English
Related papers

Related papers: SPAR: Support-Preserving Action Rectification

200 papers

Distributed training and increasing the gradient update frequency are practical strategies to accelerate learning and improve performance, but both exacerbate a central challenge: \textit{policy lag}, which is the mismatch between the…

A fundamental challenge in model-based offline reinforcement learning (RL) lies in the trade-off between generalization and robustness against exploitation errors in out-of-distribution (OOD) regions. While OOD samples may capture valid…

Artificial Intelligence · Computer Science 2026-05-11 Hongqiang Lin , Dongxu Zhang , Yiding Sun , Mingzhe Li , Ning Yang , Haijun Zhang

Reinforcement learning in discrete combinatorial action spaces requires searching over exponentially many joint actions to simultaneously select multiple sub-actions that form coherent combinations. Existing approaches either simplify…

Machine Learning · Computer Science 2026-01-29 Matthew Landers , Taylor W. Killian , Thomas Hartvigsen , Afsaneh Doryab

Offline reinforcement learning refers to the process of learning policies from fixed datasets, without requiring additional environment interaction. However, it often relies on well-defined reward functions, which are difficult and…

Artificial Intelligence · Computer Science 2025-10-13 Xiancheng Gao , Yufeng Shi , Wengang Zhou , Houqiang Li

High-dimensional, heterogeneous data with complex feature interactions pose significant challenges for traditional predictive modeling approaches. While Projection to Latent Structures (PLS) remains a popular technique, it struggles to…

Machine Learning · Computer Science 2025-10-21 Farwa Abbas , Hussain Ahmad , Claudia Szabo

We consider the offline reinforcement learning (RL) setting where the agent aims to optimize the policy solely from the data without further environment interactions. In offline RL, the distributional shift becomes the primary source of…

Machine Learning · Computer Science 2021-06-22 Jongmin Lee , Wonseok Jeon , Byung-Jun Lee , Joelle Pineau , Kee-Eung Kim

Reinforcement learning (RL) has emerged as a central paradigm for post-training LLM agents, yet its trajectory-level reward signal provides only coarse supervision for long-horizon interaction. On-Policy Self-Distillation (OPSD) complements…

Machine Learning · Computer Science 2026-05-15 Zhengxi Lu , Zhiyuan Yao , Zhuowen Han , Zi-Han Wang , Jinyang Wu , Qi Gu , Xunliang Cai , Weiming Lu , Jun Xiao , Yueting Zhuang , Yongliang Shen

Offline reinforcement learning (RL) provides a promising direction to exploit massive amount of offline data for complex decision-making tasks. Due to the distribution shift issue, current offline RL algorithms are generally designed to be…

Machine Learning · Computer Science 2022-10-25 Rui Yang , Chenjia Bai , Xiaoteng Ma , Zhaoran Wang , Chongjie Zhang , Lei Han

We study reinforcement learning in hybrid discrete-continuous action spaces, such as settings where the discrete component selects a regime (or index) and the continuous component optimizes within it -- a structure common in robotics,…

Machine Learning · Computer Science 2026-05-15 Matias Alvo , Daniel Russo , Yash Kanoria

We introduce Self-supervised Online Reward Shaping (SORS), which aims to improve the sample efficiency of any RL algorithm in sparse-reward environments by automatically densifying rewards. The proposed framework alternates between…

Machine Learning · Computer Science 2021-07-27 Farzan Memarian , Wonjoon Goo , Rudolf Lioutikov , Scott Niekum , Ufuk Topcu

Off-policy problems such as policy staleness and training--inference mismatch have become a major bottleneck for training stability and further exploration in LLM RL. The distribution gap between the inference and updated policies grows…

Machine Learning · Computer Science 2026-05-19 Chenlu Ye , Xuanchang Zhang , Yifan Hao , Zhou Yu , Ziji Zhang , Abhinav Gullapalli , Hao Chen , Jing Huang , Tong Zhang

Recent breakthroughs in preference alignment have significantly improved Large Language Models' ability to generate texts that align with human preferences and values. However, current alignment metrics typically emphasize the post-hoc…

Computation and Language · Computer Science 2024-10-15 Mingye Zhu , Yi Liu , Quan Wang , Junbo Guo , Zhendong Mao

Offline inverse reinforcement learning (Offline IRL) aims to recover the structure of rewards and environment dynamics that underlie observed actions in a fixed, finite set of demonstrations from an expert agent. Accurate models of…

Machine Learning · Computer Science 2024-03-01 Siliang Zeng , Chenliang Li , Alfredo Garcia , Mingyi Hong

In sequential decision-making problems, Return-Conditioned Supervised Learning (RCSL) has gained increasing recognition for its simplicity and stability in modern decision-making tasks. Unlike traditional offline reinforcement learning (RL)…

Machine Learning · Computer Science 2025-06-11 Zhishuai Liu , Yu Yang , Ruhan Wang , Pan Xu , Dongruo Zhou

The goal of offline reinforcement learning is to learn a policy from a fixed dataset, without further interactions with the environment. This setting will be an increasingly more important paradigm for real-world applications of…

Robotics · Computer Science 2020-11-17 Wenxuan Zhou , Sujay Bajracharya , David Held

Off-policy learning methods seek to derive an optimal policy directly from a fixed dataset of prior interactions. This objective presents significant challenges, primarily due to the inherent distributional shift and value function…

Machine Learning · Computer Science 2026-02-03 Arip Asadulaev , Maksim Bobrin , Salem Lahlou , Dmitry Dylov , Fakhri Karray , Martin Takac

Group Relative Policy Optimization (GRPO) is highly effective for post-training autoregressive (AR) language models, yet its direct application to diffusion large language models (dLLMs) often triggers reward collapse. We identify two…

Machine Learning · Computer Science 2026-03-10 Jianyuan Zhong , Kaibo Wang , Ding Ding , Zijin Feng , Haoli Bai , Yang Xiang , Jiacheng Sun , Qiang Xu

We introduce a novel reinforcement learning algorithm (AGRO, for Any-Generation Reward Optimization) for fine-tuning large-language models. AGRO leverages the concept of generation consistency, which states that the optimal policy satisfies…

Machine Learning · Computer Science 2025-04-01 Yunhao Tang , Taco Cohen , David W. Zhang , Michal Valko , Rémi Munos

Tabular data are fundamental in common machine learning applications, ranging from finance to genomics and healthcare. This paper focuses on tabular regression tasks, a field where deep learning (DL) methods are not consistently superior to…

Machine Learning · Computer Science 2024-12-17 Hong-Wei Wu , Wei-Yao Wang , Kuang-Da Wang , Wen-Chih Peng

Deep Reinforcement Learning (RL) methods rely on experience replay to approximate the minibatched supervised learning setting; however, unlike supervised learning where access to lots of training data is crucial to generalization,…

Machine Learning · Computer Science 2021-02-24 Brett Daley , Cameron Hickert , Christopher Amato