English
Related papers

Related papers: DFPO: Scaling Value Modeling via Distributional Fl…

200 papers

Large language models are increasingly post-trained with reinforcement learning in verifiable domains such as code and math. Yet, current methods for reinforcement learning with verifiable rewards (RLVR) learn only from a scalar outcome…

Improving the reasoning capabilities of diffusion-based large language models (dLLMs) through reinforcement learning (RL) remains an open problem. The intractability of dLLMs likelihood function necessitates approximating the current, old,…

Machine Learning · Computer Science 2026-02-17 Xiaohang Tang , Rares Dolga , Sangwoong Yoon , Ilija Bogunovic

Several applications in the scientific simulation of physical systems can be formulated as control/optimization problems. The computational models for such systems generally contain hyperparameters, which control solution fidelity and…

Computational Physics · Physics 2020-12-09 Suraj Pawar , Romit Maulik

Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), as the widely employed policy based reinforcement learning (RL) methods, are prone to converge to a sub-optimal solution as they limit the policy representation…

Machine Learning · Computer Science 2020-06-16 Jun Song , Chaoyue Zhao

Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to single-task optimization. Extending RL to multiple tasks is challenging: joint…

Machine Learning · Computer Science 2026-05-15 Quanhao Li , Junqiu Yu , Kaixun Jiang , Yujie Wei , Zhen Xing , Pandeng Li , Ruihang Chu , Shiwei Zhang , Yu Liu , Zuxuan Wu

Large language models (LLMs) trained via pretraining and supervised fine-tuning (SFT) can still produce harmful and misaligned outputs, or struggle in domains like math and coding. Reinforcement learning (RL)-based post-training methods,…

Computation and Language · Computer Science 2026-05-19 Zhichao Wang , Kiran Ramnath , Bin Bi , Shiva Kumar Pentyala , Sougata Chaudhuri , Shubham Mehrotra , Zixu , Zhu , Xiang-Bo Mao , Sitaram Asur , Na , Cheng

Can we use reinforcement learning to learn general-purpose policies that can perform a wide range of different tasks, resulting in flexible and reusable skills? Contextual policies provide this capability in principle, but the…

Machine Learning · Computer Science 2021-04-26 Soroush Nasiriany , Vitchyr H. Pong , Ashvin Nair , Alexander Khazatsky , Glen Berseth , Sergey Levine

This paper presents Post-Decision Proximal Policy Optimization (PDPPO), a novel variation of the leading deep reinforcement learning method, Proximal Policy Optimization (PPO). The PDPPO state transition process is divided into two steps: a…

Deep Reinforcement Learning (RL) agents often learn policies that achieve the same episodic return yet behave very differently, due to a combination of environmental (random transitions, initial conditions, reward noise) and algorithmic…

Machine Learning · Computer Science 2026-01-06 Dennis Jabs , Aditya Mohan , Marius Lindauer

Generative models such as diffusion have been employed as world models in offline reinforcement learning to generate synthetic data for more effective learning. Existing work either generates diffusion models one-time prior to training or…

Machine Learning · Computer Science 2024-05-31 Zeyu Fang , Tian Lan

Reinforcement Learning (RL) has proven highly effective for autoregressive language models, but adapting these methods to diffusion large language models (dLLMs) presents fundamental challenges. The core difficulty lies in likelihood…

Computation and Language · Computer Science 2025-12-04 Jingyang Ou , Jiaqi Han , Minkai Xu , Shaoxuan Xu , Jianwen Xie , Stefano Ermon , Yi Wu , Chongxuan Li

Optimizing discrete diffusion model (DDM) with rewards remains a challenge: the non-autoregressive paradigm makes importance sampling intractable and rollout complex, puzzling reinforcement learning methods such as Group Relative Policy…

Artificial Intelligence · Computer Science 2025-10-06 Tianren Ma , Mu Zhang , Yibing Wang , Qixiang Ye

The success of Deepseek-R1 has drawn the LLM community's attention to reinforcement learning (RL) methods like GRPO. However, such rule-based 0/1 outcome reward methods lack the capability to regulate the intermediate reasoning processes…

Artificial Intelligence · Computer Science 2025-05-26 Muzhi Dai , Shixuan Liu , Qingyi Si

Reinforcement learning has significantly enhanced the reasoning capabilities of Large Language Models (LLMs) in complex problem-solving tasks. Recently, the introduction of DeepSeek R1 has inspired a surge of interest in leveraging…

Machine Learning · Computer Science 2025-08-07 Jinghang Han , Jiawei Chen , Hang Shao , Hao Ma , Mingcheng Li , Xintian Shen , Lihao Zheng , Wei Chen , Tao Wei , Lihua Zhang

In partially observable (PO) environments, deep reinforcement learning (RL) agents often suffer from unsatisfactory performance, since two problems need to be tackled together: how to extract information from the raw observations to solve…

Machine Learning · Computer Science 2019-12-25 Dongqi Han , Kenji Doya , Jun Tani

Dynamic diagnosis is desirable when medical tests are costly or time-consuming. In this work, we use reinforcement learning (RL) to find a dynamic policy that selects lab test panels sequentially based on previous observations, ensuring…

Machine Learning · Computer Science 2023-03-01 Zheng Yu , Yikuan Li , Joseph Kim , Kaixuan Huang , Yuan Luo , Mengdi Wang

Direct Preference Optimization (DPO) has become a popular method for fine-tuning large language models (LLMs) due to its stability and simplicity. However, it is also known to be sensitive to noise in the data and prone to overfitting.…

Machine Learning · Computer Science 2025-10-28 Cheol Woo Kim , Shresth Verma , Mauricio Tec , Milind Tambe

Since the release of Deepseek-R1, reinforcement learning with verifiable rewards (RLVR) has become a central approach for training large language models (LLMs) on reasoning tasks. Recent work has largely focused on modifying loss functions…

Machine Learning · Computer Science 2025-10-03 Weizhe Chen , Sven Koenig , Bistra Dilkina

Direct Preference Optimization (DPO) has emerged as a predominant alignment method for diffusion models, facilitating off-policy training without explicit reward modeling. However, its reliance on large-scale, high-quality human preference…

Computer Vision and Pattern Recognition · Computer Science 2026-02-09 Khiem Pham , Quang Nguyen , Tung Nguyen , Jingsen Zhu , Michele Santacatterina , Dimitris Metaxas , Ramin Zabih

Instability and slowness are two main problems in deep reinforcement learning. Even if proximal policy optimization (PPO) is the state of the art, it still suffers from these two problems. We introduce an improved algorithm based on…

Machine Learning · Computer Science 2019-10-01 Zhenyu Zhang , Xiangfeng Luo , Tong Liu , Shaorong Xie , Jianshu Wang , Wei Wang , Yang Li , Yan Peng