English
Related papers

Related papers: Flow Actor-Critic for Offline Reinforcement Learni…

200 papers

This paper presents the first actor-critic algorithm for off-policy reinforcement learning. Our algorithm is online and incremental, and its per-time-step complexity scales linearly with the number of learned weights. Previous work on…

Machine Learning · Computer Science 2015-03-20 Thomas Degris , Martha White , Richard S. Sutton

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

Offline reinforcement learning (RL), also known as batch RL, offers the prospect of policy optimization from large pre-recorded datasets without online environment interaction. It addresses challenges with regard to the cost of data…

Training critiquing language models to assess and provide feedback on model outputs is a promising way to improve LLMs for complex reasoning tasks. However, existing approaches typically rely on stronger supervisors for annotating critique…

Offline reinforcement learning often relies on behavior regularization that enforces policies to remain close to the dataset distribution. However, such approaches fail to distinguish between high-value and low-value actions in their…

Offline reinforcement learning (RL) aims to learn optimal policies from previously collected datasets. Recently, due to their powerful representational capabilities, diffusion models have shown significant potential as policy models for…

Machine Learning · Computer Science 2024-05-30 Tianle Zhang , Jiayi Guan , Lin Zhao , Yihang Li , Dongjiang Li , Zecui Zeng , Lei Sun , Yue Chen , Xuelong Wei , Lusong Li , Xiaodong He

A key problem in off-policy Reinforcement Learning (RL) is the mismatch, or distribution shift, between the dataset and the distribution over states and actions visited by the learned policy. This problem is exacerbated in the fully offline…

Machine Learning · Computer Science 2023-11-28 Melrose Roderick , Gaurav Manek , Felix Berkenkamp , J. Zico Kolter

Most prior approaches to offline reinforcement learning (RL) utilize \textit{behavior regularization}, typically augmenting existing off-policy actor critic algorithms with a penalty measuring divergence between the policy and the offline…

Machine Learning · Computer Science 2021-10-15 Haoran Xu , Xianyuan Zhan , Jianxiong Li , Honglei Yin

Improving the sample efficiency of reinforcement learning algorithms requires effective exploration. Following the principle of $\textit{optimism in the face of uncertainty}$ (OFU), we train a separate exploration policy to maximize the…

Machine Learning · Computer Science 2022-11-23 Jiachen Li , Shuo Cheng , Zhenyu Liao , Huayan Wang , William Yang Wang , Qinxun Bai

Offline reinforcement learning (RL) enables the agent to effectively learn from logged data, which significantly extends the applicability of RL algorithms in real-world scenarios where exploration can be expensive or unsafe. Previous works…

Machine Learning · Computer Science 2022-12-05 Yiqin Yang , Hao Hu , Wenzhe Li , Siyuan Li , Jun Yang , Qianchuan Zhao , Chongjie Zhang

Reliable value estimation serves as the cornerstone of reinforcement learning (RL) by evaluating long-term returns and guiding policy improvement, significantly influencing the convergence speed and final performance. Existing works improve…

Machine Learning · Computer Science 2025-10-28 Shan Zhong , Shutong Ding , He Diao , Xiangyu Wang , Kah Chan Teh , Bei Peng

In this paper, we propose a distributed off-policy actor critic method to solve multi-agent reinforcement learning problems. Specifically, we assume that all agents keep local estimates of the global optimal policy parameter and update…

Machine Learning · Computer Science 2019-03-25 Yan Zhang , Michael M. Zavlanos

Offline reinforcement learning (RL) is a promising approach for many control applications but faces challenges such as limited data coverage and value function overestimation. In this paper, we propose an implicit actor-critic (iAC)…

Machine Learning · Computer Science 2024-08-29 Vanshaj Khattar , Ming Jin

In safety-critical domains where online data collection is infeasible, offline reinforcement learning (RL) offers an attractive alternative but only if policies deliver high returns without incurring catastrophic lower-tail risk. Prior work…

Machine Learning · Computer Science 2025-12-09 Kai Fukazawa , Kunal Mundada , Iman Soltani

This paper presents AFU, an off-policy deep RL algorithm addressing in a new way the challenging "max-Q problem" in Q-learning for continuous action spaces, with a solution based on regression and conditional gradient scaling. AFU has an…

Machine Learning · Computer Science 2024-10-28 Nicolas Perrin-Gilbert

In reinforcement learning (RL) research, it is common to assume access to direct online interactions with the environment. However in many real-world applications, access to the environment is limited to a fixed offline dataset of logged…

Machine Learning · Computer Science 2019-11-27 Yifan Wu , George Tucker , Ofir Nachum

Offline reinforcement learning (RL) aims to learn the optimal policy from a fixed dataset generated by behavior policies without additional environment interactions. One common challenge that arises in this setting is the…

Machine Learning · Computer Science 2026-02-06 Songyuan Zhang , Oswin So , H. M. Sabbir Ahmad , Eric Yang Yu , Matthew Cleaveland , Mitchell Black , Chuchu Fan

The goal of offline reinforcement learning (RL) is to find an optimal policy given prerecorded trajectories. Many current approaches customize existing off-policy RL algorithms, especially actor-critic algorithms in which policy evaluation…

Machine Learning · Computer Science 2021-10-07 Wonjoon Goo , Scott Niekum

Score-based generative models like the diffusion model have been testified to be effective in modeling multi-modal data from image generation to reinforcement learning (RL). However, the inference process of diffusion model can be slow,…

Machine Learning · Computer Science 2024-03-18 Zihan Ding , Chi Jin

Off-Policy Actor-Critic (Off-PAC) methods have proven successful in a variety of continuous control tasks. Normally, the critic's action-value function is updated using temporal-difference, and the critic in turn provides a loss for the…

Machine Learning · Computer Science 2020-11-03 Wei Zhou , Yiying Li , Yongxin Yang , Huaimin Wang , Timothy M. Hospedales