English
Related papers

Related papers: Proximal Policy Optimization with Relative Pearson…

200 papers

Direct Preference Optimization (DPO) has become a widely used training method for the instruction fine-tuning of large language models (LLMs). In this work, we explore an under-investigated aspect of DPO - its dependency on the reference…

Computation and Language · Computer Science 2024-08-23 Yixin Liu , Pengfei Liu , Arman Cohan

Advances in reinforcement learning (RL) often rely on massive compute resources and remain notoriously sample inefficient. In contrast, the human brain is able to efficiently learn effective control strategies using limited resources. This…

Machine Learning · Computer Science 2024-01-30 Burcu Küçükoğlu , Walraaf Borkent , Bodo Rueckauer , Nasir Ahmad , Umut Güçlü , Marcel van Gerven

In this paper, we study offline preference-based reinforcement learning (PbRL), where learning is based on pre-collected preference feedback over pairs of trajectories. While offline PbRL has demonstrated remarkable empirical success,…

Machine Learning · Computer Science 2025-06-04 Hyungkyu Kang , Min-hwan Oh

Recent advancements in Large Reasoning Models (LRMs), exemplified by DeepSeek-R1, have underscored the potential of scaling inference-time compute through Group Relative Policy Optimization (GRPO). However, GRPO frequently suffers from…

Artificial Intelligence · Computer Science 2026-02-09 Yu Zhao , Fan Jiang , Tianle Liu , Bo Zeng , Yu Liu , Longyue Wang , Weihua Luo

Despite Proximal Policy Optimization (PPO) dominating policy gradient methods -- from robotic control to game AI -- its static trust region forces a brittle trade-off: aggressive clipping stifles early exploration, while late-stage updates…

Machine Learning · Computer Science 2025-05-26 Ben Rahman

Proximal Policy Optimization (PPO) is widely used in continuous control due to its robustness and stable training, yet it remains sample-inefficient in tasks with expensive interactions and high-dimensional action spaces. This paper…

Machine Learning · Computer Science 2025-12-16 Tianci Gao , Konstantin A. Neusypin , Dmitry D. Dmitriev , Bo Yang , Shengren Rao

Reinforcement Learning (RL) has achieved remarkable success in sequential decision tasks. However, recent studies have revealed the vulnerability of RL policies to different perturbations, raising concerns about their effectiveness and…

Machine Learning · Computer Science 2025-07-08 Buqing Nie , Yangqing Fu , Jingtian Ji , Yue Gao

Policy optimization (PO) is a key ingredient for reinforcement learning (RL). For control design, certain constraints are usually enforced on the policies to optimize, accounting for either the stability, robustness, or safety concerns on…

Optimization and Control · Mathematics 2021-02-16 Kaiqing Zhang , Bin Hu , Tamer Başar

Balancing exploration and exploitation during reinforcement learning fine-tuning of generative models presents a critical challenge, as existing approaches rely on fixed divergence regularization that creates an inherent dilemma: strong…

Machine Learning · Computer Science 2025-10-22 Jiajun Fan , Tong Wei , Chaoran Cheng , Yuxin Chen , Ge Liu

Deep reinforcement learning (RL) uses model-free techniques to optimize task-specific control policies. Despite having emerged as a promising approach for complex problems, RL is still hard to use reliably for real-world applications. Apart…

Robotics · Computer Science 2020-02-25 Siddhant Gangapurwala , Alexander Mitchell , Ioannis Havoutis

The policy gradient method enjoys the simplicity of the objective where the agent optimizes the cumulative reward directly. Moreover, in the continuous action domain, parameterized distribution of action distribution allows easy control of…

Machine Learning · Computer Science 2022-12-16 Md Masudur Rahman , Yexiang Xue

Despite superior performance in many situations, deep neural networks are often vulnerable to adversarial examples and distribution shifts, limiting model generalization ability in real-world applications. To alleviate these problems,…

Machine Learning · Computer Science 2023-02-14 Hoang Phan , Trung Le , Trung Phung , Tuan Anh Bui , Nhat Ho , Dinh Phung

The rapid rise of large language models (LLMs) has unlocked many applications but also underscores the challenge of aligning them with diverse values and preferences. Direct Preference Optimization (DPO) is central to alignment but…

Programmatic reinforcement learning (PRL) offers an interpretable alternative to deep reinforcement learning by representing policies as human-readable and -editable programs. While gradient-based methods have been developed to optimize…

Machine Learning · Computer Science 2026-05-19 Chengpeng Hu , Yingqian Zhang , Hendrik Baier

Uncertainties in transition dynamics pose a critical challenge in reinforcement learning (RL), often resulting in performance degradation of trained policies when deployed on hardware. Many robust RL approaches follow two strategies:…

Machine Learning · Computer Science 2026-01-29 Xulin Chen , Ruipeng Liu , Zhenyu Gan , Garrett E. Katz

With dynamic pricing on the rise, firms are using sophisticated algorithms for price determination. These algorithms are often non-interpretable and there has been a recent interest in their seemingly emergent ability to tacitly collude…

Computer Science and Game Theory · Computer Science 2024-10-25 Pravesh Koirala , Forrest Laine

Deep Reinforcement Learning (DRL) has been successfully applied in several research domains such as robot navigation and automated video game playing. However, these methods require excessive computation and interaction with the…

Machine Learning · Computer Science 2020-04-07 Ayberk Aydın , Elif Surer

The Group Relative Policy Optimization (GRPO), a reinforcement learning method used to fine-tune large language models (LLMs), has proved its effectiveness in practical applications such as DeepSeek-R1. It raises a question whether GRPO can…

Machine Learning · Computer Science 2025-11-20 Yanchen Xu , Ziheng Jiao , Hongyuan Zhang , Xuelong Li

We propose a new sample-efficient methodology, called Supervised Policy Update (SPU), for deep reinforcement learning. Starting with data generated by the current policy, SPU formulates and solves a constrained optimization problem in the…

Machine Learning · Computer Science 2018-12-27 Quan Vuong , Yiming Zhang , Keith W. Ross

Safe reinforcement learning (RL) aims to learn policies that satisfy certain constraints before deploying them to safety-critical applications. Previous primal-dual style approaches suffer from instability issues and lack optimality…

Machine Learning · Computer Science 2022-06-20 Zuxin Liu , Zhepeng Cen , Vladislav Isenbaev , Wei Liu , Zhiwei Steven Wu , Bo Li , Ding Zhao