English
Related papers

Related papers: Beyond Fixed Morphologies: Learning Graph Policies…

200 papers

Policy gradient methods hold great potential for solving complex continuous control tasks. Still, their training efficiency can be improved by exploiting structure within the optimization problem. Recent work indicates that supervised…

Machine Learning · Computer Science 2024-03-19 Jan Schneider , Pierre Schumacher , Simon Guist , Le Chen , Daniel Häufle , Bernhard Schölkopf , Dieter Büchler

Group Relative Policy Optimization (GRPO) has been shown to be an effective algorithm when an accurate reward model is available. However, such a highly reliable reward model is not available in many real-world tasks. In this paper, we…

Machine Learning · Computer Science 2026-01-12 Yuki Ichihara , Yuu Jinnai , Tetsuro Morimura , Mitsuki Sakamoto , Ryota Mitsuhashi , Eiji Uchibe

Video action models are an appealing foundation for Vision--Language--Action systems because they can learn visual dynamics from large-scale video data and transfer this knowledge to downstream robot control. Yet current diffusion-based…

Policy evaluation is a key process in reinforcement learning. It assesses a given policy using estimation of the corresponding value function. When using a parameterized function to approximate the value, it is common to optimize the set of…

Machine Learning · Computer Science 2019-01-24 Shirli Di-Castro Shashua , Shie Mannor

Morphology-aware policy learning is a means of enhancing policy sample efficiency by aggregating data from multiple agents. These types of policies have previously been shown to help generalize over dynamic, kinematic, and limb…

Communication networks form the backbone of our society. Topology control algorithms optimize the topology of such communication networks. Due to the importance of communication networks, a topology control algorithm should guarantee…

Software Engineering · Computer Science 2018-05-10 Roland Kluge , Michael Stein , Gergely Varró , Andy Schürr , Matthias Hollick , Max Mühlhäuser

Reinforcement learning (RL) is a promising tool to solve robust optimal well control problems where the model parameters are highly uncertain, and the system is partially observable in practice. However, RL of robust control policies often…

Machine Learning · Computer Science 2022-07-14 Atish Dixit , Ahmed H. ElSheikh

Post-training plays a crucial role in refining and aligning large language models to meet specific tasks and human preferences. While recent advancements in post-training techniques, such as Group Relative Policy Optimization (GRPO),…

Artificial Intelligence · Computer Science 2025-10-28 Kaichen Zhang , Yuzhong Hong , Junwei Bao , Hongfei Jiang , Yang Song , Dingqian Hong , Hui Xiong

Direct Preference Optimization (DPO) aligns language models using pairwise preference comparisons, offering a simple and effective alternative to Reinforcement Learning (RL) from human feedback. However, in many practical settings, training…

Machine Learning · Computer Science 2026-05-11 Ning Liu , Chuanneng Sun , Kristina Klinkner , Shervin Malmasi

Five new algorithms were proposed in order to optimize well conditioning of structural matrices. Along with decreasing the size and duration of analyses, minimizing analytical errors is a critical factor in the optimal computer analysis of…

Numerical Analysis · Mathematics 2021-09-21 Farzad S. Dizaji , Mehrdad S. Dizaji

Proximal Policy Optimization (PPO) is a popular deep policy gradient algorithm. In standard implementations, PPO regularizes policy updates with clipped probability ratios, and parameterizes policies with either continuous Gaussian…

Machine Learning · Computer Science 2020-09-24 Chloe Ching-Yun Hsu , Celestine Mendler-Dünner , Moritz Hardt

Medical Image Grounding (MIG), which involves localizing specific regions in medical images based on textual descriptions, requires models to not only perceive regions but also deduce spatial relationships of these regions. Existing…

Machine Learning · Computer Science 2025-07-08 Huihui Xu , Yuanpeng Nie , Hualiang Wang , Ying Chen , Wei Li , Junzhi Ning , Lihao Liu , Hongqiu Wang , Lei Zhu , Jiyao Liu , Xiaomeng Li , Junjun He

Trust-region algorithms can be applied to very abstract optimization problems because they do not require a specific direction of descent or gradient. This has lead to recent interest in them, in particular in the area of integer optimal…

Optimization and Control · Mathematics 2025-06-12 Paul Manns

Modern policy gradient algorithms, such as TRPO and PPO, outperform vanilla policy gradient in many RL tasks. Questioning the common belief that enforcing approximate trust regions leads to steady policy improvement in practice, we show…

Machine Learning · Computer Science 2025-05-27 Tao Wang , Ruipeng Zhang , Sicun Gao

Contracts are complex documents featuring detailed formal structures, explicit and implicit dependencies and rich semantic content. Given these document properties, contract drafting and manual examination of contracts have proven to be…

Artificial Intelligence · Computer Science 2025-11-11 Moriya Dechtiar , Daniel Martin Katz , Mari Sundaresan , Sylvain Jaume , Hongming Wang

Group-based reinforcement learning (RL) methods have achieved remarkable success in improving the performance of large language models (LLMs) and have been rapidly extended to agentic tasks. However, their credit assignment relies heavily…

Machine Learning · Computer Science 2026-05-27 Xin Cheng , Shuo He , Lang Feng , HaiYang Xu , Ming Yan , Lei Feng , Bo An

We consider the problem of learning control policies that optimize a reward function while satisfying constraints due to considerations of safety, fairness, or other costs. We propose a new algorithm, Projection-Based Constrained Policy…

Machine Learning · Computer Science 2020-10-08 Tsung-Yen Yang , Justinian Rosca , Karthik Narasimhan , Peter J. Ramadge

Uncertainties in contact dynamics and object geometry remain significant barriers to robust robotic manipulation. Caging mitigates these uncertainties by constraining an object's mobility without requiring precise contact modeling. However,…

In tabular case, when the reward and environment dynamics are known, policy evaluation can be written as $\bm{V}_{\bm{\pi}} = (I - \gamma P_{\bm{\pi}})^{-1} \bm{r}_{\bm{\pi}}$, where $P_{\bm{\pi}}$ is the state transition matrix given…

Machine Learning · Computer Science 2019-09-23 Sitao Luan , Xiao-Wen Chang , Doina Precup

Reinforcement learning with verifiable rewards (RLVR) has become a practical route to improve large language model reasoning, and Group Relative Policy Optimization (GRPO) is a widely used optimizer in this setting. However, RLVR training…

Machine Learning · Computer Science 2026-05-14 Tue Le , Linh Ngo Van , Trung Le