Research Presentation


Bayesian Soft Actor-Critic: A Directed Acyclic Strategy Graph Based Deep Reinforcement Learning

A strategy describes the general plan of an agent achieving short-term or long-term goals under uncertainty, which involves setting sub-goals and priorities, determining action se- quences to fulfill the tasks, and mobilizing resources to execute the actions. [TIST Paper | 01/24/2024]


Innate-Values-driven Reinforcement Learning for Cooperative Multi-Agent Systems

Innate values describe agents’ intrinsic motivations, which reflect their inherent interests and preferences to pursue goals and drive them to develop diverse skills satisfying their various needs. [arXv Paper | 01/10/2024]


Edge Computing based Human-Robot Cognitive Fusion: A Medical Case Study in the Autism Spectrum Disorder Therapy

People with ASD usually have problems with social communication, regular interaction, and restricted or repetitive behaviors or interests. Robot-assisted therapy (RAT) is an emerging field that has attracted many researchers to study and benefited children with ASD. [arXv Paper | 01/01/2024]


A Hierarchical Game-Theoretic Decision-Making for Cooperative Multiagent Systems Under the Presence of Adversarial Agents

This research proposes a new network model called the Game-Theoretic Utility Tree (GUT), combining the core principles of game theory and utility theory to achieve cooperative decision-making for MAS in adversarial environments. [SAC Paper | 03/28/2023]

Talks


Hierarchical Needs-driven Self-adaptive Multi-Agent Systems: From Individual Utilities to Swarm Intelligence

I was invited by the Cognitive Robotics and AI Lab (CRAI) in the College of Aeronautics and Engineering at Kent State University to give a talk about my current research on AI and Robotics. [Invited Talk | 06/06/2023]

News