Single Agent RL

Single-agent reinforcement learning (RL) focuses on training a single agent to optimize its actions within an environment to maximize cumulative rewards. Current research emphasizes improving sample efficiency and theoretical guarantees, particularly within the context of large or continuous state spaces using linear function approximation and algorithms like Nash Q-learning. This field is crucial for developing robust and efficient AI agents across various applications, from resource management to complex control systems, and ongoing work addresses challenges like adversarial attacks and the development of standardized evaluation protocols to ensure reliable progress.

Papers

July 31, 2024

Multi-agent reinforcement learning for the control of three-dimensional Rayleigh-Bénard convection
Joel Vasanth, Jean Rabault, Francisco Alcántara-Ávila, Mikael Mortensen, Ricardo Vinuesa
Deep Reinforcement Learning Multi Agent Reinforcement Learning External Control Control Policy Multi Agent RL Single Agent RL Rayleigh B\'enard Convection

May 10, 2024

A First Introduction to Cooperative Multi-Agent Reinforcement Learning
Christopher Amato
Multi Agent Reinforcement Learning Cooperative Multi Agent Reinforcement Learning Independent Q Learning Single Agent RL Decentralized Policy Gradient

April 11, 2024

Differentially Private Reinforcement Learning with Self-Play
Dan Qiao, Yu-Xiang Wang
Multi Agent Reinforcement Learning Differential Privacy Self Play Episodic Markov Decision Process Multi Agent RL Single Agent RL Private Reinforcement Learning

February 11, 2024

Refined Sample Complexity for Markov Games with Independent Linear Function Approximation
Yan Dai, Qiwen Cui, Simon S. Du
Multi Agent Reinforcement Learning Multi Agent Markov Game Single Agent Linear Function Approximation Single Agent RL

April 25, 2023

Centralized control for multi-agent RL in a complex Real-Time-Strategy game
Roger Creus Castanyer
Multi Agent Reinforcement Learning Learning Agent Centralized Control RL Agent Real Time Strategy Multi Agent RL Single Agent RL

March 1, 2023

Finite-sample Guarantees for Nash Q-learning with Linear Function Approximation
Pedro Cisneros-Velarde, Sanmi Koyejo
Multi Agent Reinforcement Learning Q Learning Nash Equilibrium Linear Function Approximation Finite Sample Guarantee General Sum Markov Game Single Agent RL

October 3, 2022

Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games
Shicong Cen, Yuejie Chi, Simon S. Du, Lin Xiao
Multi Agent Reinforcement Learning Policy OpTimization Markov Game Last Iterate Convergence Zero Sum Markov Game Single Agent RL

September 21, 2022

Towards a Standardised Performance Evaluation Protocol for Cooperative MARL
Rihab Gorsane, Omayma Mahjoub, Ruan de Kock, Roland Dubb, Siddarth Singh, Arnu Pretorius
Multi Agent Reinforcement Learning Cooperative Multi Agent Reinforcement Learning Meta Analysis Decision Problem Single Agent RL Evaluation Protocol

June 4, 2022

Reward Poisoning Attacks on Offline Multi-Agent Reinforcement Learning
Young Wu, Jeremy McMahan, Xiaojin Zhu, Qiaomin Xie
Multi Agent Nash Equilibrium Offline Multi Agent Reinforcement Learning Single Agent RL Reward Poisoning Attack

May 19, 2022

Sparse Adversarial Attack in Multi-agent Reinforcement Learning
Yizheng Hu, Zhihua Zhang
Adversarial Attack Multi Agent Reinforcement Learning Cooperative Multi Agent Reinforcement Learning MARL Algorithm Single Agent RL Sparse Adversarial Attack