English
Related papers

Related papers: Trust-Region-Free Policy Optimization for Stochast…

200 papers

Solving tasks in Reinforcement Learning is no easy feat. As the goal of the agent is to maximize the accumulated reward, it often learns to exploit loopholes and misspecifications in the reward signal resulting in unwanted behavior. While…

Machine Learning · Computer Science 2018-12-27 Chen Tessler , Daniel J. Mankowitz , Shie Mannor

Policy optimization (PO), an essential approach of reinforcement learning for a broad range of system classes, requires significantly more system data than indirect (identification-followed-by-control) methods or behavioral-based direct…

Optimization and Control · Mathematics 2023-09-18 Feiran Zhao , Florian Dörfler , Keyou You

This work studies reinforcement learning (RL) in the context of multi-period supply chains subject to constraints, e.g., on production and inventory. We introduce Distributional Constrained Policy Optimization (DCPO), a novel approach for…

Machine Learning · Computer Science 2023-02-06 Jaime Sabal Bermúdez , Antonio del Rio Chanona , Calvin Tsay

This paper introduces the Trust-Based Optimization (TBO), a novel extension of the island model in evolutionary computation that replaces conventional periodic migrations with a flexible, agent-driven interaction mechanism based on trust or…

Neural and Evolutionary Computing · Computer Science 2025-10-30 Aleksandra Urbańczyk , Krzysztof Czech , Piotr Urbańczyk , Marek Kisiel-Dorohinicki , Aleksander Byrski

There is a recent proliferation of research on the integration of machine learning and optimization. One expansive area within this research stream is predictive-model embedded optimization, which proposes the use of pre-trained predictive…

Machine Learning · Computer Science 2022-10-20 Chenbo Shi , Mohsen Emadikhiav , Leonardo Lozano , David Bergman

Learning control policies for complex, long-horizon tasks is a central challenge in robotics and autonomous systems. Signal Temporal Logic (STL) offers a powerful and expressive language for specifying such tasks, but its non-Markovian…

Robotics · Computer Science 2025-10-02 Yue Meng , Fei Chen , Chuchu Fan

Recent advances in constrained reinforcement learning (RL) have endowed reinforcement learning with certain safety guarantees. However, deploying existing constrained RL algorithms in continuous control tasks with general hard constraints…

Machine Learning · Computer Science 2023-12-22 Shutong Ding , Jingya Wang , Yali Du , Ye Shi

Enforcing state-wise safety constraints is critical for the application of reinforcement learning (RL) in real-world problems, such as autonomous driving and robot manipulation. However, existing safe RL methods only enforce state-wise…

Machine Learning · Computer Science 2024-10-03 Weiye Zhao , Feihan Li , Yifan Sun , Yujie Wang , Rui Chen , Tianhao Wei , Changliu Liu

We propose a stochastic nonconvex optimization algorithm that achieves almost sure $\tilde{\mathcal{O}}(\epsilon^{-1.5})$ iteration complexity for problems with smooth objective functions and gradients only observable with noise. The…

Optimization and Control · Mathematics 2026-04-30 Yunsoo Ha , Sara Shashaani , Quoc Tran-dinh

In many applications of mathematical optimization, one may wish to optimize an objective function without access to its derivatives. These situations call for derivative-free optimization (DFO) methods. Among the most successful approaches…

Optimization and Control · Mathematics 2025-12-11 Abraar Chaudhry , Katya Scheinberg

Online and offline RLHF methods, such as PPO and DPO, have been highly successful in aligning AI with human preferences. Despite their success, however, these methods suffer from fundamental limitations: (a) Models trained with RLHF can…

Machine Learning · Computer Science 2025-04-15 Eugene Choi , Arash Ahmadian , Matthieu Geist , Oilvier Pietquin , Mohammad Gheshlaghi Azar

In RL, given a prompt, we sample a group of completions from a model and score them. Two questions follow: which completions should gain probability mass, and how should the parameters move to realize that change? Standard policy-gradient…

Machine Learning · Computer Science 2026-04-08 Jean Kaddour

Centralized training with decentralized execution (CTDE) is a standard framework for cooperative multi-agent policy-gradient reinforcement learning, allowing agents to learn from joint information while acting from local observations.…

Machine Learning · Computer Science 2026-05-12 Chulabhaya Wijesundara , Andrea Baisero , Zhongheng Li , Gregory Castañón , Alan Carlin , Christopher Amato

Recent years have witnessed a tremendous improvement of deep reinforcement learning. However, a challenging problem is that an agent may suffer from inefficient exploration, particularly for on-policy methods. Previous exploration methods…

Machine Learning · Computer Science 2020-02-17 Ling Pan , Qingpeng Cai , Longbo Huang

In this work we introduce the stochastic nonlinear constrained derivative-free optimization method (S)NOWPAC (Stochastic Nonlinear Optimization With Path-Augmented Constraints). The method extends the derivative-free optimizer NOWPAC to be…

Optimization and Control · Mathematics 2022-01-24 F. Menhorn , F. Augustin , H. -J. Bungartz , Y. M. Marzouk

Much of the recent success of deep reinforcement learning has been driven by regularized policy optimization (RPO) algorithms with strong performance across multiple domains. In this family of methods, agents are trained to maximize…

Machine Learning · Computer Science 2022-03-24 Ted Moskovitz , Michael Arbel , Jack Parker-Holder , Aldo Pacchiano

Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorithm. Despite its ubiquity, we argue that the core ratio…

Machine Learning · Computer Science 2026-05-27 Penghui Qi , Xiangxin Zhou , Zichen Liu , Tianyu Pang , Chao Du , Min Lin , Wee Sun Lee

Proximal policy optimization(PPO) has been proposed as a first-order optimization method for reinforcement learning. We should notice that an exterior penalty method is used in it. Often, the minimizers of the exterior penalty functions…

Machine Learning · Computer Science 2018-12-18 Cheng Zeng , Hongming Zhang

Recent advancements in Reinforcement Learning (RL), particularly Group Relative Policy Optimization (GRPO), have significantly enhanced the reasoning capabilities of Large Language Models. However, applying these problem-centric…

Computation and Language · Computer Science 2026-05-26 Yihong Tang , Kehai Chen , Liang Yue , Benyou Wang , Min Zhang

Under interpolation-type assumptions such as the strong growth condition, stochastic optimization methods can attain convergence rates comparable to full-batch methods, but their performance, particularly for SGD, remains highly sensitive…

Optimization and Control · Mathematics 2026-04-16 Aike Yang , Hao Wang
‹ Prev 1 4 5 6 7 8 10 Next ›