中文
相关论文

相关论文: Improving the Robustness of Reinforcement Learning…

200 篇论文

A reinforcement learning (RL) policy trained in a nominal environment could fail in a new/perturbed environment due to the existence of dynamic variations. Existing robust methods try to obtain a fixed policy for all envisioned dynamic…

机器学习 · 计算机科学 2022-03-10 Yikun Cheng , Pan Zhao , Manan Gandhi , Bo Li , Evangelos Theodorou , Naira Hovakimyan

Reinforcement Learning (RL) is a powerful method for controlling dynamic systems, but its learning mechanism can lead to unpredictable actions that undermine the safety of critical systems. Here, we propose RL with Adaptive Regularization…

机器学习 · 计算机科学 2024-11-01 Haozhe Tian , Homayoun Hamedmoghadam , Robert Shorten , Pietro Ferraro

Reinforcement learning (RL) agents need to be robust to variations in safety-critical environments. While system identification methods provide a way to infer the variation from online experience, they can fail in settings where fast…

机器学习 · 计算机科学 2022-03-07 Annie Xie , Shagun Sodhani , Chelsea Finn , Joelle Pineau , Amy Zhang

Reinforcement learning (RL) offers a compelling data-driven paradigm for synthesizing controllers for complex systems when accurate physical models are unavailable; however, most existing control-oriented RL methods assume stationarity and,…

机器学习 · 计算机科学 2026-04-22 Austin Coursey , Abel Diaz-Gonzalez , Marcos Quinones-Grueiro , Gautam Biswas

Adoption of machine learning (ML)-enabled cyber-physical systems (CPS) are becoming prevalent in various sectors of modern society such as transportation, industrial, and power grids. Recent studies in deep reinforcement learning (DRL) have…

机器学习 · 计算机科学 2020-07-15 Kai Liang Tan , Yasaman Esfandiari , Xian Yeow Lee , Aakanksha , Soumik Sarkar

A policy is said to be robust if it maximizes the reward while considering a bad, or even adversarial, model. In this work we formalize two new criteria of robustness to action uncertainty. Specifically, we consider two scenarios in which…

机器学习 · 计算机科学 2019-05-08 Chen Tessler , Yonathan Efroni , Shie Mannor

This paper considers the problem of real-time control and learning in dynamic systems subjected to parametric uncertainties. We propose a combination of a Reinforcement Learning (RL) based policy in the outer loop suitably chosen to ensure…

机器学习 · 计算机科学 2023-06-13 Anuradha M. Annaswamy , Anubhav Guha , Yingnan Cui , Sunbochen Tang , Peter A. Fisher , Joseph E. Gaudio

Reinforcement learning is a general methodology of adaptive optimal control that has attracted much attention in various fields ranging from video game industry to robot manipulators. Despite its remarkable performance demonstrations, plain…

动力系统 · 数学 2022-06-14 Pavel Osinenko , Grigory Yaremenko , Ilya Osokin

Reinforcement learning (RL) is a general framework for adaptive control, which has proven to be efficient in many domains, e.g., board games, video games or autonomous vehicles. In such problems, an agent faces a sequential decision-making…

机器学习 · 计算机科学 2020-06-16 Olivier Buffet , Olivier Pietquin , Paul Weng

Reinforcement learning (RL) algorithms find applications in inventory control, recommender systems, vehicular traffic management, cloud computing and robotics. The real-world complications of many tasks arising in these domains makes them…

机器学习 · 计算机科学 2021-06-03 Sindhu Padakandla

Ensuring reliability in modern software systems requires rigorous pre-production testing across highly heterogeneous and evolving environments. Because exhaustive evaluation is infeasible, practitioners must decide how to allocate limited…

软件工程 · 计算机科学 2025-10-08 Yu Zhu

Reinforcement learning (RL) has attracted increasing interest for adaptive traffic signal control due to its model-free ability to learn control policies directly from interaction with the traffic environment. However, several challenges…

机器学习 · 计算机科学 2026-03-17 Dickens Kwesiga , Angshuman Guin , Khaled Abdelghany , Michael Hunter

Reinforcement Learning (RL) has demonstrated a huge potential in learning optimal policies without any prior knowledge of the process to be controlled. Model Predictive Control (MPC) is a popular control technique which is able to deal with…

系统与控制 · 计算机科学 2019-04-10 Mario Zanon , Sébastien Gros , Alberto Bemporad

Reinforcement learning (RL) algorithms have been successfully used to develop control policies for dynamical systems. For many such systems, these policies are trained in a simulated environment. Due to discrepancies between the simulated…

系统与控制 · 电气工程与系统科学 2020-11-23 Anubhav Guha , Anuradha Annaswamy

Reinforcement Learning (RL) has recently impressed the world with stunning results in various applications. While the potential of RL is now well-established, many critical aspects still need to be tackled, including safety and stability…

系统与控制 · 电气工程与系统科学 2024-09-23 Mario Zanon , Sébastien Gros

Reinforcement learning (RL) policies often fail under dynamics that differ from training, a gap not fully addressed by domain randomization or existing adversarial RL methods. Distributionally robust RL provides a formal remedy but still…

机器学习 · 计算机科学 2026-04-16 Mintae Kim , Koushil Sreenath

Deep reinforcement learning agents achieve state-of-the-art performance in a wide range of simulated control tasks. However, successful applications to real-world problems remain limited. One reason for this dichotomy is because the learnt…

机器学习 · 计算机科学 2024-11-27 Rory Young , Nicolas Pugeault

Reinforcement Learning (RL) offers a promising framework for autonomous driving by enabling agents to learn control policies through interaction with environments. However, large and high-dimensional action spaces often used to support…

机器人学 · 计算机科学 2025-07-08 Elahe Delavari , Feeza Khan Khanzada , Jaerock Kwon

Due to the proliferation of renewable energy and its intrinsic intermittency and stochasticity, current power systems face severe operational challenges. Data-driven decision-making algorithms from reinforcement learning (RL) offer a…

系统与控制 · 电气工程与系统科学 2021-10-20 Alexander Pan , Yongkyun Lee , Huan Zhang , Yize Chen , Yuanyuan Shi

Safe reinforcement learning (RL) seeks to mitigate unsafe behaviors that arise from exploration during training by reducing constraint violations while maintaining task performance. Existing approaches typically rely on a single policy to…

机器人学 · 计算机科学 2026-05-12 Murad Dawood , Usama Ahmed Siddiquie , Shahram Khorshidi , Maren Bennewitz
‹ 上一页 1 2 3 10 下一页 ›