Global Reward

Global reward optimization in multi-agent systems focuses on designing algorithms that enable agents to collectively maximize a shared objective, rather than individual rewards. Current research emphasizes efficient credit assignment methods, particularly in scenarios with delayed or non-separable rewards, employing techniques like Shapley values and attention mechanisms within frameworks such as centralized training with decentralized execution (CTDE). These advancements are crucial for tackling complex problems in areas like cooperative robotics, network optimization, and resource allocation, where individual agent actions impact a shared global outcome. The development of scalable and robust algorithms for global reward maximization is driving progress in both theoretical understanding and practical applications of multi-agent reinforcement learning.

Papers

October 17, 2024

Ornstein-Uhlenbeck Adaptation as a Mechanism for Learning in Brains and Machines
Jesus Garcia Fernandez, Nasir Ahmad, Marcel van Gerven
New Machine Neuromorphic Computing Functional Mechanism Human Brain Ornstein Uhlenbeck Process Global Reward

June 2, 2024

Global Rewards in Restless Multi-Armed Bandits
Naveen Raman, Zheyuan Ryan Shi, Fei Fang
Multi Armed Bandit Reward Function Restless Multi Armed Bandit Index Policy Dynamic Restless Global Reward

June 14, 2023

Curricular Subgoals for Inverse Reinforcement Learning
Shunyu Liu, Yunpeng Qing, Shuqi Xu, Hongyan Wu, Jiangtao Zhang, Jingyuan Cong, Tianhao Chen, Yunfu Liu, Mingli Song
Imitation Learning Inverse Reinforcement Learning Global Reward

April 15, 2023

STAS: Spatial-Temporal Return Decomposition for Multi-agent Reinforcement Learning
Sirui Chen, Zhaowei Zhang, Yaodong Yang, Yali Du
Multi Agent Reinforcement Learning Temporal Attention Episodic Reinforcement Learning Temporal Credit Assignment Global Reward Return Decomposition

February 8, 2023

Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning
Volodymyr Tkachuk, Seyed Alireza Bakhtiari, Johannes Kirschner, Matej Jusup, Ilija Bogunovic, Csaba Szepesvári
Reinforcement Learning Financial Application Action Space Cooperative Multi Agent Reinforcement Learning Efficient Planning Global Reward Blow Up Algorithm

January 20, 2023

Multi-agent Reinforcement Learning with Graph Q-Networks for Antenna Tuning
Maxime Bouton, Jaeseong Jeong, Jose Outes, Adriano Mendo, Alexandros Nikou
Reinforcement Learning Multi Agent Reinforcement Learning Mobile Network Q Network Global Reward Antenna Tilt

July 12, 2022

Differentially Private Linear Bandits with Partial Distributed Feedback
Fengjiao Li, Xingyu Zhou, Bo Ji
Differential Privacy Human Feedback Linear Bandit Partial Feedback Global Reward

July 7, 2022

Learning-based Autonomous Channel Access in the Presence of Hidden Terminals
Yulin Shao, Yucheng Cai, Taotao Wang, Ziyang Guo, Peng Liu, Jiajun Luo, Deniz Gunduz
Reinforcement Learning Speech Presence Wireless Channel Hidden Backdoor Time Division Multiple Access Global Reward Channel Access