1 code implementation • 22 Apr 2024 • Zichuan Liu, Zefan Wang, Linjie Xu, Jinyu Wang, Lei Song, Tianchun Wang, Chunlin Chen, Wei Cheng, Jiang Bian
The advent of large language models (LLMs) has revolutionized the field of natural language processing, yet they might be attacked to produce harmful content.
1 code implementation • 16 Apr 2024 • Jinmei Liu, Wenbin Li, Xiangyu Yue, Shilin Zhang, Chunlin Chen, Zhi Wang
Finally, by interleaving pseudo samples with real ones of the new task, we continually update the state and behavior generators to model progressively diverse behaviors, and regularize the multi-head critic via behavior cloning to mitigate forgetting.
1 code implementation • 16 Jan 2024 • Zichuan Liu, Yingying Zhang, Tianchun Wang, Zefan Wang, Dongsheng Luo, Mengnan Du, Min Wu, Yi Wang, Chunlin Chen, Lunting Fan, Qingsong Wen
Explaining multivariate time series is a compound challenge, as it requires identifying important locations in the time series and matching complex temporal patterns.
1 code implementation • 6 Oct 2023 • Wei Lv, Chao Zhang, Huaxiong Li, Xiuyi Jia, Chunlin Chen
We further consider the graph noise of projected data caused by missing samples and use a tensor-decomposition based graph filter for robust clustering. JPLTD decomposes the original tensor into an intrinsic tensor and a sparse tensor.
1 code implementation • 1 Aug 2023 • Junyi Wang, Yuanyang Zhu, Zhi Wang, Yan Zheng, Jianye Hao, Chunlin Chen
Evolutionary reinforcement learning (ERL) algorithms recently raise attention in tackling complex reinforcement learning (RL) problems due to high parallelism, while they are prone to insufficient exploration or model collapse without carefully tuning hyperparameters (aka meta-parameters).
no code implementations • 16 Jul 2023 • Hongyu Ding, Yuanze Tang, Qing Wu, Bo wang, Chunlin Chen, Zhi Wang
Existing reward shaping methods for goal-conditioned RL are typically built on distance metrics with a linear and isotropic distribution, which may fail to provide sufficient information about the ever-changing environment with high complexity.
no code implementations • 12 May 2023 • Qingpeng Zhao, Yuanyang Zhu, Zichuan Liu, Zhi Wang, Chunlin Chen
In cooperative multi-agent reinforcement learning (MARL), the environmental stochasticity and uncertainties will increase exponentially when the number of agents increases, which puts hard pressure on how to come up with a compact latent representation from partial observation for boosting value decomposition.
no code implementations • 9 May 2023 • Hailan Ma, Zhenhong Sun, Daoyi Dong, Chunlin Chen, Herschel Rabitz
Quantum state tomography (QST) is the process of reconstructing the state of a quantum system (mathematically described as a density matrix) through a series of different measurements, which can be solved by learning a parameterized function to translate experimentally measured statistics into physical density matrices.
no code implementations • 15 Sep 2022 • Zichuan Liu, Yuanyang Zhu, Zhi Wang, Yang Gao, Chunlin Chen
While achieving tremendous success in various fields, existing multi-agent reinforcement learning (MARL) with a black-box neural network architecture makes decisions in an opaque manner that hinders humans from understanding the learned knowledge and how input observations influence decisions.
Multi-agent Reinforcement Learning reinforcement-learning +3
1 code implementation • 16 Jul 2022 • Zizheng Huang, Haoxing Chen, Ziqi Wen, Chao Zhang, Huaxiong Li, Bo wang, Chunlin Chen
Contrastive learning (CL) continuously achieves significant breakthroughs across multiple domains.
no code implementations • 22 May 2022 • Zhi Wang, Chunlin Chen, Daoyi Dong
We use a Dirichlet process mixture to model the non-stationary task distribution, which captures task relatedness by estimating the likelihood of task-to-cluster assignments and clusters the task models in a latent space.
no code implementations • 16 Apr 2022 • Jinmei Liu, Zhi Wang, Chunlin Chen, Daoyi Dong
Second, BPR algorithms usually require numerous samples to estimate the probability distribution of the tabular-based observation model, which may be expensive and even infeasible to learn and maintain, especially when using the state transition sample as the signal.
no code implementations • 6 Mar 2022 • Donghan Xie, Zhi Wang, Chunlin Chen, Daoyi Dong
In this paper, we propose a new method based on local communication learning to tackle the multi-agent RL (MARL) challenge within a large number of agents coexisting.
1 code implementation • 13 Dec 2021 • Haoxing Chen, Huaxiong Li, Yaohui Li, Chunlin Chen
Under the guidance of attribute modality, our method can learn enhanced semantic-aware representation for classification.
1 code implementation • 27 Sep 2021 • Haoxing Chen, Huaxiong Li, Yaohui Li, Chunlin Chen
Finally, we propose using an image patch-matching module to calculate the distance between dense local representations, thus determining which category the query image belongs to in the support set.
Ranked #16 on Few-Shot Image Classification on FC100 5-way (1-shot)
no code implementations • 15 Apr 2021 • Yuanyang Zhu, Zhi Wang, Chunlin Chen, Daoyi Dong
In this paper, we focus on efficient navigation with the RL technique and combine the advantages of these two kinds of methods into a rule-based RL (RuRL) algorithm for reducing the sample complexity and cost of time.
no code implementations • 4 Apr 2021 • Mingjiang Liu, Chengli Xiao, Chunlin Chen
To narrow this gap, in this paper, we propose a novel perspective-corrected spatial referring expression generation (PcSREG) approach for human-robot interaction by considering the selection of reference frames.
no code implementations • 21 Mar 2021 • Yaohui Li, Huaxiong Li, Haoxing Chen, Chunlin Chen
Few-shot image classification aims at recognizing unseen categories with a small number of labeled training data.
no code implementations • 21 Mar 2021 • Haoxing Chen, Huaxiong Li, Yaohui Li, Chunlin Chen
Moreover, a Multi-level Metric Learning (MML) method is proposed, which not only calculates the pixel-level similarity but also considers the similarity of part-level features and global-level features.
no code implementations • 6 Jan 2021 • Qing Wei, Hailan Ma, Chunlin Chen, Daoyi Dong
In this paper, a novel training paradigm inspired by quantum computation is proposed for deep reinforcement learning (DRL) with experience replay.
no code implementations • 31 Dec 2020 • Hailan Ma, Daoyi Dong, Steven X. Ding, Chunlin Chen
Deep reinforcement learning has been recognized as an efficient technique to design optimal strategies for different complex systems without prior knowledge of the control landscape.
no code implementations • 30 Nov 2020 • Haoxing Chen, Huaxiong Li, Yaohui Li, Chunlin Chen
Then, an adaptive task attention module is proposed to select the most important LRs among the entire task.
1 code implementation • 9 Oct 2020 • Zhi Wang, Chunlin Chen, Daoyi Dong
Instance novelty measures an instance's difference from the previous optimum in the original environment, while instance quality corresponds to how well an instance performs in the new environment.
1 code implementation • 28 Jul 2020 • Zhi Wang, Chunlin Chen, Daoyi Dong
In this paper, we propose LifeLong Incremental Reinforcement Learning (LLIRL), a new incremental algorithm for efficient lifelong adaptation to dynamic environments.
no code implementations • 22 May 2020 • Hailan Ma, Chang-Jiang Huang, Chunlin Chen, Daoyi Dong, Yuanlong Wang, Re-Bing Wu, Guo-Yong Xiang
Quantum autoencoders which aim at compressing quantum information in a low-dimensional latent space lie in the heart of automatic data compression in the field of quantum information.
no code implementations • 8 Jun 2018 • Chunlin Chen, Daoyi Dong, Han-Xiong Li, Jian Chu, Tzyh-Jong Tarn
In this paper, a fidelity-based probabilistic Q-learning (FPQL) approach is presented to naturally solve this problem and applied for learning control of quantum systems.
1 code implementation • IEEE International Conference on Systems, Man and Cybernetics (SMC) 2017 • Yuenan Hou, Lifeng Liu, Qing Wei, Xudong Xu, Chunlin Chen
Recently, a state-of-the-art algorithm, called deep deterministic policy gradient (DDPG), has achieved good performance in many continuous control tasks in the MuJoCo simulator.
no code implementations • 13 Feb 2017 • Daoyi Dong, Xi Xing, Hailan Ma, Chunlin Chen, Zhixin Liu, Herschel Rabitz
Numerical results are presented to demonstrate the excellent performance of the improved machine learning algorithm for these two classes of quantum robust control problems.
no code implementations • 21 Aug 2015 • Luowei Zhou, Pei Yang, Chunlin Chen, Yang Gao
In this paper, a novel algorithm named negotiation-based MARL with sparse interactions (NegoSI) is presented.
Multi-agent Reinforcement Learning reinforcement-learning +2
2 code implementations • 21 Oct 2008 • Daoyi Dong, Chunlin Chen, Hanxiong Li, Tzyh-Jong Tarn
The state (action) set can be represented with a quantum superposition state and the eigen state (eigen action) can be obtained by randomly observing the simulated quantum state according to the collapse postulate of quantum measurement.