English
Related papers

Related papers: You May Not Need Ratio Clipping in PPO

200 papers

Reinforcement learning (RL) has become a powerful paradigm for optimizing large language models (LLMs) to handle complex reasoning tasks. A core challenge in this process lies in managing policy entropy, which reflects the balance between…

Machine Learning · Computer Science 2026-04-24 Zhenpeng Su , Leiyu Pan , Minxuan Lv , Yuntao Li , Wenping Hu , Fuzheng Zhang , Kun Gai , Guorui Zhou

Post-training with reinforcement learning (RL) has recently shown strong promise for advancing multimodal agents beyond supervised imitation. However, RL remains limited by poor data efficiency, particularly in settings where interaction…

Machine Learning · Computer Science 2026-03-05 Chengxuan Lu , Zhenquan Zhang , Shukuan Wang , Qunzhi Lin , Baigui Sun , Yang Liu

On-policy reinforcement learning (RL) algorithms are widely used for their strong asymptotic performance and training stability, but they struggle to scale with larger batch sizes, as additional parallel environments yield redundant data…

Machine Learning · Computer Science 2025-11-13 Jianren Wang , Yifan Su , Abhinav Gupta , Deepak Pathak

Enhancing the reasoning capabilities of large language models effectively using reinforcement learning (RL) remains a crucial challenge. Existing approaches primarily adopt two contrasting advantage estimation granularities: token-level…

Machine Learning · Computer Science 2025-10-22 Yiran Guo , Lijie Xu , Jie Liu , Dan Ye , Shuang Qiu

This paper introduces two novel modifications to the Dynamic sAmpling Policy Optimization (DAPO) algorithm [1], approached from a mixed-policy perspective. Standard policy gradient methods can suffer from instability and sample…

Machine Learning · Computer Science 2025-08-20 Hongze Tan , Yuchen Li

Proximal Policy Optimization (PPO) is a highly popular policy-based deep reinforcement learning (DRL) approach. However, we observe that the homogeneous exploration process in PPO could cause an unexpected stability issue in the training…

Machine Learning · Computer Science 2022-12-14 Qisheng Zhang , Zhen Guo , Audun Jøsang , Lance M. Kaplan , Feng Chen , Dong H. Jeong , Jin-Hee Cho

Proximal policy optimization (PPO) approximates the trust region update using multiple epochs of clipped SGD. Each epoch may drift further from the natural gradient direction, creating path-dependent noise. To understand this drift, we can…

Machine Learning · Computer Science 2026-03-16 Zelal Su , Mustafaoglu , Sungyoung Lee , Eshan Balachandar , Risto Miikkulainen , Keshav Pingali

Safe reinforcement learning (safe RL) aims to respect safety requirements while optimizing long-term performance. In many practical applications, however, the problem involves an infinite number of constraints, known as semi-infinite safe…

Machine Learning · Computer Science 2025-11-07 Jiaming Zhang , Yujie Yang , Haoning Wang , Liping Zhang , Shengbo Eben Li

Multi-Agent Proximal Policy Optimization (MAPPO) is a variant of the Proximal Policy Optimization (PPO) algorithm, specifically tailored for multi-agent reinforcement learning (MARL). MAPPO optimizes cooperative multi-agent settings by…

Machine Learning · Computer Science 2026-05-14 Changha Lee , Gyusang Cho

Trust region policy optimization (TRPO) is a popular and empirically successful policy search algorithm in Reinforcement Learning (RL) in which a surrogate problem, that restricts consecutive policies to be 'close' to one another, is…

Machine Learning · Computer Science 2019-12-13 Lior Shani , Yonathan Efroni , Shie Mannor

To reach high performance with deep learning, hyperparameter optimization (HPO) is essential. This process is usually time-consuming due to costly evaluations of neural networks. Early discarding techniques limit the resources granted to…

Machine Learning · Computer Science 2024-04-08 Romain Egele , Felix Mohr , Tom Viering , Prasanna Balaprakash

We propose a framework for online meta-optimization of parameters that govern optimization, called Amortized Proximal Optimization (APO). We first interpret various existing neural network optimizers as approximate stochastic proximal point…

Machine Learning · Computer Science 2022-03-02 Juhan Bae , Paul Vicol , Jeff Z. HaoChen , Roger Grosse

Hyperparameter optimization (HPO) is generally treated as a bi-level optimization problem that involves fitting a (probabilistic) surrogate model to a set of observed hyperparameter responses, e.g. validation loss, and consequently…

Machine Learning · Computer Science 2021-10-18 Hadi S. Jomaa , Jonas Falkner , Lars Schmidt-Thieme

In real-world decision making tasks, it is critical for data-driven reinforcement learning methods to be both stable and sample efficient. On-policy methods typically generate reliable policy improvement throughout training, while…

Machine Learning · Computer Science 2021-11-02 James Queeney , Ioannis Ch. Paschalidis , Christos G. Cassandras

Group-Relative Policy Optimization (GRPO) has emerged as the standard for training reasoning capabilities in large language models through reinforcement learning. By estimating advantages using group-mean rewards rather than a learned…

Artificial Intelligence · Computer Science 2026-03-06 Anisha Garg , Claire Zhang , Nishit Neema , David Bick , Ganesh Venkatesh , Joel Hestness

In sequence generation task, many works use policy gradient for model optimization to tackle the intractable backpropagation issue when maximizing the non-differentiable evaluation metrics or fooling the discriminator in adversarial…

Computation and Language · Computer Science 2018-08-27 Yi-Lin Tuan , Jinzhi Zhang , Yujia Li , Hung-yi Lee

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

In various game scenarios, selecting a fixed number of targets from multiple enemy units is an extremely challenging task. This difficulty stems from the complex relationship between the threat levels of enemy units and their feature…

Machine Learning · Computer Science 2025-04-28 Wuzhou Sun , Siyi Li , Qingxiang Zou , Zixing Liao

The recent remarkable progress of deep reinforcement learning (DRL) stands on regularization of policy for stable and efficient learning. A popular method, named proximal policy optimization (PPO), has been introduced for this purpose. PPO…

Machine Learning · Computer Science 2023-07-04 Taisuke Kobayashi

Reinforcement learning (RL) plays an increasingly important role in enhancing the reasoning capabilities of large language models (LLMs), yet stable and performant policy optimization remains challenging. Token-level importance ratios often…

Machine Learning · Computer Science 2025-12-02 Chang Gao , Chujie Zheng , Xiong-Hui Chen , Kai Dang , Shixuan Liu , Bowen Yu , An Yang , Shuai Bai , Jingren Zhou , Junyang Lin