English
Related papers

Related papers: ANO: A Principled Approach to Robust Policy Optimi…

200 papers

In recent years, reinforcement learning (RL) has gained increasing attention in control engineering. Especially, policy gradient methods are widely used. In this work, we improve the tracking performance of proximal policy optimization…

Machine Learning · Computer Science 2021-07-21 Jana Mayer , Johannes Westermann , Juan Pedro Gutiérrez H. Muriedas , Uwe Mettin , Alexander Lampe

We propose Process-Aware Policy Optimization (PAPO), a method that integrates process-level evaluation into Group Relative Policy Optimization (GRPO) through decoupled advantage normalization, to address two limitations of existing reward…

Artificial Intelligence · Computer Science 2026-04-06 Zelin Tan , Zhouliang Yu , Bohan Lin , Zijie Geng , Hejia Geng , Yudong Zhang , Mulei Zhang , Yang Chen , Shuyue Hu , Zhenfei Yin , Chen Zhang , Lei Bai

Model-free reinforcement learning methods such as the Proximal Policy Optimization algorithm (PPO) have successfully applied in complex decision-making problems such as Atari games. However, these methods suffer from high variances and high…

Machine Learning · Computer Science 2018-11-20 Feiyang Pan , Qingpeng Cai , An-Xiang Zeng , Chun-Xiang Pan , Qing Da , Hualin He , Qing He , Pingzhong Tang

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for post-training reasoning models. However, group-based methods such as Group Relative Policy Optimization (GRPO) face a critical dilemma in…

Machine Learning · Computer Science 2026-04-07 Yuning Wu , Ke Wang , Devin Chen , Kai Wei

While Direct Preference Optimization (DPO) has become the de facto approach for aligning Large Vision-Language Models (LVLMs), it suffers from Likelihood Displacement, where the probability of both chosen and rejected responses collapses.…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Kaili Huang , Hongming Zhang , Rui Shen , Linjun Dai , Jiahao Wang , Hanming Deng , Lewei Lu

Single-trajectory reinforcement learning (RL) methods aim to optimize policies from datasets consisting of (prompt, response, reward) triplets, where scalar rewards are directly available. This supervision format is highly practical, as it…

Machine Learning · Computer Science 2025-12-23 Bilal Faye , Hanane Azzag , Mustapha Lebbah

Direct Preference Optimisation (DPO) has emerged as a powerful method for aligning Large Language Models (LLMs) with human preferences, offering a stable and efficient alternative to approaches that use Reinforcement learning via Human…

Artificial Intelligence · Computer Science 2025-05-06 Sarvesh Shashidhar , Ritik , Nachiketa Patil , Suraj Racha , Ganesh Ramakrishnan

Direct alignment methods typically train large language models (LLMs) by contrasting the likelihoods of preferred and dispreferred responses. While effective at capturing relative preferences, these methods are widely observed to suppress…

Computation and Language · Computer Science 2025-12-04 Kaiyang Guo , Yinchuan Li , Zhitang Chen

Tremendous progress has been made in reinforcement learning (RL) over the past decade. Most of these advancements came through the continual development of new algorithms, which were designed using a combination of mathematical derivations,…

Machine Learning · Computer Science 2022-10-14 Chris Lu , Jakub Grudzien Kuba , Alistair Letcher , Luke Metz , Christian Schroeder de Witt , Jakob Foerster

Model-based reinforcement learning approaches leverage a forward dynamics model to support planning and decision making, which, however, may fail catastrophically if the model is inaccurate. Although there are several existing methods…

Machine Learning · Computer Science 2020-09-30 Hang Lai , Jian Shen , Weinan Zhang , Yong Yu

Offline preference optimization methods are efficient for large language models (LLMs) alignment. Direct Preference optimization (DPO)-like learning, one of the most popular approaches, stands out for its efficiency in reward modeling.…

Machine Learning · Computer Science 2026-05-26 Xiaobo Wang , Zixia Jia , Jiaqi Li , Qi Liu , Zilong Zheng

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

Reinforcement Learning with Verifiable Rewards (RLVR) enhances Large Language Model (LLM) reasoning but suffers from advantage collapse on ``hard samples'' where all rollouts fail. This lack of variance eliminates crucial learning signals.…

Machine Learning · Computer Science 2026-05-08 Xinyu Lu , Kaiqi Zhang , Jinglin Yang , Boxi Cao , Yaojie Lu , Hongyu Lin , Min He , Xianpei Han , Le Sun

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

This paper provides a self-contained, from-scratch, exposition of key algorithms for instruction tuning of models: SFT, Rejection Sampling, REINFORCE, Trust Region Policy Optimization (TRPO), Proximal Policy Optimization (PPO), Group…

Computation and Language · Computer Science 2025-10-22 Rohit Patel

Safety alignment of large language models remains brittle under domain shift and noisy preference supervision. Most existing robust alignment methods focus on uncertainty in alignment data, while overlooking optimization-induced fragility…

Machine Learning · Computer Science 2026-05-22 Yonghui Yang , Wenjian Tao , Jilong Liu , Xingyu Zhu , Junfeng Fang , Weibiao Huang , Le Wu , Richang Hong , Tat-Sent Chua

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

Offline reinforcement learning (RL), also known as batch RL, aims to optimize policy from a large pre-recorded dataset without interaction with the environment. This setting offers the promise of utilizing diverse, pre-collected datasets to…

Machine Learning · Computer Science 2021-01-05 Qiang He , Xinwen Hou

Safe Reinforcement Learning (RL) often faces significant issues such as constraint violations and instability, necessitating the use of constrained policy optimization, which seeks optimal policies while ensuring adherence to specific…

Machine Learning · Computer Science 2025-08-07 Ning Yang , Pengyu Wang , Guoqing Liu , Haifeng Zhang , Pin Lv , Jun Wang

Adaptive robust optimization (ARO) extends static robust optimization by allowing decisions to depend on the realized uncertainty - weakly dominating static solutions within the modeled uncertainty set. However, ARO makes previous…

Optimization and Control · Mathematics 2025-11-20 Karl Zhu , Dimitris Bertsimas