improvement using…

Machine Learning · Computer Science 2021-12-06 David Brandfonbrener , William F. Whitney , Rajesh Ranganath , Joan Bruna

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

Policy gradient methods in actor-critic reinforcement learning (RL) have become perhaps the most promising approaches to solving continuous optimal control problems. However, the trial-and-error nature of RL and the inherent randomness…

Machine Learning · Computer Science 2024-04-19 Ruofan Wu , Junmin Zhong , Jennie Si

The off-policy learning paradigm allows for recommender systems and general ranking applications to be framed as decision-making problems, where we aim to learn decision policies that optimize an unbiased offline estimate of an online…

Machine Learning · Computer Science 2024-08-15 Shashank Gupta , Olivier Jeunen , Harrie Oosterhuis , Maarten de Rijke