English
Related papers

Related papers: Mitigating Off-Policy Bias in Actor-Critic Methods…

200 papers

We introduce a one-step generative policy for offline reinforcement learning that maps noise directly to actions via a residual reformulation of MeanFlow, making it compatible with Q-learning. While one-step Gaussian policies enable fast…

Machine Learning · Computer Science 2025-11-18 Zeyuan Wang , Da Li , Yulin Chen , Ye Shi , Liang Bai , Tianyuan Yu , Yanwei Fu

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 methods have shown success in learning control policies for high-dimensional dynamical systems. Their biggest downside is the amount of exploration they require before yielding high-performing policies. In a lifelong…

Machine Learning · Computer Science 2020-10-23 Jorge A. Mendez , Boyu Wang , Eric Eaton

Reinforcement learning (RL) in low-data and risk-sensitive domains requires performant and flexible deployment policies that can readily incorporate constraints during deployment. One such class of policies are the semi-parametric H-step…

Machine Learning · Computer Science 2021-10-07 Harshit Sikchi , Wenxuan Zhou , David Held

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

Off-policy learning is a framework for evaluating and optimizing policies without deploying them, from data collected by another policy. Real-world environments are typically non-stationary and the offline learned policies should adapt to…

Machine Learning · Computer Science 2021-04-06 Joey Hong , Branislav Kveton , Manzil Zaheer , Yinlam Chow , Amr Ahmed

A central challenge to applying many off-policy reinforcement learning algorithms to real world problems is the variance introduced by importance sampling. In off-policy learning, the agent learns about a different policy than the one being…

Machine Learning · Computer Science 2022-06-20 Eric Graves , Sina Ghiassian

A variety of theoretically-sound policy gradient algorithms exist for the on-policy setting due to the policy gradient theorem, which provides a simplified form for the gradient. The off-policy setting, however, has been less clear due to…

Machine Learning · Computer Science 2023-04-17 Eric Graves , Ehsan Imani , Raksha Kumaraswamy , Martha White

Reinforcement learning holds the promise of enabling autonomous robots to learn large repertoires of behavioral skills with minimal human intervention. However, robotic applications of reinforcement learning often compromise the autonomy of…

Robotics · Computer Science 2016-11-24 Shixiang Gu , Ethan Holly , Timothy Lillicrap , Sergey Levine

In this paper we revisit the method of off-policy corrections for reinforcement learning (COP-TD) pioneered by Hallak et al. (2017). Under this method, online updates to the value function are reweighted to avoid divergence issues typical…

Machine Learning · Computer Science 2019-01-29 Carles Gelada , Marc G. Bellemare

In this paper, we study the convergence properties of off-policy policy improvement algorithms with state-action density ratio correction under function approximation setting, where the objective function is formulated as a max-max-min…

Machine Learning · Computer Science 2022-02-15 Jiawei Huang , Nan Jiang

Current model-based reinforcement learning approaches use the model simply as a learned black-box simulator to augment the data for policy optimization or value function learning. In this paper, we show how to make more effective use of the…

Machine Learning · Computer Science 2020-05-19 Ignasi Clavera , Violet Fu , Pieter Abbeel

To estimate the value functions of policies from exploratory data, most model-free off-policy algorithms rely on importance sampling, where the use of importance sampling ratios often leads to estimates with severe variance. It is thus…

Machine Learning · Computer Science 2017-02-13 Ashique Rupam Mahmood , Huizhen Yu , Richard S. Sutton

Recently, robust reinforcement learning (RL) methods designed to handle adversarial input observations have received significant attention, motivated by RL's inherent vulnerabilities. While existing approaches have demonstrated reasonable…

Machine Learning · Computer Science 2025-06-23 Kosuke Nakanishi , Akihiro Kubo , Yuji Yasui , Shin Ishii

A great variety of off-policy learning algorithms exist in the literature, and new breakthroughs in this area continue to be made, improving theoretical understanding and yielding state-of-the-art reinforcement learning algorithms. In this…

Machine Learning · Computer Science 2020-07-31 Mark Rowland , Will Dabney , Rémi Munos

Reinforcement learning (RL) approaches for Large Language Models (LLMs) frequently use on-policy algorithms, such as PPO or GRPO. However, policy lag from distributed training architectures and differences between the training and inference…

Machine Learning · Computer Science 2026-03-03 Daniel Ritter , Owen Oertell , Bradley Guo , Jonathan Chang , Kianté Brantley , Wen Sun

Off-policy, value-based reinforcement learning methods such as Q-learning are appealing because they can learn from arbitrary experience, including data collected by older policies or other agents. In practice, however, bootstrapping makes…

Artificial Intelligence · Computer Science 2026-05-12 Armaan A. Abraham , Lucy Xiaoyang Shi , Chelsea Finn

We propose the first boosting algorithm for off-policy learning from logged bandit feedback. Unlike existing boosting methods for supervised learning, our algorithm directly optimizes an estimate of the policy's expected reward. We analyze…

Machine Learning · Computer Science 2023-05-03 Ben London , Levi Lu , Ted Sandler , Thorsten Joachims

We study the problem of online learning in adversarial bandit problems under a partial observability model called off-policy feedback. In this sequential decision making problem, the learner cannot directly observe its rewards, but instead…

Machine Learning · Computer Science 2022-07-20 Germano Gabbianelli , Matteo Papini , Gergely Neu

In this work, we take a fresh look at some old and new algorithms for off-policy, return-based reinforcement learning. Expressing these in a common form, we derive a novel algorithm, Retrace($\lambda$), with three desired properties: (1) it…

Machine Learning · Computer Science 2016-11-09 Rémi Munos , Tom Stepleton , Anna Harutyunyan , Marc G. Bellemare
‹ Prev 1 4 5 6 7 8 10 Next ›