English
Related papers

Related papers: GPG: Generalized Policy Gradient Theorem for Trans…

200 papers

Reinforcement learning is widely used to improve the reasoning ability of large language models, especially when answers can be automatically checked. Standard GRPO-style training updates the model using only the current step, while full…

Machine Learning · Computer Science 2026-05-11 Ismam Nur Swapnil , Aranya Saha , Tanvir Ahmed Khan , Mohammad Ariful Haque , Ser-Nam Lim

Markov decision processes (MDPs) is viewed as an optimization of an objective function over certain linear operators over general function spaces. A new existence result is established for the existence of optimal policies in general MDPs,…

Machine Learning · Computer Science 2026-04-01 Abhishek Gupta , Aditya Mahajan

In this paper, we propose a new algorithm PPG (Proximal Policy Gradient), which is close to both VPG (vanilla policy gradient) and PPO (proximal policy optimization). The PPG objective is a partial variation of the VPG objective and the…

Machine Learning · Computer Science 2020-10-21 Ju-Seung Byun , Byungmoon Kim , Huamin Wang

Policy gradient methods are among the most effective methods in challenging reinforcement learning problems with large state and/or action spaces. However, little is known about even their most basic theoretical convergence properties,…

Machine Learning · Computer Science 2020-10-16 Alekh Agarwal , Sham M. Kakade , Jason D. Lee , Gaurav Mahajan

We investigate the challenge of parametrizing policies for reinforcement learning (RL) in high-dimensional continuous action spaces. Our objective is to develop a multimodal policy that overcomes limitations inherent in the commonly-used…

Machine Learning · Computer Science 2023-07-21 Zhiao Huang , Litian Liang , Zhan Ling , Xuanlin Li , Chuang Gan , Hao Su

Reinforcement learning has become a powerful paradigm for post-training large language model agents, yet credit assignment in multi-turn environments remains a challenge. Agents often receive sparse, trajectory-level rewards only at the end…

Computation and Language · Computer Science 2026-05-14 Siyuan Zhu , Chao Yu , Rongxin Yang , Zongkai Liu , Jinjun Hu , Qiwen Chen , Yibo Zhang

Group Relative Policy Optimization (GRPO) has shown promise in discrete action spaces by eliminating value function dependencies through group-based advantage estimation. However, its application to continuous control remains unexplored,…

Robotics · Computer Science 2025-07-29 Rajat Khanda , Mohammad Baqar , Sambuddha Chakrabarti , Satyasaran Changdar

A longstanding objective in classical planning is to synthesize policies that generalize across multiple problems from the same domain. In this work, we study generalized policy search-based methods with a focus on the score function used…

Artificial Intelligence · Computer Science 2022-04-25 Ryan Yang , Tom Silver , Aidan Curtis , Tomas Lozano-Perez , Leslie Pack Kaelbling

While reinforcement learning methods have delivered remarkable results in a number of settings, generalization, i.e., the ability to produce policies that generalize in a reliable and systematic way, has remained a challenge. The problem of…

Artificial Intelligence · Computer Science 2025-12-23 Simon Ståhlberg , Blai Bonet , Hector Geffner

Gradient-based approaches to direct policy search in reinforcement learning have received much recent attention as a means to solve problems of partial observability and to avoid some of the problems associated with policy degradation in…

Artificial Intelligence · Computer Science 2019-11-18 Jonathan Baxter , Peter L. Bartlett

In this paper, we consider the problem of learning policies to control a large number of homogeneous robots. To this end, we propose a new algorithm we call Graph Policy Gradients (GPG) that exploits the underlying graph symmetry among the…

Robotics · Computer Science 2019-12-03 Arbaaz Khan , Ekaterina Tolstaya , Alejandro Ribeiro , Vijay Kumar

Traditional model-based reinforcement learning approaches learn a model of the environment dynamics without explicitly considering how it will be used by the agent. In the presence of misspecified model classes, this can lead to poor…

Machine Learning · Computer Science 2020-10-20 Pierluca D'Oro , Alberto Maria Metelli , Andrea Tirinzoni , Matteo Papini , Marcello Restelli

We derive a policy gradient theorem for Cumulative Prospect Theory (CPT) objectives in finite-horizon Reinforcement Learning (RL), generalizing the standard policy gradient theorem and encompassing distortion-based risk objectives as…

Machine Learning · Computer Science 2026-02-18 Olivier Lepel , Anas Barakat

Policy gradient methods rely on a baseline to measure the relative advantage of an action, ensuring the model reinforces behaviors that outperform its current average capability. In the training of Large Language Models (LLMs) using…

Computation and Language · Computer Science 2026-04-01 Yi-Kai Zhang , Zhiyuan Yao , Hongyan Hao , Yueqing Sun , Qi Gu , Hui Su , Xunliang Cai , De-Chuan Zhan , Han-Jia Ye

We introduce the Graded Transformer framework, a new class of sequence models that embeds algebraic inductive biases through grading transformations on vector spaces. Extending Graded Neural Networks (GNNs), we propose two architectures:…

Machine Learning · Computer Science 2025-09-03 Tony Shaska

Traditional policy gradient methods are fundamentally flawed. Natural gradients converge quicker and better, forming the foundation of contemporary Reinforcement Learning such as Trust Region Policy Optimization (TRPO) and Proximal Policy…

Machine Learning · Computer Science 2022-09-07 W. J. A. van Heeswijk

Many problems at the intersection of combinatorics and computer science require solving for a permutation that optimally matches, ranks, or sorts some data. These problems usually have a task-specific, often non-differentiable objective…

Machine Learning · Computer Science 2018-05-21 Patrick Emami , Sanjay Ranka

Reinforcement learning has been widely applied to enhance the reasoning capabilities of large language models. Extending the inference limits of smaller models has become a prominent research focus. However, algorithms such as Group…

Artificial Intelligence · Computer Science 2025-10-10 Hao Wu , Wei Liu

While Group Relative Policy Optimization (GRPO) offers a powerful framework for LLM post-training, its effectiveness in open-ended domains like Machine Translation hinges on accurate intra-group ranking. We identify that standard Scalar…

Computation and Language · Computer Science 2026-02-17 Sen Yang , Shanbo Cheng , Lu Xu , Jianbing Zhang , Shujian Huang

This paper introduces Group Sequence Policy Optimization (GSPO), our stable, efficient, and performant reinforcement learning algorithm for training large language models. Unlike previous algorithms that adopt token-level importance ratios,…

Machine Learning · Computer Science 2025-07-29 Chujie Zheng , Shixuan Liu , Mingze Li , Xiong-Hui Chen , Bowen Yu , Chang Gao , Kai Dang , Yuqiong Liu , Rui Men , An Yang , Jingren Zhou , Junyang Lin