Zobrazeno 1 - 10
of 57
pro vyhledávání: '"Gu, Shangding"'
Autor:
Zhang, Ruiqi, Hou, Jing, Walter, Florian, Gu, Shangding, Guan, Jiayi, Röhrbein, Florian, Du, Yali, Cai, Panpan, Chen, Guang, Knoll, Alois
Reinforcement Learning (RL) is a potent tool for sequential decision-making and has achieved performance surpassing human capabilities across many challenging real-world tasks. As the extension of RL in the multi-agent system domain, multi-agent RL (
Externí odkaz:
http://arxiv.org/abs/2408.09675
Autor:
Gu, Shangding, Shi, Laixi, Ding, Yuhao, Knoll, Alois, Spanos, Costas, Wierman, Adam, Jin, Ming
Safe reinforcement learning (RL) is crucial for deploying RL agents in real-world applications, as it aims to maximize long-term rewards while satisfying safety constraints. However, safe RL often suffers from sample inefficiency, requiring extensive
Externí odkaz:
http://arxiv.org/abs/2405.20860
Autor:
Zheng, Zhi, Gu, Shangding
Ensuring safety in MARL, particularly when deploying it in real-world applications such as autonomous driving, emerges as a critical challenge. To address this challenge, traditional safe MARL methods extend MARL approaches to incorporate safety cons
Externí odkaz:
http://arxiv.org/abs/2405.18209
In numerous reinforcement learning (RL) problems involving safety-critical systems, a key challenge lies in balancing multiple objectives while simultaneously meeting all stringent safety constraints. To tackle this issue, we propose a primal-based f
Externí odkaz:
http://arxiv.org/abs/2405.16390
Ensuring the safety of Reinforcement Learning (RL) is crucial for its deployment in real-world applications. Nevertheless, managing the trade-off between reward and safety during exploration presents a significant challenge. Improving reward performa
Externí odkaz:
http://arxiv.org/abs/2405.01677
The development of Large Language Models (LLMs) often confronts challenges stemming from the heavy reliance on human annotators in the reinforcement learning with human feedback (RLHF) framework, or the frequent and costly external queries tied to th
Externí odkaz:
http://arxiv.org/abs/2403.08694
Autor:
Gu, Shangding
Large Language Models (LLMs) have demonstrated remarkable capabilities for reinforcement learning (RL) models, such as planning and reasoning capabilities. However, the problems of LLMs and RL model collaboration still need to be solved. In this stud
Externí odkaz:
http://arxiv.org/abs/2401.06603
The promotion of large-scale applications of reinforcement learning (RL) requires efficient training computation. While existing parallel RL frameworks encompass a variety of RL algorithms and parallelization techniques, the excessively burdensome co
Externí odkaz:
http://arxiv.org/abs/2312.06126
Autor:
Mhamed, Jaafar, Gu, Shangding
Incorporating safety is an essential prerequisite for broadening the practical applications of reinforcement learning in real-world scenarios. To tackle this challenge, Constrained Markov Decision Processes (CMDPs) are leveraged, which introduce a di
Externí odkaz:
http://arxiv.org/abs/2311.00880
Deployment of Reinforcement Learning (RL) algorithms for robotics applications in the real world requires ensuring the safety of the robot and its environment. Safe Robot RL (SRRL) is a crucial step towards achieving human-robot coexistence. In this
Externí odkaz:
http://arxiv.org/abs/2302.13137