no code implementations • 27 Apr 2024 • Dapeng Li, Hang Dong, Lu Wang, Bo Qiao, Si Qin, QIngwei Lin, Dongmei Zhang, Qi Zhang, Zhiwei Xu, Bin Zhang, Guoliang Fan
The entire framework has a message module and an action module.
no code implementations • 26 Dec 2023 • Tiezheng Guo, Qingwen Yang, Chen Wang, Yanyi Liu, Pan Li, Jiawei Tang, Dapeng Li, Yingyou Wen
Large language model (LLM) has achieved outstanding performance on various downstream tasks with its powerful natural language understanding and zero-shot capability, but LLM still suffers from knowledge limitation.
no code implementations • 14 Dec 2023 • Dapeng Li, Na Lou, Bin Zhang, Zhiwei Xu, Guoliang Fan
Parameter sharing, as an important technique in multi-agent systems, can effectively solve the scalability issue in large-scale agent problems.
no code implementations • 23 Nov 2023 • Bin Zhang, Hangyu Mao, Jingqing Ruan, Ying Wen, Yang Li, Shao Zhang, Zhiwei Xu, Dapeng Li, Ziyue Li, Rui Zhao, Lijuan Li, Guoliang Fan
The remarkable progress in Large Language Models (LLMs) opens up new avenues for addressing planning and decision-making problems in Multi-Agent Systems (MAS).
no code implementations • 13 May 2023 • Bin Zhang, Hangyu Mao, Lijuan Li, Zhiwei Xu, Dapeng Li, Rui Zhao, Guoliang Fan
Our research contributes to the development of an effective and adaptable asynchronous action coordination method that can be widely applied to various task types and environmental configurations in MAS.
no code implementations • 28 Apr 2023 • Dapeng Li, Zhiwei Xu, Bin Zhang, Guoliang Fan
Centralized training with decentralized execution (CTDE) is a widely-used learning paradigm that has achieved significant success in complex tasks.
no code implementations • 25 Apr 2023 • Dapeng Li, Zhiwei Xu, Bin Zhang, Guoliang Fan
In addition, our structure can be applied to various existing mainstream reinforcement learning algorithms with minor modifications and can deal with the problem with a variable number of agents.
no code implementations • 20 Apr 2023 • Bin Zhang, Lijuan Li, Zhiwei Xu, Dapeng Li, Guoliang Fan
In multi-agent reinforcement learning (MARL), self-interested agents attempt to establish equilibrium and achieve coordination depending on game structure.
no code implementations • 18 Apr 2023 • Neng Wan, Dapeng Li, Naira Hovakimyan, Petros G. Voulgaris
Fundamental limitations or performance trade-offs/limits are important properties and constraints of control and filtering systems.
no code implementations • 21 Mar 2023 • Dapeng Li, Feiyang Pan, Jia He, Zhiwei Xu, Dandan Tu, Guoliang Fan
In high-dimensional time-series analysis, it is essential to have a set of key factors (namely, the style factors) that explain the change of the observed variable.
no code implementations • 4 Feb 2023 • Zhiwei Xu, Bin Zhang, Dapeng Li, Guangchong Zhou, Zeren Zhang, Guoliang Fan
Value decomposition methods have gained popularity in the field of cooperative multi-agent reinforcement learning.
no code implementations • 6 Jun 2022 • Zhiwei Xu, Bin Zhang, Dapeng Li, Zeren Zhang, Guangchong Zhou, Hao Chen, Guoliang Fan
Almost all multi-agent reinforcement learning algorithms without communication follow the principle of centralized training with decentralized execution.
no code implementations • 20 Apr 2022 • Zhiwei Xu, Dapeng Li, Bin Zhang, Yuan Zhan, Yunpeng Bai, Guoliang Fan
Recently, model-based agents have achieved better performance than model-free ones using the same computational budget and training time in single-agent environments.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 8 Apr 2022 • Neng Wan, Dapeng Li, Lin Song, Naira Hovakimyan
A simplified analysis is performed on the Bode-type filtering sensitivity trade-off integrals, which capture the sensitivity characteristics of the estimate and estimation error with respect to the process input and estimated signal in continuous- and discrete-time linear time-invariant filtering systems.
no code implementations • 7 Mar 2022 • Bin Zhang, Yunpeng Bai, Zhiwei Xu, Dapeng Li, Guoliang Fan
The application of deep reinforcement learning in multi-agent systems introduces extra challenges.
no code implementations • 14 Oct 2021 • Zhiwei Xu, Yunpeng Bai, Bin Zhang, Dapeng Li, Guoliang Fan
Recently, some challenging tasks in multi-agent systems have been solved by some hierarchical reinforcement learning methods.
Hierarchical Reinforcement Learning Multi-agent Reinforcement Learning +4
no code implementations • 22 Jun 2021 • Zhiwei Xu, Dapeng Li, Yunpeng Bai, Guoliang Fan
In the real world, many tasks require multiple agents to cooperate with each other under the condition of local observations.
Distributional Reinforcement Learning reinforcement-learning +3
no code implementations • 8 Jun 2021 • Junyan Liu, Shuai Li, Dapeng Li
Our algorithm not only achieves near-optimal regret in the stochastic setting, but also obtains a regret with an additive term of corruption in the corrupted setting, while maintaining efficient communication.
no code implementations • 13 May 2021 • Zhiwei Xu, Yunpeng Bai, Dapeng Li, Bin Zhang, Guoliang Fan
As one of the solutions to the decentralized partially observable Markov decision process (Dec-POMDP) problems, the value decomposition method has achieved significant results recently.
Multi-agent Reinforcement Learning reinforcement-learning +3
no code implementations • 24 Feb 2021 • Kazuma Nagao, Dapeng Li, Ludwig Mathey
We develop a squeezed-field path-integral representation for BCS superconductors utilizing a generalized completeness relation of squeezed-fermionic coherent states.
Superconductivity
no code implementations • NeurIPS 2020 • Neng Wan, Dapeng Li, Naira Hovakimyan
This paper introduces the $f$-divergence variational inference ($f$-VI) that generalizes variational inference to all $f$-divergences.
no code implementations • WS 2017 • Mingbo Ma, Dapeng Li, Kai Zhao, Liang Huang
This paper describes Oregon State University's submissions to the shared WMT'17 task "multimodal translation task I".