Search Results for author: Jianhong Wang

Found 19 papers, 11 papers with code

Attaining Human`s Desirable Outcomes in Human-AI Interaction via Structural Causal Games

no code implementations26 May 2024 Anjie Liu, Jianhong Wang, Haoxuan Li, Xu Chen, Jun Wang, Samuel Kaski, Mengyue Yang

In human-AI interaction, a prominent goal is to attain human`s desirable outcome with the assistance of AI agents, which can be ideally delineated as a problem of seeking the optimal Nash Equilibrium that matches the human`s desirable outcome.

Tiny Refinements Elicit Resilience: Toward Efficient Prefix-Model Against LLM Red-Teaming

no code implementations21 May 2024 Jiaxu Liu, Xiangyu Yin, Sihao Wu, Jianhong Wang, Meng Fang, Xinping Yi, Xiaowei Huang

With the proliferation of red-teaming strategies for Large Language Models (LLMs), the deficiency in the literature about improving the safety and robustness of LLM defense strategies is becoming increasingly pronounced.

Shapley Value Based Multi-Agent Reinforcement Learning: Theory, Method and Its Application to Energy Network

no code implementations23 Feb 2024 Jianhong Wang

We first extend a game model called convex game and a payoff distribution scheme called Shapley value in cooperative game theory to Markov decision process, named as Markov convex game and Markov Shapley value respectively.

Learning Theory Multi-agent Reinforcement Learning +1

Open Ad Hoc Teamwork with Cooperative Game Theory

1 code implementation23 Feb 2024 Jianhong Wang, Yang Li, Yuan Zhang, Wei Pan, Samuel Kaski

Ad hoc teamwork poses a challenging problem, requiring the design of an agent to collaborate with teammates without prior coordination or joint training.

Aligning Individual and Collective Objectives in Multi-Agent Cooperation

no code implementations19 Feb 2024 Yang Li, WenHao Zhang, Jianhong Wang, Shao Zhang, Yali Du, Ying Wen, Wei Pan

Among the research topics in multi-agent learning, mixed-motive cooperation is one of the most prominent challenges, primarily due to the mismatch between individual and collective goals.

SMAC+ Starcraft +1

Invariant Learning via Probability of Sufficient and Necessary Causes

1 code implementation NeurIPS 2023 Mengyue Yang, Zhen Fang, Yonggang Zhang, Yali Du, Furui Liu, Jean-Francois Ton, Jianhong Wang, Jun Wang

To capture the information of sufficient and necessary causes, we employ a classical concept, the probability of sufficiency and necessary causes (PNS), which indicates the probability of whether one is the necessary and sufficient cause.

Semi-Supervised Dual-Stream Self-Attentive Adversarial Graph Contrastive Learning for Cross-Subject EEG-based Emotion Recognition

no code implementations13 Aug 2023 Weishan Ye, Zhiguo Zhang, Min Zhang, Fei Teng, Li Zhang, Linling Li, Gan Huang, Jianhong Wang, Dong Ni, Zhen Liang

In this paper, a semi-supervised Dual-stream Self-Attentive Adversarial Graph Contrastive learning framework (termed as DS-AGC) is proposed to tackle the challenge of limited labeled data in cross-subject EEG-based emotion recognition.

Contrastive Learning Domain Adaptation +2

Robust Reinforcement Learning in Continuous Control Tasks with Uncertainty Set Regularization

1 code implementation5 Jul 2022 Yuan Zhang, Jianhong Wang, Joschka Boedecker

To deal with unknown uncertainty sets, we further propose a novel adversarial approach to generate them based on the value function.

Continuous Control reinforcement-learning +1

Learning to Estimate and Refine Fluid Motion with Physical Dynamics

1 code implementation21 Jun 2022 Mingrui Zhang, Jianhong Wang, James Tlhomole, Matthew D. Piggott

General optical flow methods are typically designed for rigid body motion, and thus struggle if applied to fluid motion estimation directly.

Motion Estimation Optical Flow Estimation

Blending Data and Physics Against False Data Injection Attack: An Event-Triggered Moving Target Defence Approach

1 code implementation27 Apr 2022 Wangkun Xu, Martin Higgins, Jianhong Wang, Imad M. Jaimoukha, Fei Teng

However, the uncontrollable false positive rate of the data-driven detector and the extra cost of frequent MTD usage limit their wide applications.

Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks

1 code implementation NeurIPS 2021 Jianhong Wang, Wangkun Xu, Yunjie Gu, Wenbin Song, Tim C. Green

This paper presents a problem in power networks that creates an exciting and yet challenging real-world scenario for application of multi-agent reinforcement learning (MARL).

Multi-agent Reinforcement Learning reinforcement-learning +1

SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learning

1 code implementation31 May 2021 Jianhong Wang, Yuan Zhang, Yunjie Gu, Tae-Kyun Kim

This paper studies a theoretical framework for value factorisation with interpretability via Shapley value theory.

Fairness Q-Learning +2

Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System

2 code implementations ICLR 2021 Jianhong Wang, Yuan Zhang, Tae-Kyun Kim, Yunjie Gu

We test HDNO on MultiWoz 2. 0 and MultiWoz 2. 1, the datasets on multi-domain dialogues, in comparison with word-level E2E model trained with RL, LaRL and HDSA, showing improvements on the performance evaluated by automatic evaluation metrics and human evaluation.

Hierarchical Reinforcement Learning reinforcement-learning +2

Shapley Q-value: A Local Reward Approach to Solve Global Reward Games

2 code implementations11 Jul 2019 Jianhong Wang, Yuan Zhang, Tae-Kyun Kim, Yunjie Gu

To deal with this problem, we i) introduce a cooperative-game theoretical framework called extended convex game (ECG) that is a superset of global reward game, and ii) propose a local reward approach called Shapley Q-value.

Multi-agent Reinforcement Learning Policy Gradient Methods

Thermostat-assisted continuously-tempered Hamiltonian Monte Carlo for Bayesian learning

1 code implementation NeurIPS 2018 Rui Luo, Jianhong Wang, Yaodong Yang, Zhanxing Zhu, Jun Wang

We propose a new sampling method, the thermostat-assisted continuously-tempered Hamiltonian Monte Carlo, for Bayesian learning on large datasets and multimodal distributions.

Spatio-temporal Aware Non-negative Component Representation for Action Recognition

no code implementations27 Aug 2016 Jianhong Wang, Tian Lan, Xu Zhang, Limin Luo

This paper presents a novel mid-level representation for action recognition, named spatio-temporal aware non-negative component representation (STANNCR).

Action Recognition Temporal Action Localization

Cannot find the paper you are looking for? You can Submit a new open access paper.