中文
相关论文

相关论文: Platform-Agnostic Reinforcement Learning Framework…

200 篇论文

Reinforcement learning (RL) agents with pre-specified reward functions cannot provide guaranteed safety across variety of circumstances that an uncertain system might encounter. To guarantee performance while assuring satisfaction of safety…

人工智能 · 计算机科学 2021-04-20 Aquib Mustafa , Majid Mazouchi , Subramanya Nageshrao , Hamidreza Modares

In this paper, a novel approach is introduced which utilizes a Rapidly-exploring Random Graph to improve sampling-based autonomous exploration of unknown environments with unmanned ground vehicles compared to the current state of the art.…

机器人学 · 计算机科学 2021-09-15 Marco Steinbrink , Philipp Koch , Bernhard Jung , Stefan May

Autonomous navigation is a fundamental task for robot vacuum cleaners in indoor environments. Since their core function is to clean entire areas, robots inevitably encounter dead zones in cluttered and narrow scenarios. Existing planning…

机器人学 · 计算机科学 2025-03-06 Han Zheng , Jiale Zhang , Mingyang Jiang , Peiyuan Liu , Danni Liu , Tong Qin , Ming Yang

There have been many recent advances on provably efficient Reinforcement Learning (RL) in problems with rich observation spaces. However, all these works share a strong realizability assumption about the optimal value function of the true…

机器学习 · 计算机科学 2021-06-23 Christoph Dann , Yishay Mansour , Mehryar Mohri , Ayush Sekhari , Karthik Sridharan

Exploration algorithms for reinforcement learning typically replace or augment the reward function with an additional ``intrinsic'' reward that trains the agent to seek previously unseen states of the environment. Here, we consider an…

机器学习 · 计算机科学 2025-09-30 Kevin McKee , Eric Alt , Andrew Grebenisan , Mick van Gelderen , Gary Miguel

Reinforcement Learning (RL) in partially observable environments poses significant challenges due to the complexity of learning under uncertainty. While additional information, such as that available in simulations, can enhance training,…

机器学习 · 计算机科学 2026-03-16 Yueheng Li , Guangming Xie , Zongqing Lu

This paper introduces SANGO (Socially Aware Navigation through Grouped Obstacles), a novel method that ensures socially appropriate behavior by dynamically grouping obstacles and adhering to social norms. Using deep reinforcement learning,…

机器人学 · 计算机科学 2024-12-02 Rahath Malladi , Amol Harsh , Arshia Sangwan , Sunita Chauhan , Sandeep Manjanna

Multimodal Large Language Models (MLLMs) excel in vision-language reasoning but often struggle with structured perception tasks requiring precise localization and robustness. We propose a reinforcement learning framework that augments Group…

计算机视觉与模式识别 · 计算机科学 2025-10-08 Xu Jia

Reinforcement learning has been established over the past decade as an effective tool to find optimal control policies for dynamical systems, with recent focus on approaches that guarantee safety during the learning and/or execution phases.…

系统与控制 · 电气工程与系统科学 2021-10-06 S M Nahid Mahmud , Scott A Nivison , Zachary I. Bell , Rushikesh Kamalapurkar

A default assumption in the design of reinforcement-learning algorithms is that a decision-making agent always explores to learn optimal behavior. In sufficiently complex environments that approach the vastness and scale of the real world,…

机器学习 · 计算机科学 2024-07-23 Dilip Arumugam , Saurabh Kumar , Ramki Gummadi , Benjamin Van Roy

Traditional robotic approaches rely on an accurate model of the environment, a detailed description of how to perform the task, and a robust perception system to keep track of the current state. On the other hand, reinforcement learning…

机器人学 · 计算机科学 2020-05-27 Michelle A. Lee , Carlos Florensa , Jonathan Tremblay , Nathan Ratliff , Animesh Garg , Fabio Ramos , Dieter Fox

Identifying uncertainty and taking mitigating actions is crucial for safe and trustworthy reinforcement learning agents, especially when deployed in high-risk environments. In this paper, risk sensitivity is promoted in a model-based…

机器学习 · 计算机科学 2021-11-10 Stefan Radic Webster , Peter Flach

Nonlinear model predictive control (NMPC) is typically restricted to short, finite horizons to limit the computational burden of online optimization. As a result, global planning frameworks are frequently necessary to avoid local minima…

机器人学 · 计算机科学 2025-06-11 Adam Polevoy , Mark Gonzales , Marin Kobilarov , Joseph Moore

Recent advances in deep reinforcement learning (RL) have achieved strong results on high-dimensional control tasks, but applying RL to reachability problems raises a fundamental mismatch: reachability seeks to maximize the set of states…

机器学习 · 计算机科学 2026-02-18 Oswin So , Eric Yang Yu , Songyuan Zhang , Matthew Cleaveland , Mitchell Black , Chuchu Fan

Approximate nearest neighbor search (ANNS) in high-dimensional spaces is a pivotal challenge in the field of machine learning. In recent years, graph-based methods have emerged as the superior approach to ANNS, establishing a new state of…

机器学习 · 计算机科学 2024-07-11 Kejing Lu , Chuan Xiao , Yoshiharu Ishikawa

Logistics optimization nowadays is becoming one of the hottest areas in the AI community. In the past year, significant advancements in the domain were achieved by representing the problem in a form of graph. Another promising area of…

机器学习 · 计算机科学 2022-05-26 Zangir Iklassov , Dmitrii Medvedev

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…

机器学习 · 计算机科学 2021-07-02 Mónika Farsang , Luca Szegletes

We propose a method to tackle the problem of mapless collision-avoidance navigation where humans are present using 2D laser scans. Our proposed method uses ego-safety to measure collision from the robot's perspective while social-safety to…

机器人学 · 计算机科学 2020-11-20 Jun Jin , Nhat M. Nguyen , Nazmus Sakib , Daniel Graves , Hengshuai Yao , Martin Jagersand

Model-free continuous control for robot navigation tasks using Deep Reinforcement Learning (DRL) that relies on noisy policies for exploration is sensitive to the density of rewards. In practice, robots are usually deployed in cluttered…

机器人学 · 计算机科学 2023-02-24 Mingyu Cai , Erfan Aasi , Calin Belta , Cristian-Ioan Vasile

Zero-shot reinforcement learning is necessary for extracting optimal policies in absence of concrete rewards for fast adaptation to future problem settings. Forward-backward representations (FB) have emerged as a promising method for…

机器学习 · 计算机科学 2025-07-09 Núria Armengol Urpí , Marin Vlastelica , Georg Martius , Stelian Coros