中文
相关论文

相关论文: Beyond Scalar Rewards: Distributional Reinforcemen…

200 篇论文

Reinforcement Learning (RL) can mitigate the causal confusion and distribution shift inherent to imitation learning (IL). However, applying RL to end-to-end autonomous driving (E2E-AD) remains an open problem for its training difficulty,…

机器人学 · 计算机科学 2025-10-28 Zhenjie Yang , Xiaosong Jia , Qifeng Li , Xue Yang , Maoqing Yao , Junchi Yan

Reinforcement learning (RL) has shown a promising performance in learning optimal policies for a variety of sequential decision-making tasks. However, in many real-world RL problems, besides optimizing the main objectives, the agent is…

机器学习 · 计算机科学 2021-07-30 Ashkan B. Jeddi , Nariman L. Dehghani , Abdollah Shafieezadeh

Recent advances in reinforcement learning (RL) enable its use on increasingly complex tasks, but the lack of formal safety guarantees still limits its application in safety-critical settings. A common practical approach is to augment the RL…

机器学习 · 计算机科学 2026-02-12 Donggeon David Oh , Duy P. Nguyen , Haimin Hu , Jaime F. Fisac

Standard reinforcement learning (RL) optimizes policies for reward but imposes few constraints on how decisions evolve over time. As a result, policies may achieve high performance while exhibiting temporally incoherent behavior such as…

机器学习 · 计算机科学 2026-04-24 Sukesh Subaharan

Deep reinforcement learning (DRL) allows a system to interact with its environment and take actions by training an efficient policy that maximizes self-defined rewards. In autonomous driving, it can be used as a strategy for high-level…

机器人学 · 计算机科学 2024-07-02 Xibo Li , Shruti Patel , Christof Büskens

The learning inefficiency of reinforcement learning (RL) from scratch hinders its practical application towards continuous robotic tracking control, especially for high-dimensional robots. This work proposes a data-informed residual…

系统与控制 · 电气工程与系统科学 2024-06-10 Cong Li , Fangzhou Liu , Yongchao Wang , Martin Buss

In recent years, $Q$-learning has become indispensable for model-free reinforcement learning (MFRL). However, it suffers from well-known problems such as under- and overestimation bias of the value, which may adversely affect the policy…

机器学习 · 计算机科学 2021-02-09 Youngmin Oh , Jinwoo Shin , Eunho Yang , Sung Ju Hwang

Autonomous driving has been at the forefront of public interest, and a pivotal debate to widespread concerns is safety in the transportation system. Deep reinforcement learning (DRL) has been applied to autonomous driving to provide…

人工智能 · 计算机科学 2022-01-21 Zehong Cao , Jie Yun

Autonomous driving decision-making is a challenging task due to the inherent complexity and uncertainty in traffic. For example, adjacent vehicles may change their lane or overtake at any time to pass a slow vehicle or to help traffic flow.…

We study off-dynamics Reinforcement Learning (RL), where the policy training and deployment environments are different. To deal with this environmental perturbation, we focus on learning policies robust to uncertainties in transition…

机器学习 · 计算机科学 2024-10-01 Zhishuai Liu , Weixin Wang , Pan Xu

Frontier models have demonstrated exceptional capabilities following the integration of task-reward-based reinforcement learning (RL) into their training pipelines, enabling systems to evolve from pure reasoning models into sophisticated…

机器学习 · 计算机科学 2026-04-20 Sarthak Mittal , Leo Gagnon , Guillaume Lajoie

Preference-aligned robot navigation in human environments is typically achieved through learning-based approaches, utilizing user feedback or demonstrations for personalization. However, personal preferences are subject to change and might…

机器人学 · 计算机科学 2025-10-21 Jorge de Heuvel , Tharun Sethuraman , Maren Bennewitz

Multi-task representation learning (MTRL) is an approach that learns shared latent representations across related tasks, facilitating collaborative learning that improves the overall learning efficiency. This paper studies MTRL for…

机器学习 · 计算机科学 2026-04-07 Yaoze Guo , Shana Moothedath

Deep Reinforcement Learning (DRL) has made considerable advances in simulated and physical robot control tasks, especially when problems admit a fully observed Markov Decision Process (MDP) formulation. When observations only partially…

机器人学 · 计算机科学 2026-03-24 Lingheng Meng , Rob Gorbet , Michael Burke , Dana Kulić

Reinforcement learning (RL) is a powerful data-driven control method that has been largely explored in autonomous driving tasks. However, conventional RL approaches learn control policies through trial-and-error interactions with the…

机器人学 · 计算机科学 2021-11-03 Tianyu Shi , Dong Chen , Kaian Chen , Zhaojian Li

Many sequential decision problems involve finding a policy that maximizes total reward while obeying safety constraints. Although much recent research has focused on the development of safe reinforcement learning (RL) algorithms that…

机器学习 · 计算机科学 2021-07-20 Nolan Wagener , Byron Boots , Ching-An Cheng

We study the problem of inverse reinforcement learning (IRL), where the learning agent recovers a reward function using expert demonstrations. Most of the existing IRL techniques make the often unrealistic assumption that the agent has…

机器学习 · 计算机科学 2021-12-20 Franck Djeumou , Murat Cubuktepe , Craig Lennon , Ufuk Topcu

Reinforcement Learning (RL) has the potential to surpass human performance in driving without needing any expert supervision. Despite its promise, the state-of-the-art in sensorimotor self-driving is dominated by imitation learning methods…

机器人学 · 计算机科学 2023-09-19 Ege Onat Özsüer , Barış Akgün , Fatma Güney

Constrained reinforcement learning is to maximize the expected reward subject to constraints on utilities/costs. However, the training environment may not be the same as the test one, due to, e.g., modeling error, adversarial attack,…

机器学习 · 计算机科学 2022-09-16 Yue Wang , Fei Miao , Shaofeng Zou

Reinforcement learning (RL) approaches based on Markov Decision Processes (MDPs) are predominantly applied in the robot joint space, often relying on limited task-specific information and partial awareness of the 3D environment. In…

机器人学 · 计算机科学 2026-03-09 Bingkun Huang , Yuhe Gong , Zewen Yang , Tianyu Ren , Luis Figueredo