中文
相关论文

相关论文: Platform-Agnostic Reinforcement Learning Framework…

200 篇论文

One of the key challenges to deep reinforcement learning (deep RL) is to ensure safety at both training and testing phases. In this work, we propose a novel technique of unsupervised action planning to improve the safety of on-policy…

机器人学 · 计算机科学 2021-09-30 Hao-Lun Hsu , Qiuhua Huang , Sehoon Ha

Autonomous navigation in underwater environments remains a major challenge due to the absence of GPS, degraded visibility, and the presence of submerged obstacles. This article investigates these issues through the case of the BlueROV2, an…

机器学习 · 计算机科学 2025-12-12 Zamirddine Mari , Mohamad Motasem Nawaf , Pierre Drap

Model-based reinforcement learning is a powerful tool, but collecting data to fit an accurate model of the system can be costly. Exploring an unknown environment in a sample-efficient manner is hence of great importance. However, the…

机器学习 · 计算机科学 2023-04-27 Matthieu Blanke , Marc Lelarge

Deploying Reinforcement Learning (RL) agents in the real-world require that the agents satisfy safety constraints. Current RL agents explore the environment without considering these constraints, which can lead to damage to the hardware or…

机器学习 · 计算机科学 2021-03-17 Harshit Sikchi , Wenxuan Zhou , David Held

Despite Proximal Policy Optimization (PPO) dominating policy gradient methods -- from robotic control to game AI -- its static trust region forces a brittle trade-off: aggressive clipping stifles early exploration, while late-stage updates…

机器学习 · 计算机科学 2025-05-26 Ben Rahman

In this paper, we present an autonomous navigation system for goal-driven exploration of unknown environments through deep reinforcement learning (DRL). Points of interest (POI) for possible navigation directions are obtained from the…

机器人学 · 计算机科学 2021-09-10 Reinis Cimurs , Il Hong Suh , Jin Han Lee

We present a map-less path planning algorithm based on Deep Reinforcement Learning (DRL) for mobile robots navigating in unknown environment that only relies on 40-dimensional raw laser data and odometry information. The planner is trained…

机器人学 · 计算机科学 2020-02-12 Nicolò Botteghi , Beril Sirmacek , Khaled A. A. Mustafa , Mannes Poel , Stefano Stramigioli

Pushing objects through cluttered scenes is a challenging task, especially when the objects to be pushed have initially unknown dynamics and touching other entities has to be avoided to reduce the risk of damage. In this paper, we approach…

机器人学 · 计算机科学 2022-07-18 Nils Dengler , David Großklaus , Maren Bennewitz

Applying reinforcement learning to autonomous driving entails particular challenges, primarily due to dynamically changing traffic flows. To address such challenges, it is necessary to quickly determine response strategies to the changing…

机器人学 · 计算机科学 2022-12-12 Se-Wook Yoo , Chan Kim , Jin-Woo Choi , Seong-Woo Kim , Seung-Woo Seo

In this article, we explore the feasibility of applying proximal policy optimization, a state-of-the-art deep reinforcement learning algorithm for continuous control tasks, on the dual-objective problem of controlling an underactuated…

机器学习 · 计算机科学 2019-12-20 Eivind Meyer , Haakon Robinson , Adil Rasheed , Omer San

Policy-gradient methods such as Proximal Policy Optimization (PPO) are typically updated along a single stochastic gradient direction, leaving the rich local structure of the parameter space unexplored. Previous work has shown that the…

机器学习 · 计算机科学 2025-10-01 Xinyu Zhang , Aishik Deb , Klaus Mueller

Collaborative pursuit-evasion in cluttered environments presents significant challenges due to sparse rewards and constrained Fields of View (FOV). Standard Multi-Agent Reinforcement Learning (MARL) often suffers from inefficient…

机器人学 · 计算机科学 2025-12-11 Jialin Ying , Zhihao Li , Zicheng Dong , Guohua Wu , Yihuan Liao

The behavior decision-making subsystem is a key component of the autonomous driving system, which reflects the decision-making ability of the vehicle and the driver, and is an important symbol of the high-level intelligence of the vehicle.…

机器学习 · 计算机科学 2024-12-31 Zixiang Wang , Hao Yan , Changsong Wei , Junyu Wang , Minheng Xiao

Constrained Reinforcement Learning (RL) aims to maximize the return while adhering to predefined constraint limits, which represent domain-specific safety requirements. In continuous control settings, where learning agents govern system…

机器学习 · 计算机科学 2025-09-12 Somnath Hazra , Pallab Dasgupta , Soumyajit Dey

This paper addresses the problem of maintaining safety during training in Reinforcement Learning (RL), such that the safety constraint violations are bounded at any point during learning. In a variety of RL applications the safety of the…

机器学习 · 计算机科学 2023-12-19 Rohan Mitta , Hosein Hasanbeig , Jun Wang , Daniel Kroening , Yiannis Kantaros , Alessandro Abate

Safe navigation is essential for autonomous systems operating in hazardous environments. Traditional planning methods excel at long-horizon tasks but rely on a predefined graph with fixed distance metrics. In contrast, safe Reinforcement…

机器人学 · 计算机科学 2025-09-12 Meng Feng , Viraj Parimi , Brian Williams

We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent.…

机器学习 · 计算机科学 2017-08-29 John Schulman , Filip Wolski , Prafulla Dhariwal , Alec Radford , Oleg Klimov

We propose a framework for ensuring safe behavior of a reinforcement learning agent when the reward function may be difficult to specify. In order to do this, we rely on the existence of demonstrations from expert policies, and we provide a…

机器学习 · 计算机科学 2018-11-22 Jessie Huang , Fa Wu , Doina Precup , Yang Cai

Autonomous UAV inspection of confined industrial infrastructure, such as ventilation ducts, demands robust navigation policies where collisions are unacceptable. While Deep Reinforcement Learning (DRL) offers a powerful paradigm for…

This research introduces a novel application of a masked Proximal Policy Optimization (PPO) algorithm from the field of deep reinforcement learning (RL), for determining the most efficient sequence of space debris visitation, utilizing the…

机器学习 · 计算机科学 2024-09-26 Agni Bandyopadhyay , Guenther Waxenegger-Wilfing