English
Related papers

Related papers: RTMC: Step-Level Credit Assignment via Rollout Tre…

200 papers

Large language models (LLMs) are increasingly applied to complex reasoning tasks that require executing several complex steps before receiving any reward. Properly assigning credit to these steps is essential for enhancing model…

We tackle the Multi-task Batch Reinforcement Learning problem. Given multiple datasets collected from different tasks, we train a multi-task policy to perform well in unseen tasks sampled from the same distribution. The task identities of…

Machine Learning · Computer Science 2020-10-27 Jiachen Li , Quan Vuong , Shuang Liu , Minghua Liu , Kamil Ciosek , Keith Ross , Henrik Iskov Christensen , Hao Su

Credit assignment in Meta-reinforcement learning (Meta-RL) is still poorly understood. Existing methods either neglect credit assignment to pre-adaptation behavior or implement it naively. This leads to poor sample-efficiency during…

Machine Learning · Computer Science 2022-02-14 Jonas Rothfuss , Dennis Lee , Ignasi Clavera , Tamim Asfour , Pieter Abbeel

Recent advancements in Multimodal Large Language Models (MLLMs) have incentivized models to ``think with images'' by actively invoking visual tools during multi-turn reasoning. The common Reinforcement Learning (RL) practice of relying on…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Wenhao Yang , Yu Xia , Jinlong Huang , Shiyin Lu , Qing-Guo Chen , Zhao Xu , Weihua Luo , Kaifu Zhang , Yuchen Zhou , Xiaobo Xia , Yuanyu Wan , Lijun Zhang , Tat-Seng Chua

Reinforcement learning (RL) shows great potential for optimizing multi-vehicle cooperative driving strategies through the state-action-reward feedback loop, but it still faces challenges such as low sample efficiency. This paper proposes a…

Artificial Intelligence · Computer Science 2025-08-12 Ye Han , Lijun Zhang , Dejian Meng , Zhuang Zhang

Reinforcement learning, such as PPO and GRPO, has powered recent breakthroughs in LLM reasoning. Scaling rollout to sample more prompts enables models to selectively use higher-quality data for training, which can stabilize RL training and…

Artificial Intelligence · Computer Science 2025-06-04 Haizhong Zheng , Yang Zhou , Brian R. Bartoldson , Bhavya Kailkhura , Fan Lai , Jiawei Zhao , Beidi Chen

Standard reinforcement learning (RL) assumes that an agent can observe a reward for each state-action pair. However, in practical applications, it is often difficult and costly to collect a reward for each state-action pair. While there…

Machine Learning · Computer Science 2025-06-18 Yihan Du , Anna Winnicki , Gal Dalal , Shie Mannor , R. Srikant

Agentic reinforcement learning has enabled large language models to perform complex multi-turn planning and tool use. However, learning in long-horizon settings remains challenging due to sparse, trajectory-level outcome rewards. While…

Computation and Language · Computer Science 2026-02-04 Yubao Zhao , Weiquan Huang , Sudong Wang , Ruochen Zhao , Chen Chen , Yao Shu , Chengwei Qin

The question of how to determine which states and actions are responsible for a certain outcome is known as the credit assignment problem and remains a central research question in reinforcement learning and artificial intelligence.…

Machine Learning · Computer Science 2021-02-09 Hado van Hasselt , Sephora Madjiheurem , Matteo Hessel , David Silver , André Barreto , Diana Borsa

One major limitation to the applicability of Reinforcement Learning (RL) to many practical domains is the large number of samples required to learn an optimal policy. To address this problem and improve learning efficiency, we consider a…

Machine Learning · Computer Science 2023-08-07 Roberto Cipollone , Giuseppe De Giacomo , Marco Favorito , Luca Iocchi , Fabio Patrizi

AI agents are increasingly used to solve real-world tasks by reasoning over multi-turn user interactions and invoking external tools. However, applying reinforcement learning to such settings remains difficult: realistic objectives often…

Reinforcement learning (RL) is the dominant paradigm for post-training large language models. However, in the online, on-policy setting, rollout generation dominates the computational cost of training. Group-based policy optimization…

Machine Learning · Computer Science 2026-05-27 Woojeong Kim , Ziyi Yang , Jing Nathan Yan , Jialu Liu

Reinforcement Learning (RL) has gained substantial attention across diverse application domains and theoretical investigations. Existing literature on RL theory largely focuses on risk-neutral settings where the decision-maker learns to…

Machine Learning · Computer Science 2024-12-24 Zhengqi Wu , Renyuan Xu

Achieving safe and coordinated behavior in dynamic, constraint-rich environments remains a major challenge for learning-based control. Pure end-to-end learning often suffers from poor sample efficiency and limited reliability, while…

Systems and Control · Electrical Eng. & Systems 2025-10-10 Max Studt , Georg Schildbach

In environments with sparse or delayed rewards, reinforcement learning (RL) incurs high sample complexity due to the large number of interactions needed for learning. This limitation has motivated the use of large language models (LLMs) for…

Machine Learning · Computer Science 2026-02-23 Narjes Nourzad , Carlee Joe-Wong

Portfolio management is a fundamental problem in finance. It involves periodic reallocations of assets to maximize the expected returns within an appropriate level of risk exposure. Deep reinforcement learning (RL) has been considered a…

Computational Finance · Quantitative Finance 2022-10-05 Hui Niu , Siyuan Li , Jian Li

Experience replay is one of the most commonly used approaches to improve the sample efficiency of reinforcement learning algorithms. In this work, we propose an approach to select and replay sequences of transitions in order to accelerate…

Artificial Intelligence · Computer Science 2022-09-29 Thommen George Karimpanal , Roland Bouffanais

Existing automatic 3D image segmentation methods usually fail to meet the clinic use. Many studies have explored an interactive strategy to improve the image segmentation performance by iteratively incorporating user hints. However, the…

Computer Vision and Pattern Recognition · Computer Science 2019-11-26 Xuan Liao , Wenhao Li , Qisen Xu , Xiangfeng Wang , Bo Jin , Xiaoyun Zhang , Ya Zhang , Yanfeng Wang

In multi-task reinforcement learning (RL) under Markov decision processes (MDPs), the presence of shared latent structures among multiple MDPs has been shown to yield significant benefits to the sample efficiency compared to single-task RL.…

Machine Learning · Computer Science 2023-10-23 Ruiquan Huang , Yuan Cheng , Jing Yang , Vincent Tan , Yingbin Liang

Interpretability of AI models allows for user safety checks to build trust in these models. In particular, decision trees (DTs) provide a global view on the learned model and clearly outlines the role of the features that are critical to…

Machine Learning · Computer Science 2023-04-13 Hector Kohler , Riad Akrour , Philippe Preux