CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Community

Y Liu, B Guo, N Li, Y Ding, Z Zhang… - … Surveys & Tutorials, 2024 - ieeexplore.ieee.org
Artificial Intelligence of Things (AIoT) is an emerging frontier based on the deep fusion of
Internet of Things (IoT) and Artificial Intelligence (AI) technologies. The fundamental goal of …

Multi-agent incentive communication via decentralized teammate modeling

L Yuan, J Wang, F Zhang, C Wang, Z Zhang… - Proceedings of the …, 2022 - ojs.aaai.org
Effective communication can improve coordination in cooperative multi-agent reinforcement
learning (MARL). One popular communication scheme is exchanging agents' local …

ATA-MAOPT: Multi-Agent Online Policy Transfer using Attention Mechanism with Time Abstraction

C Wang, X Zhu - IEEE Access, 2024 - ieeexplore.ieee.org
Multi-agent deep reinforcement learning inherits one of the shortcomings of reinforcement
learning, which is that a very large number of experimental episodes need to be performed …

Adaptive Curriculum Learning: Optimizing Reinforcement Learning through Dynamic Task Sequencing

M Nesterova, A Skrynnik, A Panov - Optical Memory and Neural Networks, 2024 - Springer
Curriculum learning in reinforcement learning utilizes a strategy that sequences simpler
tasks in order to optimize the learning process for more complex problems. Typically …

[PDF][PDF] Fast Teammate Adaptation in the Presence of Sudden Policy Change (Supplementary Material)

Z Zhang, L Yuan, L Li, K Xue, C Jia, C Guan, C Qian… - proceedings.mlr.press
Chinese restaurant process (CRP)[Blei and Frazier, 2010] is a discrete-time stochastic
process that defines a prior distribution over the cluster structures, which can be described …