English
Related papers

Related papers: A Parametric Class of Approximate Gradient Updates…

200 papers

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

We propose Orthogonalized Policy Optimization (OPO), a principled framework for large language model alignment derived from optimization in the Hilbert function space L2(pi_k). Lifting policy updates from the probability simplex into…

Machine Learning · Computer Science 2026-02-26 Wang Zixian

Existing policy-gradient methods for auto-regressive language models typically select subsequent tokens one at a time as actions in the policy. While effective for many generation tasks, such an approach may not fully capture the structure…

Computation and Language · Computer Science 2026-02-17 Mufan Xu , Kehai Chen , Xuefeng Bai , Zhengyu Niu , Muyun Yang , Tiejun Zhao , Min Zhang

We revisit the finite time analysis of policy gradient methods in the one of the simplest settings: finite state and action MDPs with a policy class consisting of all stochastic policies and with exact gradient evaluations. There has been…

Machine Learning · Computer Science 2021-12-14 Jalaj Bhandari , Daniel Russo

Proximal Policy Optimization (PPO) is among the most widely used algorithms in reinforcement learning, which achieves state-of-the-art performance in many challenging problems. The keys to its success are the reliable policy updates through…

Machine Learning · Computer Science 2021-07-02 Mónika Farsang , Luca Szegletes

Large Language Models (LLMs) can acquire extensive world knowledge through pre-training on large corpora. However, due to exposure to low-quality data, LLMs may exhibit harmful behavior without aligning with human values. The dominant…

Machine Learning · Computer Science 2023-10-11 Tianhao Wu , Banghua Zhu , Ruoyu Zhang , Zhaojin Wen , Kannan Ramchandran , Jiantao Jiao

Model-based policy optimization is a well-established framework for designing reliable and high-performance controllers across a wide range of control applications. Recently, this approach has been extended to model predictive control…

Systems and Control · Electrical Eng. & Systems 2026-04-15 Riccardo Zuliani , Efe C. Balta , John Lygeros

Linear-parametric optimization, where multiple objectives are combined into a single objective using linear combinations with parameters as coefficients, has numerous links to other fields in optimization and a wide range of application…

Optimization and Control · Mathematics 2025-01-22 Levin Nemesch , Stefan Ruzika , Clemens Thielen , Alina Wittmann

Reinforcement learning algorithms are fundamental to align large language models with human preferences and to enhance their reasoning capabilities. However, current reinforcement learning algorithms often suffer from training instability…

Machine Learning · Computer Science 2025-06-05 Yaru Hao , Li Dong , Xun Wu , Shaohan Huang , Zewen Chi , Furu Wei

Policy gradient methods can solve complex tasks but often fail when the dimensionality of the action-space or objective multiplicity grow very large. This occurs, in part, because the variance on score-based gradient estimators scales…

Machine Learning · Computer Science 2021-11-24 Thomas Spooner , Nelson Vadori , Sumitra Ganesh

Deep Policy Gradient (PG) algorithms employ value networks to drive the learning of parameterized policies and reduce the variance of the gradient estimates. However, value function approximation gets stuck in local optima and struggles to…

Machine Learning · Computer Science 2023-02-21 Enrico Marchesini , Christopher Amato

The most common approaches for solving stochastic resource allocation problems in the research literature is to either use value functions ("dynamic programming") or scenario trees ("stochastic programming") to approximate the impact of a…

Optimization and Control · Mathematics 2020-01-06 Saeed Ghadimi , Raymond T. Perkins , Warren B. Powell

Modern deep learning models require immense computational resources, motivating research into low-precision training. Quantised training addresses this by representing training components in low-bit integers, but typically relies on…

Machine Learning · Computer Science 2025-12-08 Paul Wilson , Fabio Zanasi , George Constantinides

Policy gradient based reinforcement learning algorithms coupled with neural networks have shown success in learning complex policies in the model free continuous action space control setting. However, explicitly parameterized policies are…

Machine Learning · Computer Science 2019-09-30 Oliver Richter , Roger Wattenhofer

In modern deep learning, the models are learned by applying gradient updates using an optimizer, which transforms the updates based on various statistics. Optimizers are often hand-designed and tuning their hyperparameters is a big part of…

Machine Learning · Computer Science 2024-10-08 Gus Kristiansen , Mark Sandler , Andrey Zhmoginov , Nolan Miller , Anirudh Goyal , Jihwan Lee , Max Vladymyrov

While reinforcement learning (RL) has been central to the recent success of large language models (LLMs), RL optimization is notoriously unstable, especially when compared to supervised fine-tuning (SFT). In this work, we investigate the…

Machine Learning · Computer Science 2026-03-03 Hongzhan Chen , Tao Yang , Yuhua Zhu , Shiping Gao , Xiaojun Quan , Ting Yao

Data augmentation is a critical component of deep learning pipelines, enhancing model generalization by increasing dataset diversity. Traditional augmentation strategies rely on manually designed transformations, stochastic sampling, or…

Computer Vision and Pattern Recognition · Computer Science 2025-08-06 Ant Duru , Alptekin Temizel

Black-box policy optimization is a class of reinforcement learning algorithms that explores and updates the policies at the parameter level. This class of algorithms is widely applied in robotics with movement primitives or…

Machine Learning · Computer Science 2022-03-22 Marius Memmel , Puze Liu , Davide Tateo , Jan Peters

Policy gradient algorithms have driven many recent advancements in language model reasoning. An appealing property is their ability to learn from exploration on their own trajectories, a process crucial for fostering diverse and creative…

Machine Learning · Computer Science 2026-03-13 Aleksei Petrenko , Ben Lipkin , Kevin Chen , Erik Wijmans , Marco Cusumano-Towner , Raja Giryes , Philipp Krähenbühl

We introduce a novel reinforcement learning algorithm (AGRO, for Any-Generation Reward Optimization) for fine-tuning large-language models. AGRO leverages the concept of generation consistency, which states that the optimal policy satisfies…

Machine Learning · Computer Science 2025-04-01 Yunhao Tang , Taco Cohen , David W. Zhang , Michal Valko , Rémi Munos